revert: remove renovate schedule change (moved to separate PR)

CronJob runs at 0/6/12/18h. Old 2-4 PM window never had a run
inside it, so Renovate never created PRs. Shift to 5-7 PM so the
18:00 run lands in the window. nixpkgs-qt staggered to 7-9 PM.

.gitattributes

@@ -0,0 +1,3 @@
+
+# Use bd merge for beads JSONL files
+.beads/issues.jsonl merge=beads

.gitea/workflows/ci.yml

@@ -48,7 +48,9 @@ jobs:
             custom-mcrcon-rbw
             custom-tea-rbw
             custom-rclone-torbox-setup
-            custom-nextcloud-talk-desktop
+            custom-beads
+            custom-gastown
+            custom-perles
             qt-pinned-jellyfin-media-player
             qt-pinned-stremio
             nix-deck-kernel

AGENTS.md

@@ -6,6 +6,10 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 This is a NixOS configuration repository using flakes, managing multiple machines and home-manager configurations. The repository follows a modular architecture with reusable "roles" that can be composed for different machines.
 
+## Issue Tracking
+
+This repository uses `beads` for issue tracking and management. Run `bd quickstart` to get an overview of the system at the start of every session.
+
 ## Architecture
 
 ### Flake Structure

flake.lock

@@ -1,13 +1,33 @@
 {
   "nodes": {
+    "beads": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs-unstable"
+        ]
+      },
+      "locked": {
+        "lastModified": 1773070962,
+        "narHash": "sha256-kHZXx+kygpVholOBsuQocCtksHo5ZWYskP64qK2Kjh0=",
+        "owner": "steveyegge",
+        "repo": "beads",
+        "rev": "9604d30b7c746f9f04f6dea5f82996f71bb66073",
+        "type": "github"
+      },
+      "original": {
+        "owner": "steveyegge",
+        "repo": "beads",
+        "type": "github"
+      }
+    },
     "doomemacs": {
       "flake": false,
       "locked": {
-        "lastModified": 1774080407,
+        "lastModified": 1772615218,
-        "narHash": "sha256-FYbalilgDFjIVwK+D6DjDos1IMmMGA20lRf8k6Ykm1Y=",
+        "narHash": "sha256-z+3c0AGkrMf1xZ+pq57aVp4Zo4KsqFMIjEVzSZinghc=",
         "owner": "doomemacs",
         "repo": "doomemacs",
-        "rev": "d8d75443d39d95f3c5256504eb838e0acc62ef44",
+        "rev": "d23bbe87721c61f4d5a605f2914b32780bb89949",
         "type": "github"
       },
       "original": {
@@ -26,11 +46,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1774256052,
+        "lastModified": 1772706147,
-        "narHash": "sha256-7OLaUBQCOCt4XXbjHq9xqBopOJJpbV6Cl8mWdMLzazc=",
+        "narHash": "sha256-C0UMYQg3KBU6+L8TLfQ/s60O6/Tiu/JpN8C/WiIH9DU=",
         "owner": "nix-community",
         "repo": "emacs-overlay",
-        "rev": "c4b7915a9467aa611c7346d2322514cdf8c1ba45",
+        "rev": "54af2ae96631311dc4d2686a07e4f472fb36f516",
         "type": "github"
       },
       "original": {
@@ -39,6 +59,48 @@
         "type": "github"
       }
     },
+    "flake-utils": {
+      "inputs": {
+        "systems": "systems"
+      },
+      "locked": {
+        "lastModified": 1731533236,
+        "narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
+    "gastown": {
+      "inputs": {
+        "beads": [
+          "beads"
+        ],
+        "flake-utils": "flake-utils",
+        "nixpkgs": [
+          "nixpkgs-unstable"
+        ]
+      },
+      "locked": {
+        "lastModified": 1773088127,
+        "narHash": "sha256-gJFayiBYrF0Q99AOQH29uq0Mli8KRfwReYeAh5H5evY=",
+        "owner": "steveyegge",
+        "repo": "gastown",
+        "rev": "8da798be0663af74be7960844b90038e51769203",
+        "type": "github"
+      },
+      "original": {
+        "owner": "steveyegge",
+        "repo": "gastown",
+        "type": "github"
+      }
+    },
     "google-cookie-retrieval": {
       "inputs": {
         "nixpkgs": [
@@ -66,11 +128,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1774274588,
+        "lastModified": 1772633058,
-        "narHash": "sha256-dnHvv5EMUgTzGZmA+3diYjQU2O6BEpGLEOgJ1Qe9LaY=",
+        "narHash": "sha256-SO7JapRy2HPhgmqiLbfnW1kMx5rakPMKZ9z3wtRLQjI=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "cf9686ba26f5ef788226843bc31fda4cf72e373b",
+        "rev": "080657a04188aca25f8a6c70a0fb2ea7e37f1865",
         "type": "github"
       },
       "original": {
@@ -87,11 +149,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1774292006,
+        "lastModified": 1772633327,
-        "narHash": "sha256-RI5sjkDEwIiD2eZHd7iM6ZqPoPWZvn3KdBiMumA3IYI=",
+        "narHash": "sha256-jl+DJB2DUx7EbWLRng+6HNWW/1/VQOnf0NsQB4PlA7I=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "3cea83bf84abeb72581bdee380fa526d7fcd7e5b",
+        "rev": "5a75730e6f21ee624cbf86f4915c6e7489c74acc",
         "type": "github"
       },
       "original": {
@@ -109,11 +171,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1774168156,
+        "lastModified": 1772517207,
-        "narHash": "sha256-+pwZSARdlM2RQQ6V0q76+WMKW9aNIcxkSOIThcz/f0A=",
+        "narHash": "sha256-qxHfxqbigqBTn//U4leIS5he22Wp1GS0+zmwGV7Pozs=",
         "owner": "Jovian-Experiments",
         "repo": "Jovian-NixOS",
-        "rev": "939caad56508542d0f19cab963e2bc693f5f2831",
+        "rev": "7ca1501c2d80900b5967baea4d42581f84b388dd",
         "type": "github"
       },
       "original": {
@@ -148,14 +210,14 @@
         "doomemacs": "doomemacs",
         "emacs-overlay": "emacs-overlay",
         "nixpkgs": [],
-        "systems": "systems"
+        "systems": "systems_2"
       },
       "locked": {
-        "lastModified": 1774265710,
+        "lastModified": 1772716420,
-        "narHash": "sha256-ar8pFUSAxXhV7DpVRjNvgviWuqOqWPAImb4MM7lSh5Y=",
+        "narHash": "sha256-T3UEKNTGqBl44AQ0+0OIpiWMXeQ8+4QW/akSc4yeL2A=",
         "owner": "marienz",
         "repo": "nix-doom-emacs-unstraightened",
-        "rev": "f6022b9192e034a817373692ede18a9319cf9730",
+        "rev": "be3ecb81a85be302e27d46ff32a1e251e444327d",
         "type": "github"
       },
       "original": {
@@ -188,11 +250,11 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1774244481,
+        "lastModified": 1772598333,
-        "narHash": "sha256-4XfMXU0DjN83o6HWZoKG9PegCvKvIhNUnRUI19vzTcQ=",
+        "narHash": "sha256-YaHht/C35INEX3DeJQNWjNaTcPjYmBwwjFJ2jdtr+5U=",
         "owner": "nixos",
         "repo": "nixpkgs",
-        "rev": "4590696c8693fea477850fe379a01544293ca4e2",
+        "rev": "fabb8c9deee281e50b1065002c9828f2cf7b2239",
         "type": "github"
       },
       "original": {
@@ -204,11 +266,11 @@
     },
     "nixpkgs-qt": {
       "locked": {
-        "lastModified": 1774244481,
+        "lastModified": 1772598333,
-        "narHash": "sha256-4XfMXU0DjN83o6HWZoKG9PegCvKvIhNUnRUI19vzTcQ=",
+        "narHash": "sha256-YaHht/C35INEX3DeJQNWjNaTcPjYmBwwjFJ2jdtr+5U=",
         "owner": "nixos",
         "repo": "nixpkgs",
-        "rev": "4590696c8693fea477850fe379a01544293ca4e2",
+        "rev": "fabb8c9deee281e50b1065002c9828f2cf7b2239",
         "type": "github"
       },
       "original": {
@@ -220,11 +282,11 @@
     },
     "nixpkgs-unstable": {
       "locked": {
-        "lastModified": 1774106199,
+        "lastModified": 1772624091,
-        "narHash": "sha256-US5Tda2sKmjrg2lNHQL3jRQ6p96cgfWh3J1QBliQ8Ws=",
+        "narHash": "sha256-QKyJ0QGWBn6r0invrMAK8dmJoBYWoOWy7lN+UHzW1jc=",
         "owner": "nixos",
         "repo": "nixpkgs",
-        "rev": "6c9a78c09ff4d6c21d0319114873508a6ec01655",
+        "rev": "80bdc1e5ce51f56b19791b52b2901187931f5353",
         "type": "github"
       },
       "original": {
@@ -234,6 +296,22 @@
         "type": "github"
       }
     },
+    "perles": {
+      "flake": false,
+      "locked": {
+        "lastModified": 1772661365,
+        "narHash": "sha256-kMlvIpfGMBkN5D1W0O1fcqUiH3dyobcH0GRRLCX7GGo=",
+        "owner": "zjrosen",
+        "repo": "perles",
+        "rev": "326ff1938dfe073daab7939762ce2f44c2ee74a1",
+        "type": "github"
+      },
+      "original": {
+        "owner": "zjrosen",
+        "repo": "perles",
+        "type": "github"
+      }
+    },
     "plasma-manager": {
       "inputs": {
         "home-manager": [
@@ -282,6 +360,8 @@
     },
     "root": {
       "inputs": {
+        "beads": "beads",
+        "gastown": "gastown",
         "google-cookie-retrieval": "google-cookie-retrieval",
         "home-manager": "home-manager",
         "home-manager-unstable": "home-manager-unstable",
@@ -291,6 +371,7 @@
         "nixpkgs": "nixpkgs",
         "nixpkgs-qt": "nixpkgs-qt",
         "nixpkgs-unstable": "nixpkgs-unstable",
+        "perles": "perles",
         "plasma-manager": "plasma-manager",
         "plasma-manager-unstable": "plasma-manager-unstable"
       }
@@ -309,6 +390,21 @@
         "repo": "default",
         "type": "github"
       }
+    },
+    "systems_2": {
+      "locked": {
+        "lastModified": 1681028828,
+        "narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
+        "owner": "nix-systems",
+        "repo": "default",
+        "rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
+        "type": "github"
+      },
+      "original": {
+        "owner": "nix-systems",
+        "repo": "default",
+        "type": "github"
+      }
     }
   },
   "root": "root",

flake.nix

@@ -45,6 +45,22 @@
       inputs.nixpkgs.follows = "nixpkgs-unstable";
     };
 
+    beads = {
+      url = "github:steveyegge/beads";
+      inputs.nixpkgs.follows = "nixpkgs-unstable";
+    };
+
+    gastown = {
+      url = "github:steveyegge/gastown";
+      inputs.nixpkgs.follows = "nixpkgs-unstable";
+      inputs.beads.follows = "beads";
+    };
+
+    perles = {
+      url = "github:zjrosen/perles";
+      flake = false;  # No flake.nix upstream yet
+    };
+
     nix-doom-emacs-unstraightened = {
       url = "github:marienz/nix-doom-emacs-unstraightened";
       # Don't follow nixpkgs to avoid rebuild issues with emacs-overlay
@@ -52,340 +68,306 @@
     };
   };
 
-  outputs =
+  outputs = { self, nixpkgs, nixpkgs-unstable, ... } @ inputs: let
-    {
+    # Shared overlay function to reduce duplication across module sets
-      self,
+    # Parameters:
-      nixpkgs,
+    #   unstableOverlays: Additional overlays to apply when importing nixpkgs-unstable
-      nixpkgs-unstable,
+    mkBaseOverlay = { unstableOverlays ? [] }: (final: prev: {
-      ...
+      unstable = import nixpkgs-unstable {
-    }@inputs:
+        system = prev.stdenv.hostPlatform.system;
-    let
+        config.allowUnfree = true;
-      # Shared overlay function to reduce duplication across module sets
+        overlays = unstableOverlays;
-      # Parameters:
+      };
-      #   unstableOverlays: Additional overlays to apply when importing nixpkgs-unstable
+      # Separate nixpkgs for qt5webengine-heavy packages to avoid rebuild churn
-      mkBaseOverlay =
+      qt-pinned = import inputs.nixpkgs-qt {
-        {
+        system = prev.stdenv.hostPlatform.system;
-          unstableOverlays ? [ ],
+        config = {
-        }:
+          allowUnfree = true;
-        (final: prev: {
+          permittedInsecurePackages = [ "qtwebengine-5.15.19" ];
-          unstable = import nixpkgs-unstable {
-            system = prev.stdenv.hostPlatform.system;
-            config.allowUnfree = true;
-            overlays = unstableOverlays;
-          };
-          # Separate nixpkgs for qt5webengine-heavy packages to avoid rebuild churn
-          qt-pinned = import inputs.nixpkgs-qt {
-            system = prev.stdenv.hostPlatform.system;
-            config = {
-              allowUnfree = true;
-              permittedInsecurePackages = [ "qtwebengine-5.15.19" ];
-            };
-          };
-          custom = prev.callPackage ./packages { };
-          # Compatibility: bitwarden renamed to bitwarden-desktop in unstable
-          bitwarden-desktop = prev.bitwarden-desktop or prev.bitwarden;
-        });
-
-      # Shared home-manager configuration factory
-      # Parameters:
-      #   sharedModules: Additional modules to include in home-manager.sharedModules
-      mkHomeManagerConfig =
-        {
-          sharedModules ? [ ],
-        }:
-        {
-          home-manager.useGlobalPkgs = true;
-          home-manager.useUserPackages = true;
-          home-manager.sharedModules = sharedModules ++ [
-            inputs.nix-doom-emacs-unstraightened.homeModule
-          ];
-          home-manager.extraSpecialArgs = {
-            globalInputs = inputs;
-          };
         };
+      };
+      custom = prev.callPackage ./packages {};
+      # Compatibility: bitwarden renamed to bitwarden-desktop in unstable
+      bitwarden-desktop = prev.bitwarden-desktop or prev.bitwarden;
+    });
 
-      # Shared unstable overlays for custom package builds
+    # Shared home-manager configuration factory
-      customUnstableOverlays = [
+    # Parameters:
-        # Override claude-code in unstable to use our custom GCS-based build
+    #   sharedModules: Additional modules to include in home-manager.sharedModules
-        # (needed for corporate networks that block npm registry)
+    mkHomeManagerConfig = { sharedModules ? [] }: {
-        (ufinal: uprev: {
+      home-manager.useGlobalPkgs = true;
-          claude-code = uprev.callPackage ./packages/claude-code { };
+      home-manager.useUserPackages = true;
-        })
+      home-manager.sharedModules = sharedModules ++ [
+        inputs.nix-doom-emacs-unstraightened.homeModule
       ];
+      home-manager.extraSpecialArgs = {
+        globalInputs = inputs;
+      };
+    };
 
-      nixosModules = [
+
-        ./roles
+    # Shared unstable overlays for custom package builds
-        inputs.home-manager.nixosModules.home-manager
+    customUnstableOverlays = [
+      # Override claude-code in unstable to use our custom GCS-based build
+      # (needed for corporate networks that block npm registry)
+      (ufinal: uprev: {
+        claude-code = uprev.callPackage ./packages/claude-code {};
+      })
+      # Pin dolt to v1.82.4 (gastown requires >= 1.82.4)
+      (ufinal: uprev: {
+        dolt = uprev.dolt.overrideAttrs (old: rec {
+          version = "1.82.4";
+          src = uprev.fetchFromGitHub {
+            owner = "dolthub";
+            repo = "dolt";
+            tag = "v${version}";
+            hash = "sha256-mavL3y+Kv25hzFlDFXk7W/jeKVKlCBjlc67GkL3Jcwk=";
+          };
+          vendorHash = "sha256-K1KzsqptZxO5OraWKIXeqKuVSzb6E/Mjy3c5PQ7Rs9k=";
+        });
+      })
+    ];
+
+    nixosModules = [
+      ./roles
+      inputs.home-manager.nixosModules.home-manager
+      {
+        nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
+      }
+      (mkHomeManagerConfig {
+        sharedModules = [ inputs.plasma-manager.homeModules.plasma-manager ];
+      })
+    ];
+
+    # Modules for unstable-based systems (like nix-deck)
+    nixosModulesUnstable = [
+      ./roles
+      inputs.home-manager-unstable.nixosModules.home-manager
+      inputs.jovian.nixosModules.jovian
+      {
+        nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
+      }
+      (mkHomeManagerConfig {
+        sharedModules = [ inputs.plasma-manager-unstable.homeModules.plasma-manager ];
+      })
+    ];
+
+    darwinModules = [
+      ./roles/darwin.nix
+      inputs.home-manager.darwinModules.home-manager
+      {
+        nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
+      }
+      (mkHomeManagerConfig { sharedModules = []; })
+    ];
+
+  in {
+    nixosConfigurations.nix-book = nixpkgs.lib.nixosSystem rec {
+      system = "x86_64-linux";
+      modules = nixosModules ++ [
+        ./machines/nix-book/configuration.nix
         {
-          nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
+          home-manager.users.johno = {
-        }
+            imports = [ ./home/home-laptop-compact.nix ];
-        (mkHomeManagerConfig {
+            # Machine-specific overrides
-          sharedModules = [ inputs.plasma-manager.homeModules.plasma-manager ];
+            home.roles.i3_sway.extraSwayConfig = {
-        })
+              output.eDP-1.scale = "1.75";
-      ];
-
-      # Modules for unstable-based systems (like nix-deck)
-      nixosModulesUnstable = [
-        ./roles
-        inputs.home-manager-unstable.nixosModules.home-manager
-        inputs.jovian.nixosModules.jovian
-        {
-          nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
-        }
-        (mkHomeManagerConfig {
-          sharedModules = [ inputs.plasma-manager-unstable.homeModules.plasma-manager ];
-        })
-      ];
-
-      darwinModules = [
-        ./roles/darwin.nix
-        inputs.home-manager.darwinModules.home-manager
-        {
-          nixpkgs.overlays = [ (mkBaseOverlay { unstableOverlays = customUnstableOverlays; }) ];
-        }
-        (mkHomeManagerConfig { sharedModules = [ ]; })
-      ];
-
-    in
-    {
-      nixosConfigurations.nix-book = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
-        modules = nixosModules ++ [
-          ./machines/nix-book/configuration.nix
-          {
-            home-manager.users.johno = {
-              imports = [ ./home/home-laptop-compact.nix ];
-              # Machine-specific overrides
-              home.roles.i3_sway.extraSwayConfig = {
-                output.eDP-1.scale = "1.75";
-              };
             };
-            home-manager.extraSpecialArgs = { inherit system; };
+          };
-          }
+          home-manager.extraSpecialArgs = { inherit system; };
-        ];
+        }
-      };
+      ];
+    };
 
-      nixosConfigurations.boxy = nixpkgs.lib.nixosSystem rec {
+    nixosConfigurations.boxy = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
+      system = "x86_64-linux";
-        modules = nixosModules ++ [
+      modules = nixosModules ++ [
-          ./machines/boxy/configuration.nix
+        ./machines/boxy/configuration.nix
-          {
+        {
-            home-manager.users.johno = import ./home/home-media-center.nix;
+          home-manager.users.johno = import ./home/home-media-center.nix;
-            # kodi user: AVR volume control + minimal Plasma config for Bigscreen session
+          home-manager.users.kodi = import ./home/home-kodi.nix;
-            home-manager.users.kodi = import ./home/home-kodi.nix;
+          home-manager.extraSpecialArgs = { inherit system; };
-            home-manager.extraSpecialArgs = { inherit system; };
+        }
-          }
+      ];
-        ];
+    };
-      };
 
-      nixosConfigurations.gym-box = nixpkgs.lib.nixosSystem rec {
+    nixosConfigurations.zix790prors = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
+      system = "x86_64-linux";
-        modules = nixosModules ++ [
+      modules = nixosModules ++ [
-          ./machines/gym-box/configuration.nix
+        ./machines/zix790prors/configuration.nix
-          {
+        {
-            home-manager.users.johno = import ./home/home-media-center.nix;
+          home-manager.users.johno = {
-            home-manager.users.kodi = import ./home/home-kodi.nix;
+            imports = [ ./home/home-desktop.nix ];
-            home-manager.extraSpecialArgs = { inherit system; };
+            home.roles.i3_sway.extraSwayConfig = {
-          }
+              output = {
-        ];
+                "DP-1" = {
-      };
+                  mode = "3440x1440@164.900Hz";
-
-      nixosConfigurations.zix790prors = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
-        modules = nixosModules ++ [
-          ./machines/zix790prors/configuration.nix
-          {
-            home-manager.users.johno = {
-              imports = [ ./home/home-desktop.nix ];
-              home.roles.i3_sway.extraSwayConfig = {
-                output = {
-                  "DP-1" = {
-                    mode = "3440x1440@164.900Hz";
-                  };
                 };
               };
             };
-            home-manager.extraSpecialArgs = { inherit system; };
-          }
-        ];
-      };
-
-      # Live USB ISO configuration
-      nixosConfigurations.live-usb = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
-        modules = nixosModules ++ [
-          ./machines/live-usb/configuration.nix
-          {
-            home-manager.users.nixos = import ./home/home-live-usb.nix;
-            home-manager.extraSpecialArgs = { inherit system; };
-          }
-        ];
-      };
-
-      # Steam Deck configuration (using unstable for better Jovian compatibility)
-      nixosConfigurations.nix-deck = nixpkgs-unstable.lib.nixosSystem rec {
-        system = "x86_64-linux";
-        modules = nixosModulesUnstable ++ [
-          ./machines/nix-deck/configuration.nix
-          {
-            home-manager.users.johno = import ./home/home-desktop.nix;
-            home-manager.extraSpecialArgs = { inherit system; };
-          }
-        ];
-      };
-
-      # ZFS/NFS server configuration
-      nixosConfigurations.john-endesktop = nixpkgs.lib.nixosSystem rec {
-        system = "x86_64-linux";
-        modules = nixosModules ++ [
-          ./machines/john-endesktop/configuration.nix
-          inputs.home-manager.nixosModules.home-manager
-          {
-            home-manager.users.johno = import ./home/home-server.nix;
-            home-manager.extraSpecialArgs = { inherit system; };
-          }
-        ];
-      };
-
-      # Darwin/macOS configurations
-      darwinConfigurations."BLKFV4YF49KT7" = inputs.nix-darwin.lib.darwinSystem rec {
-        system = "aarch64-darwin";
-        modules = darwinModules ++ [
-          ./machines/johno-macbookpro/configuration.nix
-          {
-            home-manager.users.johno = import ./home/home-darwin-work.nix;
-            home-manager.extraSpecialArgs = { inherit system; };
-          }
-        ];
-      };
-
-      # Packages for CI caching (custom packages, flake inputs, and qt-pinned)
-      packages = nixpkgs.lib.genAttrs [ "x86_64-linux" "aarch64-linux" ] (
-        system:
-        let
-          pkgs = import nixpkgs {
-            inherit system;
-            config.allowUnfree = true;
-            overlays = [ (mkBaseOverlay { }) ];
           };
-          pkgsQt = import inputs.nixpkgs-qt {
+          home-manager.extraSpecialArgs = { inherit system; };
-            inherit system;
-            config = {
-              allowUnfree = true;
-              permittedInsecurePackages = [ "qtwebengine-5.15.19" ];
-            };
-          };
-        in
-        {
-          "custom-claude-code" = pkgs.custom.claude-code;
-          "custom-app-launcher-server" = pkgs.custom.app-launcher-server;
-          "custom-mcrcon-rbw" = pkgs.custom.mcrcon-rbw;
-          "custom-tea-rbw" = pkgs.custom.tea-rbw;
-          "custom-rclone-torbox-setup" = pkgs.custom.rclone-torbox-setup;
-          "custom-opencode" = pkgs.custom.opencode;
-          "qt-pinned-jellyfin-media-player" = pkgsQt.jellyfin-media-player;
-          "qt-pinned-stremio" = pkgsQt.stremio;
         }
-        // (
+      ];
-          if system == "x86_64-linux" then
-            {
-              "custom-nextcloud-talk-desktop" = pkgs.custom.nextcloud-talk-desktop;
-              # nix-deck kernel from Jovian-NixOS (Steam Deck) - expensive to build
-              "nix-deck-kernel" = self.nixosConfigurations.nix-deck.config.boot.kernelPackages.kernel;
-            }
-          else
-            { }
-        )
-      );
-
-      # Flake apps
-      apps = nixpkgs.lib.genAttrs [ "x86_64-linux" "aarch64-linux" "aarch64-darwin" ] (
-        system:
-        let
-          pkgs = import nixpkgs { inherit system; };
-          commonDeps = [
-            pkgs.curl
-            pkgs.jq
-            pkgs.nix
-            pkgs.git
-            pkgs.gnused
-            pkgs.gnugrep
-            pkgs.coreutils
-            pkgs.gawk
-          ];
-
-          update-doomemacs = pkgs.writeShellScriptBin "update-doomemacs" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./scripts/update-doomemacs.sh}
-          '';
-
-          update-claude-code = pkgs.writeShellScriptBin "update-claude-code" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./packages/claude-code/update.sh}
-          '';
-
-          update-opencode = pkgs.writeShellScriptBin "update-opencode" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./packages/opencode/update.sh}
-          '';
-
-          rotate-wallpaper = pkgs.writeShellScriptBin "rotate-wallpaper" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./scripts/rotate-wallpaper.sh}
-          '';
-
-          upgrade = pkgs.writeShellScriptBin "upgrade" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./scripts/upgrade.sh}
-          '';
-
-          bootstrap = pkgs.writeShellScriptBin "bootstrap" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./scripts/bootstrap.sh}
-          '';
-
-          build-liveusb = pkgs.writeShellScriptBin "build-liveusb" ''
-            export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
-            ${builtins.readFile ./scripts/build-liveusb.sh}
-          '';
-        in
-        {
-          update-doomemacs = {
-            type = "app";
-            program = "${update-doomemacs}/bin/update-doomemacs";
-            meta.description = "Update Doom Emacs configuration";
-          };
-          update-claude-code = {
-            type = "app";
-            program = "${update-claude-code}/bin/update-claude-code";
-            meta.description = "Update Claude Code package version";
-          };
-          update-opencode = {
-            type = "app";
-            program = "${update-opencode}/bin/update-opencode";
-            meta.description = "Update OpenCode package version";
-          };
-          rotate-wallpaper = {
-            type = "app";
-            program = "${rotate-wallpaper}/bin/rotate-wallpaper";
-            meta.description = "Rotate desktop wallpaper";
-          };
-          upgrade = {
-            type = "app";
-            program = "${upgrade}/bin/upgrade";
-            meta.description = "Upgrade NixOS configuration";
-          };
-          bootstrap = {
-            type = "app";
-            program = "${bootstrap}/bin/bootstrap";
-            meta.description = "Bootstrap a new NixOS machine";
-          };
-          build-liveusb = {
-            type = "app";
-            program = "${build-liveusb}/bin/build-liveusb";
-            meta.description = "Build a bootable Live USB ISO";
-          };
-        }
-      );
     };
+
+    # Live USB ISO configuration
+    nixosConfigurations.live-usb = nixpkgs.lib.nixosSystem rec {
+      system = "x86_64-linux";
+      modules = nixosModules ++ [
+        ./machines/live-usb/configuration.nix
+        {
+          home-manager.users.nixos = import ./home/home-live-usb.nix;
+          home-manager.extraSpecialArgs = { inherit system; };
+        }
+      ];
+    };
+
+    # Steam Deck configuration (using unstable for better Jovian compatibility)
+    nixosConfigurations.nix-deck = nixpkgs-unstable.lib.nixosSystem rec {
+      system = "x86_64-linux";
+      modules = nixosModulesUnstable ++ [
+        ./machines/nix-deck/configuration.nix
+        {
+          home-manager.users.johno = import ./home/home-desktop.nix;
+          home-manager.extraSpecialArgs = { inherit system; };
+        }
+      ];
+    };
+
+    # ZFS/NFS server configuration
+    nixosConfigurations.john-endesktop = nixpkgs.lib.nixosSystem rec {
+      system = "x86_64-linux";
+      modules = nixosModules ++ [
+        ./machines/john-endesktop/configuration.nix
+        inputs.home-manager.nixosModules.home-manager
+        {
+          home-manager.users.johno = import ./home/home-server.nix;
+          home-manager.extraSpecialArgs = { inherit system; };
+        }
+      ];
+    };
+
+    # Darwin/macOS configurations
+    darwinConfigurations."BLKFV4YF49KT7" = inputs.nix-darwin.lib.darwinSystem rec {
+      system = "aarch64-darwin";
+      modules = darwinModules ++ [
+        ./machines/johno-macbookpro/configuration.nix
+        {
+          home-manager.users.johno = import ./home/home-darwin-work.nix;
+          home-manager.extraSpecialArgs = { inherit system; };
+        }
+      ];
+    };
+
+    # Packages for CI caching (custom packages, flake inputs, and qt-pinned)
+    packages = nixpkgs.lib.genAttrs [ "x86_64-linux" "aarch64-linux" ] (system:
+      let
+        pkgs = import nixpkgs {
+          inherit system;
+          config.allowUnfree = true;
+          overlays = [ (mkBaseOverlay {}) ];
+        };
+        pkgsQt = import inputs.nixpkgs-qt {
+          inherit system;
+          config = {
+            allowUnfree = true;
+            permittedInsecurePackages = [ "qtwebengine-5.15.19" ];
+          };
+        };
+        # Version strings for flake input packages
+        beadsRev = builtins.substring 0 8 (inputs.beads.rev or "unknown");
+        gastownRev = builtins.substring 0 8 (inputs.gastown.rev or "unknown");
+      in {
+        "custom-claude-code" = pkgs.custom.claude-code;
+        "custom-app-launcher-server" = pkgs.custom.app-launcher-server;
+        "custom-mcrcon-rbw" = pkgs.custom.mcrcon-rbw;
+        "custom-tea-rbw" = pkgs.custom.tea-rbw;
+        "custom-rclone-torbox-setup" = pkgs.custom.rclone-torbox-setup;
+        "qt-pinned-jellyfin-media-player" = pkgsQt.jellyfin-media-player;
+        "qt-pinned-stremio" = pkgsQt.stremio;
+        # Flake input packages (beads, gastown) - these get version from input rev
+        "custom-beads" = pkgs.callPackage ./packages/beads {
+          inherit (pkgs.unstable) buildGoModule;
+          src = inputs.beads;
+          version = "0.52.0-${beadsRev}";
+        };
+        "custom-gastown" = pkgs.callPackage ./packages/gastown {
+          src = inputs.gastown;
+          version = "unstable-${gastownRev}";
+        };
+        "custom-perles" = pkgs.callPackage ./packages/perles {
+          inherit (pkgs.unstable) buildGoModule;
+          src = inputs.perles;
+          version = "unstable-${builtins.substring 0 8 (inputs.perles.rev or "unknown")}";
+        };
+      } // (if system == "x86_64-linux" then {
+        # nix-deck kernel from Jovian-NixOS (Steam Deck) - expensive to build
+        "nix-deck-kernel" = self.nixosConfigurations.nix-deck.config.boot.kernelPackages.kernel;
+      } else {})
+    );
+
+    # Flake apps
+    apps = nixpkgs.lib.genAttrs [ "x86_64-linux" "aarch64-linux" "aarch64-darwin" ] (system:
+      let
+        pkgs = import nixpkgs { inherit system; };
+        commonDeps = [ pkgs.curl pkgs.jq pkgs.nix pkgs.git pkgs.gnused pkgs.gnugrep pkgs.coreutils pkgs.gawk ];
+
+        update-doomemacs = pkgs.writeShellScriptBin "update-doomemacs" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./scripts/update-doomemacs.sh}
+        '';
+
+        update-claude-code = pkgs.writeShellScriptBin "update-claude-code" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./packages/claude-code/update.sh}
+        '';
+
+        rotate-wallpaper = pkgs.writeShellScriptBin "rotate-wallpaper" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./scripts/rotate-wallpaper.sh}
+        '';
+
+        upgrade = pkgs.writeShellScriptBin "upgrade" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./scripts/upgrade.sh}
+        '';
+
+        bootstrap = pkgs.writeShellScriptBin "bootstrap" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./scripts/bootstrap.sh}
+        '';
+
+        build-liveusb = pkgs.writeShellScriptBin "build-liveusb" ''
+          export PATH="${pkgs.lib.makeBinPath commonDeps}:$PATH"
+          ${builtins.readFile ./scripts/build-liveusb.sh}
+        '';
+      in {
+        update-doomemacs = {
+          type = "app";
+          program = "${update-doomemacs}/bin/update-doomemacs";
+        };
+        update-claude-code = {
+          type = "app";
+          program = "${update-claude-code}/bin/update-claude-code";
+        };
+        rotate-wallpaper = {
+          type = "app";
+          program = "${rotate-wallpaper}/bin/rotate-wallpaper";
+        };
+        upgrade = {
+          type = "app";
+          program = "${upgrade}/bin/upgrade";
+        };
+        bootstrap = {
+          type = "app";
+          program = "${bootstrap}/bin/bootstrap";
+        };
+        build-liveusb = {
+          type = "app";
+          program = "${build-liveusb}/bin/build-liveusb";
+        };
+      }
+    );
+  };
 }

home/roles/base/default.nix

@@ -1,9 +1,4 @@
-{
+{ config, lib, pkgs, ... }:
-  config,
-  lib,
-  pkgs,
-  ...
-}:
 
 with lib;
 
@@ -23,13 +18,11 @@ in
       htop
       killall
       less
-      lnav
       ncdu
       shellcheck
       tmux
       tree
       watch
-      custom.opencode
     ];
 
     # Automatic garbage collection for user profile (home-manager generations).
@@ -60,7 +53,6 @@ in
 
     programs.git = {
       enable = true;
-      signing.format = null;
       settings = {
         user.name = "John Ogle";
         user.email = "john@ogle.fyi";

home/roles/communication/default.nix

@@ -20,7 +20,7 @@ in
       pkgs.element-desktop
       # Re-enabled in 25.11 after security issues were resolved
       pkgs.fluffychat
-      pkgs.custom.nextcloud-talk-desktop
+      pkgs.nextcloud-talk-desktop
     ];
   };
 }

home/roles/development/commands/beads_batch_research_plan.md

@@ -0,0 +1,317 @@
+---
+description: Batch research and planning for multiple beads with interactive question review
+model: opus
+---
+
+# Beads Batch Research+Plan
+
+This skill automates the common workflow of:
+1. Running /beads_research in parallel for multiple beads
+2. Presenting open questions interactively for user input (bead-by-bead)
+3. Running /beads_plan for all researched beads (plus any spawned from splits)
+
+## When to Use
+
+- You have multiple beads ready for work
+- You want to research and plan them efficiently before implementation
+- You prefer to batch your question-answering rather than context-switching between skills
+
+## Phase 1: Selection
+
+1. **Get ready beads**: Run `bd ready --limit=20` to list beads with no blockers
+
+2. **Filter already-researched beads**:
+   For each ready bead, check if it already has research:
+   ```bash
+   ls thoughts/beads-{bead-id}/research.md 2>/dev/null
+   ```
+
+   Categorize beads:
+   - **Needs research**: No `research.md` exists
+   - **Has research, needs plan**: `research.md` exists but no `plan.md`
+   - **Already planned**: Both `research.md` and `plan.md` exist
+
+3. **Present selection**:
+   ```
+   Ready beads available for batch research+plan:
+
+   NEEDS RESEARCH:
+   - {bead-id}: {title} (type: {type})
+   - ...
+
+   HAS RESEARCH (plan only):
+   - {bead-id}: {title} (type: {type})
+   - ...
+
+   ALREADY PLANNED (skip):
+   - {bead-id}: {title}
+
+   Which beads would you like to process?
+   ```
+
+4. **Use AskUserQuestion** with `multiSelect: true`:
+   - Include bead ID and title for each option
+   - Separate options by category
+   - Allow selection across categories
+
+## Phase 2: Parallel Research
+
+For each selected bead that NEEDS RESEARCH, launch a research subagent.
+
+### Subagent Instructions Template
+
+```
+Research bead [BEAD_ID]: [BEAD_TITLE]
+
+1. **Load bead context**:
+   ```bash
+   bd show [BEAD_ID]
+   ```
+
+2. **Create artifact directory**:
+   ```bash
+   mkdir -p thoughts/beads-[BEAD_ID]
+   ```
+
+3. **Conduct research** following beads_research.md patterns:
+   - Analyze and decompose the research question
+   - Spawn parallel sub-agent tasks (codebase-locator, codebase-analyzer, etc.)
+   - Synthesize findings
+
+4. **Write research document** to `thoughts/beads-[BEAD_ID]/research.md`:
+   - Include frontmatter with metadata
+   - Document findings with file:line references
+   - **CRITICAL**: Include "## Open Questions" section listing any unresolved items
+
+5. **Return summary**:
+   - Research status (complete/partial)
+   - Number of open questions
+   - Key findings summary (2-3 bullet points)
+   - List of open questions verbatim
+```
+
+### Launching Subagents
+
+Use `subagent_type: "opus"` for research subagents (matches beads_research model setting).
+
+Launch ALL research subagents in a single message for parallel execution:
+```
+<Task calls for each selected bead needing research - all in one message>
+```
+
+### Collecting Results
+
+Wait for ALL research subagents to complete. Collect:
+- Bead ID
+- Research status
+- Open questions list
+- Any errors encountered
+
+## Phase 3: Interactive Question Review
+
+Present each bead's open questions sequentially for user input.
+
+### For Each Bead (in order):
+
+1. **Present research summary**:
+   ```
+   ## Bead {N}/{total}: {bead-id} - {title}
+
+   Research complete. Key findings:
+   - {finding 1}
+   - {finding 2}
+
+   Open questions requiring your input:
+   1. {question 1}
+   2. {question 2}
+
+   Additionally:
+   - Should this bead be split into multiple beads? (y/n)
+   - If split, describe the split:
+   ```
+
+2. **Collect user responses**:
+   - Answers to open questions
+   - Split decision (yes/no)
+   - If split: new bead titles and how to divide the work
+
+3. **Handle splits**:
+   If user indicates a split:
+   ```bash
+   # Create new beads for split work
+   bd create --title="{split title 1}" --type={type} --priority={priority} \
+     --description="{description based on user input}"
+
+   # Update original bead if scope narrowed
+   bd update {original-bead-id} --description="{updated description}"
+   ```
+
+   Track new bead IDs for inclusion in planning phase.
+
+4. **Update research document**:
+   Append user answers to `thoughts/beads-{id}/research.md`:
+   ```markdown
+   ## User Clarifications [{timestamp}]
+
+   Q: {question 1}
+   A: {user answer 1}
+
+   Q: {question 2}
+   A: {user answer 2}
+
+   ## Bead Splits
+   {If split: description of split and new bead IDs}
+   ```
+
+### Progress Tracking
+
+After each bead's questions are answered, confirm before moving to next:
+```
+Questions answered for {bead-id}. {N-1} beads remaining.
+Continue to next bead? (y/n)
+```
+
+### Beads with No Questions
+
+If a bead's research had no open questions:
+```
+## Bead {N}/{total}: {bead-id} - {title}
+
+Research complete with no open questions.
+
+Key findings:
+- {finding 1}
+- {finding 2}
+
+Should this bead be split? (y/n)
+```
+
+## Phase 4: Parallel Planning
+
+After all questions answered, launch planning subagents for all beads.
+
+### Beads to Plan
+
+Include:
+- Original beads that were researched
+- Beads that had existing research (from selection phase)
+- New beads spawned from splits
+
+### Subagent Instructions Template
+
+```
+Create implementation plan for bead [BEAD_ID]: [BEAD_TITLE]
+
+1. **Load context**:
+   ```bash
+   bd show [BEAD_ID]
+   ```
+
+2. **Read research** (it exists and has user clarifications):
+   Read `thoughts/beads-[BEAD_ID]/research.md` FULLY
+
+3. **Create plan** following beads_plan.md patterns:
+   - Context gathering via sub-agents
+   - Design approach based on research findings and user clarifications
+   - **Skip interactive questions** - they were already answered in research review
+
+4. **Write plan** to `thoughts/beads-[BEAD_ID]/plan.md`:
+   - Full plan structure with phases
+   - Success criteria (automated and manual)
+   - References to research document
+
+5. **Update bead**:
+   ```bash
+   bd update [BEAD_ID] --notes="Plan created: thoughts/beads-[BEAD_ID]/plan.md"
+   ```
+
+6. **Return summary**:
+   - Plan status (complete/failed)
+   - Number of phases
+   - Estimated complexity (small/medium/large)
+   - Any issues encountered
+```
+
+### Launching Subagents
+
+Use `subagent_type: "opus"` for planning subagents (matches beads_plan model setting).
+
+Launch ALL planning subagents in a single message:
+```
+<Task calls for each bead to plan - all in one message>
+```
+
+### Handling Beads Without Research
+
+For beads that had existing research but user didn't review questions:
+- Planning subagent reads existing research
+- If research has unresolved open questions, subagent should flag this in its return
+
+## Phase 5: Summary
+
+After all planning completes, present final summary.
+
+### Summary Format
+
+```
+## Batch Research+Plan Complete
+
+### Successfully Processed:
+| Bead | Title | Research | Plan | Phases | Complexity |
+|------|-------|----------|------|--------|------------|
+| {id} | {title} | Complete | Complete | 3 | medium |
+| {id} | {title} | Complete | Complete | 2 | small |
+
+### New Beads (from splits):
+| Bead | Title | Parent | Status |
+|------|-------|--------|--------|
+| {new-id} | {title} | {parent-id} | Planned |
+
+### Failed:
+| Bead | Title | Phase Failed | Error |
+|------|-------|--------------|-------|
+| {id} | {title} | Research | Timeout |
+
+### Next Steps:
+1. Review plans at `thoughts/beads-{id}/plan.md`
+2. Run `/parallel_beads` to implement all planned beads
+3. Or run `/beads_implement {id}` for individual implementation
+
+### Artifacts Created:
+- Research: thoughts/beads-{id}/research.md (x{N} files)
+- Plans: thoughts/beads-{id}/plan.md (x{N} files)
+```
+
+## Error Handling
+
+### Research Subagent Failure
+- Log the failure with bead ID and error
+- Continue with other beads
+- Exclude failed beads from question review and planning
+- Report in final summary
+
+### Planning Subagent Failure
+- Log the failure with bead ID and error
+- Research still valid - can retry planning manually
+- Report in final summary
+
+### User Cancellation During Question Review
+- Save progress to bead notes
+- Report which beads were completed
+- User can resume with remaining beads in new session
+
+### Split Bead Creation Failure
+- Report error but continue with original bead
+- User can manually create split beads later
+
+## Resource Limits
+
+- Maximum concurrent research subagents: 5
+- Maximum concurrent planning subagents: 5
+- If more beads selected, process in batches
+
+## Notes
+
+- This skill is designed for the "research+plan before implementation" workflow
+- Pairs well with `/parallel_beads` for subsequent implementation
+- Run `/reconcile_beads` after implementation PRs merge

home/roles/development/commands/beads_implement.md

@@ -0,0 +1,253 @@
+---
+description: Implement a plan from thoughts/ for a bead issue
+---
+
+# Beads Implement
+
+You are tasked with implementing an approved plan for a bead issue. Plans are stored in `thoughts/beads-{id}/plan.md`.
+
+## Initial Setup
+
+When this command is invoked:
+
+1. **Parse the input for bead ID**:
+   - If a bead ID is provided, use it
+   - If no bead ID, check for beads with plans:
+     ```bash
+     bd list --status=in_progress
+     ```
+     Then check which have plans in `thoughts/beads-{id}/plan.md`
+
+2. **Load bead context**:
+   ```bash
+   bd show {bead-id}
+   ```
+   Note the bead **type** (bug, feature, task) from the output.
+
+3. **Check for plan and handle by type**:
+
+   Check if plan exists:
+   ```bash
+   ls thoughts/beads-{bead-id}/plan.md 2>/dev/null
+   ```
+
+   **If plan exists**: Proceed normally (skip to step 4)
+
+   **If no plan**:
+   - **type=bug**: Proceed without plan (simple bugs can implement directly)
+   - **type=feature or type=task**: Warn and ask:
+     ```
+     No plan found for this {type}.
+
+     Plans help ensure complex work is well-designed and verifiable.
+     Location expected: thoughts/beads-{bead-id}/plan.md
+
+     Options:
+     1. Create a plan first (recommended) - Run /beads_plan {bead-id}
+     2. Proceed without a plan (for simple changes)
+
+     How would you like to proceed?
+     ```
+     Wait for user response before continuing.
+
+4. **Load plan and research context** (if plan exists):
+   - Read `thoughts/beads-{bead-id}/plan.md` FULLY
+   - Check for any existing checkmarks (- [x]) indicating partial progress
+   - Read any research at `thoughts/beads-{bead-id}/research.md`
+   - If plan's Success Criteria references contribution guidelines (e.g., "Per CONTRIBUTING.md:"),
+     verify the original CONTRIBUTING.md still exists and requirements are current
+
+5. **Mark bead in progress** (if not already):
+   ```bash
+   bd update {bead-id} --status=in_progress
+   ```
+
+6. **Respond with**:
+   ```
+   Implementing plan for bead {bead-id}: {bead-title}
+
+   Plan location: thoughts/beads-{bead-id}/plan.md
+   {If partial progress: "Resuming from Phase X - previous phases completed."}
+
+   I'll implement each phase and verify success criteria before proceeding.
+   ```
+
+## Implementation Process
+
+### Step 1: Understand the Plan
+
+1. **Read the plan completely**
+2. **Check for existing progress** (checkmarked items)
+3. **Read all files mentioned in the plan**
+4. **Create a TodoWrite list** tracking each phase
+
+### Step 2: Implement Each Phase
+
+For each phase in the plan:
+
+1. **Announce the phase**:
+   ```
+   ## Starting Phase {N}: {Phase Name}
+
+   This phase will: {overview from plan}
+   ```
+
+2. **Make the changes**:
+   - Follow the plan's specific instructions
+   - Use Edit tool for modifications
+   - Create new files only when specified
+
+3. **Run automated verification**:
+   - Execute each command in "Automated Verification"
+   - Fix any issues before proceeding
+
+4. **Update plan checkboxes**:
+   - Use Edit tool to check off completed items in the plan
+   - This enables resume if session is interrupted
+
+5. **Update bead notes** with progress:
+   ```bash
+   bd update {bead-id} --notes="Phase {N} complete. Automated verification passed."
+   ```
+
+### Step 3: Per-Plan Checkpoint
+
+**CRITICAL**: After completing ALL phases and ALL automated verification:
+
+```
+## Implementation Complete - Ready for Manual Verification
+
+All phases completed and automated verification passed:
+- [ ] Phase 1: {name} - DONE
+- [ ] Phase 2: {name} - DONE
+- [ ] ...
+
+**Automated checks passed:**
+- {List of automated checks that passed}
+
+**Please perform manual verification:**
+- {List manual verification items from plan}
+
+Let me know when manual testing is complete so I can close the bead.
+
+**Contribution guidelines compliance:**
+- {List any contribution guideline requirements that were part of Success Criteria}
+- {Note if any requirements could not be automated and need manual review}
+```
+
+**STOP HERE and wait for user confirmation.**
+
+Do NOT:
+- Close the bead automatically
+- Proceed to "next steps" without confirmation
+- Start additional work
+
+### Step 4: After Manual Verification
+
+When user confirms manual verification passed:
+
+1. **Update plan status**:
+   - Edit the plan's frontmatter: `status: complete`
+
+2. **Close the bead**:
+   ```bash
+   bd close {bead-id} --reason="Implementation complete. All verification passed."
+   ```
+
+3. **Final summary**:
+   ```
+   Bead {bead-id} closed.
+
+   Summary:
+   - {What was implemented}
+   - {Key changes made}
+
+   Artifacts:
+   - Plan: thoughts/beads-{bead-id}/plan.md
+   - {Any other artifacts created}
+   ```
+
+## Handling Issues
+
+### When something doesn't match the plan:
+
+```
+Issue in Phase {N}:
+
+Expected: {what the plan says}
+Found: {actual situation}
+Why this matters: {explanation}
+
+Options:
+1. Adapt the implementation to work with current state
+2. Update the plan to reflect reality
+3. Stop and investigate further
+
+How should I proceed?
+```
+
+### When tests fail:
+
+1. **Analyze the failure**
+2. **Attempt to fix** if the fix is clear and within scope
+3. **If fix is unclear**, report:
+   ```
+   Test failure in Phase {N}:
+
+   Failing test: {test name}
+   Error: {error message}
+
+   I've attempted: {what you tried}
+
+   This may require: {your assessment}
+   ```
+
+### When blocked:
+
+```
+Blocked in Phase {N}:
+
+Blocker: {description}
+Impact: {what can't proceed}
+
+Suggested resolution: {your recommendation}
+```
+
+## Resuming Work
+
+If the plan has existing checkmarks:
+
+1. **Trust completed work** - don't re-verify unless something seems off
+2. **Pick up from first unchecked item**
+3. **Verify previous work only if** current phase depends on it and seems broken
+
+## Important Guidelines
+
+1. **Follow the plan's intent** while adapting to reality
+2. **Implement each phase fully** before moving to next
+3. **Update checkboxes in real-time** as you complete items
+4. **One checkpoint per plan** - not per phase
+5. **Never close bead** without manual verification confirmation
+6. **Keep bead notes updated** with progress
+
+## Session Close Protocol
+
+If you need to end the session before completion:
+
+1. **Update plan** with current progress (checkboxes)
+2. **Update bead notes**:
+   ```bash
+   bd update {bead-id} --notes="In progress: Phase {N} partially complete. Next: {what's next}"
+   ```
+3. **Inform user** of status and how to resume
+
+## Example Invocation
+
+```
+User: /beads:implement nixos-configs-abc123
+Assistant: Implementing plan for bead nixos-configs-abc123...
+
+## Starting Phase 1: Database Schema
+
+This phase will add the new user_preferences table...
+```

home/roles/development/commands/beads_iterate.md

@@ -0,0 +1,214 @@
+---
+description: Iterate on existing implementation plans for a bead issue
+model: opus
+---
+
+# Beads Iterate
+
+You are tasked with updating existing implementation plans based on feedback. Plans are stored in `thoughts/beads-{id}/plan.md`.
+
+## Initial Setup
+
+When this command is invoked:
+
+1. **Parse the input**:
+   - Bead ID (required or ask for it)
+   - Requested changes/feedback (can be provided with command or after)
+
+2. **Handle different scenarios**:
+
+   **No bead ID provided**:
+   ```
+   Which bead's plan would you like to iterate on?
+
+   Recent beads with plans:
+   {list beads that have thoughts/beads-{id}/plan.md}
+   ```
+
+   **Bead ID but no feedback**:
+   ```
+   I've found the plan at thoughts/beads-{bead-id}/plan.md
+
+   What changes would you like to make? For example:
+   - "Add a phase for migration handling"
+   - "Update success criteria to include performance tests"
+   - "Adjust scope to exclude feature X"
+   - "Split Phase 2 into two separate phases"
+   ```
+
+   **Both bead ID and feedback provided**:
+   - Proceed immediately to Step 1
+
+## Iteration Process
+
+### Step 1: Understand Current Plan
+
+1. **Read the existing plan COMPLETELY**:
+   ```bash
+   cat thoughts/beads-{bead-id}/plan.md
+   ```
+   - Understand current structure, phases, scope
+   - Note success criteria and approach
+
+2. **Read the bead for context**:
+   ```bash
+   bd show {bead-id}
+   ```
+
+3. **Understand requested changes**:
+   - Parse what user wants to add/modify/remove
+   - Identify if changes require codebase research
+
+### Step 2: Research If Needed
+
+**Only if changes require new technical understanding:**
+
+1. **Spawn parallel research tasks**:
+   - **codebase-locator**: Find relevant files
+   - **codebase-analyzer**: Understand implementation details
+   - **codebase-pattern-finder**: Find similar patterns
+
+2. **Be specific about directories** in prompts
+
+3. **Wait for ALL tasks** before proceeding
+
+### Step 3: Present Understanding
+
+Before making changes:
+
+```
+Based on your feedback, I understand you want to:
+- {Change 1 with specific detail}
+- {Change 2 with specific detail}
+
+{If research was needed:}
+My research found:
+- {Relevant discovery}
+- {Important constraint}
+
+I plan to update the plan by:
+1. {Specific modification}
+2. {Another modification}
+
+Does this align with your intent?
+```
+
+Get user confirmation before proceeding.
+
+### Step 4: Update the Plan
+
+1. **Make focused, precise edits**:
+   - Use Edit tool for surgical changes
+   - Maintain existing structure unless explicitly changing it
+   - Keep file:line references accurate
+
+2. **Ensure consistency**:
+   - New phases follow existing pattern
+   - Update "What We're NOT Doing" if scope changes
+   - Maintain automated vs manual success criteria distinction
+
+3. **Update plan metadata**:
+   - Update frontmatter `date` to current timestamp
+   - Add `iteration: {N}` to frontmatter
+   - Add `iteration_reason: "{brief description}"` to frontmatter
+
+4. **Preserve completed work**:
+   - Don't uncheck items that were already completed
+   - If changing completed phases, discuss with user first
+
+### Step 5: Save Iteration History (Optional)
+
+For significant changes, save the previous version:
+
+```bash
+cp thoughts/beads-{bead-id}/plan.md thoughts/beads-{bead-id}/plan-v{N}.md
+```
+
+Then update the main plan.
+
+### Step 6: Update Bead
+
+```bash
+bd update {bead-id} --notes="Plan iterated: {brief description of changes}"
+```
+
+### Step 7: Present Changes
+
+```
+I've updated the plan at `thoughts/beads-{bead-id}/plan.md`
+
+Changes made:
+- {Specific change 1}
+- {Specific change 2}
+
+The updated plan now:
+- {Key improvement}
+- {Another improvement}
+
+Would you like any further adjustments?
+```
+
+## Important Guidelines
+
+1. **Be Skeptical**:
+   - Don't blindly accept changes that seem problematic
+   - Question vague feedback - ask for clarification
+   - Point out conflicts with existing phases
+
+2. **Be Surgical**:
+   - Make precise edits, not wholesale rewrites
+   - Preserve good content that doesn't need changing
+   - Only research what's necessary
+
+3. **Be Thorough**:
+   - Read entire plan before making changes
+   - Ensure updated sections maintain quality
+   - Verify success criteria are still measurable
+
+4. **Be Interactive**:
+   - Confirm understanding before making changes
+   - Allow course corrections
+   - Don't disappear into research without communicating
+
+5. **No Open Questions**:
+   - If changes raise questions, ASK
+   - Don't update plan with unresolved questions
+
+## Success Criteria Guidelines
+
+When updating success criteria, maintain two categories:
+
+**Automated Verification**:
+- Commands: `make test`, `npm run lint`
+- Prefer `make` commands when available
+- File existence checks
+
+**Manual Verification**:
+- UI/UX functionality
+- Performance under real conditions
+- Edge cases hard to automate
+
+## Handling Major Changes
+
+If feedback requires significant restructuring:
+
+1. **Discuss scope** before proceeding
+2. **Consider if this should be a new plan** instead of iteration
+3. **Preserve the original** in `plan-v{N}.md`
+4. **Update bead description** if scope changed significantly
+
+## Example Invocations
+
+**With full context**:
+```
+User: /beads:iterate nixos-configs-abc123 - add error handling phase
+Assistant: Based on your feedback, I understand you want to add a new phase for error handling...
+```
+
+**Interactive**:
+```
+User: /beads:iterate nixos-configs-abc123
+Assistant: I've found the plan. What changes would you like to make?
+User: Split Phase 2 into backend and frontend phases
+Assistant: I'll split Phase 2 into two separate phases...
+```

home/roles/development/commands/beads_plan.md

@@ -0,0 +1,306 @@
+---
+description: Create detailed implementation plans for a bead issue
+model: opus
+---
+
+# Beads Plan
+
+You are tasked with creating detailed implementation plans for a bead issue. This skill integrates with the beads issue tracker and stores plans in the `thoughts/` directory.
+
+## Initial Setup
+
+When this command is invoked:
+
+1. **Parse the input for bead ID**:
+   - If a bead ID is provided, use it
+   - If no bead ID, run `bd ready` and ask which bead to plan for
+
+2. **Load bead context**:
+   ```bash
+   bd show {bead-id}
+   ```
+   - Read the bead description for requirements
+   - Check for existing research: `thoughts/beads-{bead-id}/research.md`
+   - Note any dependencies or blockers
+
+3. **Create artifact directory**:
+   ```bash
+   mkdir -p thoughts/beads-{bead-id}
+   ```
+
+4. **Check for existing research**:
+   - If `thoughts/beads-{bead-id}/research.md` exists, read it fully
+   - This research provides crucial context for planning
+
+5. **Respond with**:
+   ```
+   Creating implementation plan for bead {bead-id}: {bead-title}
+
+   {If research exists: "Found existing research at thoughts/beads-{bead-id}/research.md - incorporating findings."}
+
+   Let me analyze the requirements and codebase to create a detailed plan.
+   ```
+
+## Planning Process
+
+### Step 1: Context Gathering
+
+1. **Read all mentioned files FULLY**:
+   - Bead description references
+   - Existing research document
+   - Any linked tickets or docs
+   - Use Read tool WITHOUT limit/offset
+
+2. **Check for contribution guidelines**:
+
+   ```bash
+   # Check standard locations for contribution guidelines
+   for f in CONTRIBUTING.md .github/CONTRIBUTING.md docs/CONTRIBUTING.md; do
+     if [ -f "$f" ]; then
+       echo "Found: $f"
+       break
+     fi
+   done
+   ```
+
+   If found:
+   - Read the file fully
+   - Extract actionable requirements (testing, code style, documentation, PR conventions)
+   - These requirements MUST be incorporated into the plan's Success Criteria
+
+   If not found, note "No contribution guidelines found" and proceed.
+
+3. **Spawn initial research tasks**:
+   - **codebase-locator**: Find all files related to the task
+   - **codebase-analyzer**: Understand current implementation
+   - **codebase-pattern-finder**: Find similar features to model after
+   - **thoughts-locator**: Find any existing plans or decisions
+
+4. **Read all files identified by research**:
+   - Read them FULLY into main context
+   - Cross-reference with requirements
+
+### Step 2: Present Understanding
+
+Before writing the plan, confirm understanding:
+
+```
+Based on the bead and my research, I understand we need to [accurate summary].
+
+I've found that:
+- [Current implementation detail with file:line reference]
+- [Relevant pattern or constraint discovered]
+- [Potential complexity or edge case identified]
+
+Questions that my research couldn't answer:
+- [Specific technical question requiring human judgment]
+- [Business logic clarification]
+```
+
+Only ask questions you genuinely cannot answer through code investigation.
+
+### Step 3: Research & Discovery
+
+After getting clarifications:
+
+1. **If user corrects any misunderstanding**:
+   - Spawn new research tasks to verify
+   - Read specific files/directories mentioned
+   - Only proceed once verified
+
+2. **Present design options**:
+   ```
+   Based on my research:
+
+   **Current State:**
+   - [Key discovery about existing code]
+   - [Pattern or convention to follow]
+
+   **Design Options:**
+   1. [Option A] - [pros/cons]
+   2. [Option B] - [pros/cons]
+
+   Which approach aligns best?
+   ```
+
+### Step 4: Plan Structure
+
+Once aligned on approach:
+
+```
+Here's my proposed plan structure:
+
+## Overview
+[1-2 sentence summary]
+
+## Implementation Phases:
+1. [Phase name] - [what it accomplishes]
+2. [Phase name] - [what it accomplishes]
+
+Does this phasing make sense?
+```
+
+Get feedback on structure before writing details.
+
+### Step 5: Write the Plan
+
+Write to `thoughts/beads-{bead-id}/plan.md`:
+
+```markdown
+---
+date: {ISO timestamp}
+bead_id: {bead-id}
+bead_title: "{bead title}"
+author: claude
+git_commit: {commit hash}
+branch: {branch name}
+repository: {repo name}
+status: draft
+---
+
+# {Feature/Task Name} Implementation Plan
+
+## Overview
+
+{Brief description of what we're implementing and why}
+
+## Current State Analysis
+
+{What exists now, what's missing, key constraints}
+
+### Key Discoveries:
+- {Finding with file:line reference}
+- {Pattern to follow}
+
+## Desired End State
+
+{Specification of desired end state and how to verify it}
+
+## What We're NOT Doing
+
+{Explicitly list out-of-scope items}
+
+## Implementation Approach
+
+{High-level strategy and reasoning}
+
+## Phase 1: {Descriptive Name}
+
+### Overview
+{What this phase accomplishes}
+
+### Changes Required:
+
+#### 1. {Component/File Group}
+**File**: `path/to/file.ext`
+**Changes**: {Summary}
+
+```{language}
+// Specific code to add/modify
+```
+
+### Success Criteria:
+
+#### Automated Verification:
+- [ ] Tests pass: `make test`
+- [ ] Linting passes: `make lint`
+- [ ] Type checking passes: `make typecheck`
+
+#### Manual Verification:
+- [ ] Feature works as expected in UI
+- [ ] Edge cases handled correctly
+
+---
+
+## Phase 2: {Descriptive Name}
+{Similar structure...}
+
+---
+
+## Testing Strategy
+
+### Unit Tests:
+- {What to test}
+- {Key edge cases}
+
+### Integration Tests:
+- {End-to-end scenarios}
+
+### Manual Testing Steps:
+1. {Specific step}
+2. {Another step}
+
+## References
+
+- Bead: {bead-id}
+- Research: `thoughts/beads-{bead-id}/research.md`
+- Similar implementation: {file:line}
+```
+
+### Step 6: Update the bead
+
+```bash
+bd update {bead-id} --notes="Plan created: thoughts/beads-{bead-id}/plan.md"
+```
+
+### Step 7: Create implementation bead (if appropriate)
+
+If the planning bead is separate from implementation:
+
+```bash
+bd create --title="Implement: {feature name}" --type=task --priority=1 \
+  --description="Implement the plan at thoughts/beads-{original-bead-id}/plan.md
+
+See bead {original-bead-id} for planning context."
+
+# Link as dependency
+bd dep add {new-bead-id} {original-bead-id}
+```
+
+### Step 8: Present for Review
+
+```
+I've created the implementation plan at:
+`thoughts/beads-{bead-id}/plan.md`
+
+Please review it and let me know:
+- Are the phases properly scoped?
+- Are the success criteria specific enough?
+- Any technical details that need adjustment?
+- Missing edge cases or considerations?
+```
+
+## Important Guidelines
+
+1. **Be Skeptical**: Question vague requirements, identify potential issues early
+2. **Be Interactive**: Don't write the full plan in one shot, get buy-in at each step
+3. **Be Thorough**: Read all context files COMPLETELY, include specific file:line refs
+4. **Be Practical**: Focus on incremental, testable changes
+5. **No Open Questions**: If you have unresolved questions, STOP and ask
+
+## Success Criteria Guidelines
+
+Always separate into two categories:
+
+**Automated Verification** (run by agents):
+- Commands: `make test`, `npm run lint`, etc.
+- File existence checks
+- Type checking
+
+**Manual Verification** (requires human):
+- UI/UX functionality
+- Performance under real conditions
+- Edge cases hard to automate
+
+**From Contribution Guidelines** (if CONTRIBUTING.md exists):
+- Include any testing requirements specified in guidelines
+- Include any code style/linting requirements
+- Include any documentation requirements
+- Reference the guideline: "Per CONTRIBUTING.md: {requirement}"
+
+## Example Invocation
+
+```
+User: /beads:plan nixos-configs-abc123
+Assistant: Creating implementation plan for bead nixos-configs-abc123...
+```

home/roles/development/commands/beads_research.md

@@ -0,0 +1,222 @@
+---
+description: Research a bead topic comprehensively and store findings in thoughts/
+model: opus
+---
+
+# Beads Research
+
+You are tasked with conducting comprehensive research for a bead issue. This skill integrates with the beads issue tracker and stores findings in the `thoughts/` directory.
+
+## CRITICAL: YOUR ONLY JOB IS TO DOCUMENT AND EXPLAIN THE CODEBASE AS IT EXISTS TODAY
+- DO NOT suggest improvements or changes unless the user explicitly asks for them
+- DO NOT perform root cause analysis unless the user explicitly asks for them
+- DO NOT propose future enhancements unless the user explicitly asks for them
+- DO NOT critique the implementation or identify problems
+- ONLY describe what exists, where it exists, how it works, and how components interact
+- You are creating a technical map/documentation of the existing system
+
+## Initial Setup
+
+When this command is invoked:
+
+1. **Parse the input for bead ID**:
+   - If a bead ID is provided (e.g., `nixos-configs-abc123`), use it
+   - If no bead ID provided, run `bd ready --type=research` to find research beads, or ask which bead to research
+
+2. **Load bead context**:
+   ```bash
+   bd show {bead-id}
+   ```
+   - Read the bead description to understand the research question
+   - Note any linked files or references in the bead
+
+3. **Create artifact directory**:
+   ```bash
+   mkdir -p thoughts/beads-{bead-id}
+   ```
+
+4. **Respond with**:
+   ```
+   Starting research for bead {bead-id}: {bead-title}
+
+   Research question: {extracted from bead description}
+
+   I'll analyze this thoroughly and store findings in thoughts/beads-{bead-id}/research.md
+   ```
+
+## Research Process
+
+### Step 1: Read any directly mentioned files
+- If the bead or user mentions specific files, read them FULLY first
+- Use the Read tool WITHOUT limit/offset parameters
+- Read these files yourself in the main context before spawning sub-tasks
+
+### Step 1.5: Check for contribution guidelines
+
+Before spawning sub-agents, check if the repository has contribution guidelines:
+
+```bash
+for f in CONTRIBUTING.md .github/CONTRIBUTING.md docs/CONTRIBUTING.md; do
+  if [ -f "$f" ]; then echo "Found: $f"; break; fi
+done
+```
+
+If found, read the file and note key requirements. These should be included in the research document under a "## Contribution Guidelines" section if relevant to the research question.
+
+### Step 2: Analyze and decompose the research question
+- Break down the query into composable research areas
+- Identify specific components, patterns, or concepts to investigate
+- Create a research plan using TodoWrite
+- Consider which directories, files, or patterns are relevant
+
+### Step 3: Spawn parallel sub-agent tasks
+
+Use specialized agents for research:
+
+**For codebase research:**
+- **codebase-locator** - Find WHERE files and components live
+- **codebase-analyzer** - Understand HOW specific code works
+- **codebase-pattern-finder** - Find examples of existing patterns
+
+**For thoughts directory:**
+- **thoughts-locator** - Discover what documents exist about the topic
+- **thoughts-analyzer** - Extract key insights from specific documents
+
+**For web research (only if explicitly requested):**
+- **web-search-researcher** - External documentation and resources
+
+Key principles:
+- Run multiple agents in parallel when searching for different things
+- Each agent knows its job - tell it what you're looking for, not HOW to search
+- Remind agents they are documenting, not evaluating
+
+### Step 4: Synthesize findings
+
+Wait for ALL sub-agents to complete, then:
+- Compile all results (codebase and thoughts findings)
+- Prioritize live codebase findings as primary source of truth
+- Connect findings across different components
+- Include specific file paths and line numbers
+- Highlight patterns, connections, and architectural decisions
+
+### Step 5: Gather metadata
+
+```bash
+# Git metadata
+git rev-parse HEAD                    # Current commit
+git branch --show-current             # Current branch
+basename $(git rev-parse --show-toplevel)  # Repo name
+date -Iseconds                        # Current timestamp
+```
+
+### Step 6: Write research document
+
+Write to `thoughts/beads-{bead-id}/research.md`:
+
+```markdown
+---
+date: {ISO timestamp with timezone}
+bead_id: {bead-id}
+bead_title: "{bead title}"
+researcher: claude
+git_commit: {commit hash}
+branch: {branch name}
+repository: {repo name}
+status: complete
+---
+
+# Research: {bead title}
+
+**Bead**: {bead-id}
+**Date**: {timestamp}
+**Git Commit**: {commit hash}
+**Branch**: {branch name}
+
+## Research Question
+{Original question from bead description}
+
+## Summary
+{High-level documentation answering the research question}
+
+## Detailed Findings
+
+### {Component/Area 1}
+- Description of what exists (file.ext:line)
+- How it connects to other components
+- Current implementation details
+
+### {Component/Area 2}
+...
+
+## Code References
+- `path/to/file.py:123` - Description
+- `another/file.ts:45-67` - Description
+
+## Architecture Documentation
+{Current patterns, conventions found in codebase}
+
+## Contribution Guidelines
+{If CONTRIBUTING.md exists, summarize key requirements relevant to the research topic}
+{If no guidelines found, omit this section}
+
+## Historical Context (from thoughts/)
+{Relevant insights from thoughts/ with references}
+
+## Open Questions
+{Any areas needing further investigation}
+```
+
+### Step 7: Update the bead
+
+```bash
+# Add artifact link to bead notes
+bd update {bead-id} --notes="Research complete: thoughts/beads-{bead-id}/research.md"
+```
+
+### Step 8: Autonomy decision
+
+**For research beads (type=research):**
+- If research is complete and comprehensive, close the bead:
+  ```bash
+  bd close {bead-id} --reason="Research complete. See thoughts/beads-{bead-id}/research.md"
+  ```
+- Present summary to user
+
+**For other bead types:**
+- Do NOT close the bead
+- Present findings and ask how to proceed
+
+### Step 9: Handle follow-up questions
+
+If the user has follow-up questions:
+- Append to the same research document
+- Add a new section: `## Follow-up Research [{timestamp}]`
+- Update the bead notes with the new findings
+
+## Important Guidelines
+
+- Always use parallel Task agents to maximize efficiency
+- Always run fresh codebase research - never rely solely on existing documents
+- Focus on finding concrete file paths and line numbers
+- Research documents should be self-contained
+- Document cross-component connections
+- Include temporal context (when research was conducted)
+- Keep the main agent focused on synthesis, not deep file reading
+- **CRITICAL**: You and all sub-agents are documentarians, not evaluators
+- **REMEMBER**: Document what IS, not what SHOULD BE
+
+## Example Invocation
+
+```
+User: /beads:research nixos-configs-abc123
+Assistant: Starting research for bead nixos-configs-abc123: Investigate auth flow
+...
+```
+
+Or without bead ID:
+```
+User: /beads:research
+Assistant: Let me check for research beads...
+[runs bd ready]
+Which bead would you like me to research?
+```

home/roles/development/commands/beads_workflow.md

@@ -0,0 +1,387 @@
+---
+description: Comprehensive guide for the beads + humanlayer integrated workflow
+---
+
+# Beads Workflow Guide
+
+This document describes the integrated workflow combining **beads** (issue tracking) with **humanlayer-style skills** (deep research, planning, implementation).
+
+## Philosophy
+
+### Two Systems, Complementary Purposes
+
+| System | Purpose | Storage |
+|--------|---------|---------|
+| **Beads** | Track WHAT work exists | `.beads/` (git-synced) |
+| **Thoughts** | Store HOW to do the work | `thoughts/` (local or symlinked) |
+
+### Autonomy Model
+
+| Bead Type | Agent Autonomy | Checkpoint |
+|-----------|----------------|------------|
+| `research` | **Full** - agent closes when satisfied | None |
+| `feature`, `task`, `bug` | **Checkpointed** - pause for validation | Per-plan |
+
+**Key insight**: Research produces artifacts. Implementation produces commits. Commits are the review boundary.
+
+## Directory Structure
+
+```
+project/
+├── .beads/                              # Beads database (git-synced)
+│   ├── beads.db
+│   ├── config.yaml
+│   └── issues.jsonl
+├── thoughts/                            # Artifacts (local or symlink)
+│   ├── beads-{id}/                      # Per-bead artifacts
+│   │   ├── research.md
+│   │   ├── plan.md
+│   │   └── plan-v1.md                   # Iteration history
+│   └── shared/                          # Legacy/non-bead artifacts
+│       ├── research/
+│       └── plans/
+└── home/roles/development/skills/       # Skill definitions
+    ├── beads_research.md
+    ├── beads_plan.md
+    ├── beads_implement.md
+    └── beads_iterate.md
+```
+
+## When to Use What
+
+### Use Beads When:
+- Work spans multiple sessions
+- Work has dependencies or blockers
+- You need to track status across interruptions
+- Multiple related tasks need coordination
+- Context recovery after compaction matters
+
+### Use TodoWrite When:
+- Single-session execution tracking
+- Breaking down work within a session
+- Tracking progress on a single bead
+
+### Use Both Together:
+- Beads track the overall work items
+- TodoWrite tracks progress within a session
+- Example: Bead for "Implement auth", TodoWrite for each file being edited
+
+## Workflow Patterns
+
+### Pattern 1: Research-First Approach
+
+```
+1. Create research bead
+   bd create --title="Research auth patterns" --type=research --priority=1
+
+2. Run research
+   /beads:research {bead-id}
+   → Agent researches, writes to thoughts/beads-{id}/research.md
+   → Agent closes bead when satisfied
+
+3. Create implementation bead
+   bd create --title="Implement auth" --type=feature --priority=1
+
+4. Plan the implementation
+   /beads:plan {bead-id}
+   → Agent reads prior research, creates plan
+   → Plan saved to thoughts/beads-{id}/plan.md
+
+5. Implement
+   /beads:implement {bead-id}
+   → Agent follows plan, pauses for manual verification
+   → You validate, agent closes bead
+```
+
+### Pattern 2: Direct Implementation
+
+For well-understood tasks without research:
+
+```
+1. Create bead
+   bd create --title="Fix login bug" --type=bug --priority=0
+
+2. Plan and implement
+   /beads:plan {bead-id}
+   → Quick planning based on bead description
+
+   /beads:implement {bead-id}
+   → Follow plan, pause at checkpoint
+```
+
+### Pattern 3: Iterative Planning
+
+When requirements evolve:
+
+```
+1. Initial plan
+   /beads:plan {bead-id}
+
+2. Iterate based on feedback
+   /beads:iterate {bead-id} - add error handling phase
+
+3. Iterate again if needed
+   /beads:iterate {bead-id} - split phase 2 into backend/frontend
+
+4. Implement when plan is solid
+   /beads:implement {bead-id}
+```
+
+### Pattern 4: Parallel Work
+
+Using parallel_beads skill for multiple independent tasks:
+
+```
+1. Check what's ready
+   bd ready
+
+2. Select multiple beads
+   /parallel_beads
+   → Select beads to work on
+   → Each gets worktree, PR, review
+
+3. Reconcile after PRs merge
+   /reconcile_beads
+```
+
+## Skills Reference
+
+### /beads:research {bead-id}
+- Conducts comprehensive codebase research
+- Uses parallel sub-agents for efficiency
+- Outputs to `thoughts/beads-{id}/research.md`
+- **Autonomy**: Can close research beads automatically
+
+### /beads:plan {bead-id}
+- Creates detailed implementation plans
+- Interactive process with checkpoints
+- Outputs to `thoughts/beads-{id}/plan.md`
+- Can create dependent implementation beads
+
+### /beads:implement {bead-id}
+- Follows plans from thoughts/
+- Updates plan checkboxes for resumability
+- **Checkpoint**: Pauses after plan completion for manual verification
+- Only closes bead after human confirms
+
+### /beads:iterate {bead-id}
+- Updates existing plans based on feedback
+- Preserves plan structure while making targeted changes
+- Saves iteration history as `plan-v{N}.md`
+
+### /parallel_beads
+- Orchestrates parallel bead processing
+- Creates worktrees, PRs, reviews for multiple beads
+- Good for batching independent work
+
+### /reconcile_beads
+- Closes beads whose PRs have merged
+- Run after merging PRs to keep beads in sync
+
+## Session Protocols
+
+### Starting a Session
+
+```bash
+# Check what's available
+bd ready
+
+# Pick work and start
+bd update {bead-id} --status=in_progress
+```
+
+### Ending a Session
+
+```bash
+# Always run this checklist:
+[ ] git status                    # Check changes
+[ ] git add <files>               # Stage code changes
+[ ] bd sync                       # Sync beads
+[ ] git commit -m "..."           # Commit code
+[ ] git push                      # Push to remote
+```
+
+### Resuming Work
+
+```bash
+# Find in-progress work
+bd list --status=in_progress
+
+# Check bead notes for context
+bd show {bead-id}
+
+# Check for partial plan progress
+cat thoughts/beads-{id}/plan.md | grep "\[x\]"
+```
+
+## Thoughts Directory Patterns
+
+### For Work Repos (via symlink)
+```
+project/thoughts → ~/thoughts/repos/{repo-name}/
+```
+- Syncs via codelayer to work remote
+- Shared across projects on same machine
+
+### For Personal Repos (local)
+```
+project/thoughts/  # Regular directory, not symlink
+```
+- Stays local to project
+- Committed with project or gitignored
+
+### Determining Which Pattern
+```bash
+# Check if thoughts is a symlink
+ls -la thoughts
+
+# If symlink, it points to ~/thoughts/repos/{repo}/
+# If directory, it's local to this project
+```
+
+## Best Practices
+
+### 1. Bead Descriptions Matter
+Write clear descriptions - they're the input for research and planning:
+```bash
+bd create --title="Implement user preferences" --type=feature \
+  --description="Add user preferences storage and UI.
+
+Requirements:
+- Store preferences in SQLite
+- Expose via REST API
+- Add settings page in UI
+
+See related: thoughts/shared/research/preferences-patterns.md"
+```
+
+### 2. Link Artifacts in Beads
+Always update bead notes with artifact locations:
+```bash
+bd update {id} --notes="Research: thoughts/beads-{id}/research.md
+Plan: thoughts/beads-{id}/plan.md"
+```
+
+### 3. Use Dependencies
+Structure work with dependencies:
+```bash
+# Research blocks planning
+bd dep add {plan-bead} {research-bead}
+
+# Planning blocks implementation
+bd dep add {impl-bead} {plan-bead}
+```
+
+### 4. Trust the Checkpoint Model
+- Research beads: Let agent close them
+- Implementation beads: Always validate before closing
+- If in doubt, err on the side of checkpoints
+
+### 5. Keep Plans Updated
+- Check off completed items as you go
+- Update notes with progress
+- This enables seamless resume across sessions
+
+## Troubleshooting
+
+### "What bead should I work on?"
+```bash
+bd ready  # Shows unblocked work
+```
+
+### "Where did the research go?"
+```bash
+ls thoughts/beads-{id}/
+bd show {id}  # Check notes for artifact links
+```
+
+### "Plan doesn't match reality"
+```bash
+/beads:iterate {id}  # Update plan based on findings
+```
+
+### "Session ended mid-implementation"
+```bash
+bd show {id}  # Check notes for progress
+cat thoughts/beads-{id}/plan.md | grep "\[x\]"  # See completed items
+/beads:implement {id}  # Resume - will pick up from last checkpoint
+```
+
+### "Bead is blocked"
+```bash
+bd show {id}  # See what's blocking
+bd blocked    # See all blocked beads
+```
+
+## Migration Notes
+
+### From Pure Humanlayer to Beads+Humanlayer
+
+Old pattern:
+```
+thoughts/shared/research/2025-01-01-topic.md
+thoughts/shared/plans/2025-01-01-feature.md
+```
+
+New pattern:
+```
+thoughts/beads-{id}/research.md
+thoughts/beads-{id}/plan.md
+```
+
+The `shared/` structure still works for non-bead artifacts, but prefer per-bead directories for tracked work.
+
+### Existing Content
+- Keep existing `thoughts/shared/` content
+- New bead-tracked work uses `thoughts/beads-{id}/`
+- Reference old research from bead descriptions when relevant
+
+## Design Decisions
+
+### Phase Tracking: Artifacts vs Statuses
+
+**Current approach**: Skills infer workflow phase from artifact presence:
+- Has `research.md` → research done
+- Has `plan.md` → planning done
+- No artifacts → needs research/planning
+
+**Alternative considered**: Explicit phase statuses (`needs_research`, `needs_plan`, `implementing`, etc.)
+
+**Why artifacts win**:
+1. **Single source of truth** - Status can't drift from reality
+2. **Less state to maintain** - No need to update status when creating artifacts
+3. **Works across repos** - No custom status config needed
+4. **Skills already check artifacts** - Natural fit with existing behavior
+
+**When explicit statuses would help**:
+- Pipeline visualization (e.g., `bd list --status=needs_plan`)
+- Agent self-selection by phase
+- Team coordination dashboards
+
+**Recommendation**: Keep artifact-inference as primary mechanism. If pipeline visibility becomes important, consider adding statuses that skills auto-set when creating artifacts (advisory, not enforced).
+
+### One Bead Per Feature (Default)
+
+**Current approach**: File one bead per logical feature. Skills handle phases internally.
+
+**Alternative considered**: Separate beads for research → planning → implementation, linked by dependencies.
+
+**Why single bead wins for most work**:
+1. **Lower friction** - Quick idea dump without filing 3 tickets
+2. **Simpler tracking** - One status to check
+3. **Natural grouping** - Artifacts stay together in `thoughts/beads-{id}/`
+
+**When to split into multiple beads**:
+- Research reveals the work should be multiple features
+- Different phases need different assignees
+- Explicit dependency tracking matters (e.g., "auth must ship before payments")
+
+**The discovered-work pattern**: Start with one bead. If research reveals split work, file additional beads with dependencies. Skills guide this naturally.
+
+### Plan Requirements by Type
+
+**Bug fixes** (`type=bug`): Can proceed without plans - usually well-scoped from bug report.
+
+**Features/tasks** (`type=feature`, `type=task`): Should have plans - helps ensure design is sound before implementation.
+
+This is advisory, not enforced. Skills warn but allow override for simple changes.

home/roles/development/commands/gitea_pr_review.md

@@ -0,0 +1,472 @@
+---
+description: Address Gitea/Forgejo PR review comments with code changes
+---
+
+# Gitea PR Review
+
+You are tasked with **addressing** PR review comments by making code changes, then summarizing what was done. This skill drives PR progress, not just conversation.
+
+## Philosophy
+
+**Comments are work items, not conversation starters.**
+
+When a reviewer leaves a comment, they're identifying something that needs attention. This skill:
+1. Categorizes comments by actionability
+2. Makes code changes to address actionable comments
+3. Commits and pushes those changes
+4. Posts a single summary comment describing what was done
+
+## Prerequisites
+
+- `tea` CLI configured with a Gitea/Forgejo instance
+- Access token from tea config: `~/.config/tea/config.yml`
+- Repository must be a Gitea/Forgejo remote (not GitHub)
+- **Nix users**: All tools available via nixpkgs (`nix run nixpkgs#tea`)
+
+## Initial Setup
+
+When this command is invoked:
+
+1. **Parse the input for PR number**:
+   - If a PR number is provided as argument, use it
+   - If no PR number, detect from current branch (see PR Detection section)
+
+2. **Verify required tools are available**:
+   ```bash
+   which tea
+   ```
+
+   If tea is missing:
+   ```
+   Error: `tea` CLI not found.
+
+   Please install:
+   - Nix: nix run nixpkgs#tea
+   - Other: https://gitea.com/gitea/tea
+   ```
+   **STOP** if tea is missing.
+
+3. **Extract configuration from tea config**:
+   ```bash
+   # Read tea config (it's YAML but simple enough to grep)
+   TEA_CONFIG="$HOME/.config/tea/config.yml"
+   GITEA_URL=$(grep -A1 'logins:' "$TEA_CONFIG" | grep 'url:' | head -1 | sed 's/.*url: //')
+   TOKEN=$(grep -A5 'logins:' "$TEA_CONFIG" | grep 'token:' | head -1 | sed 's/.*token: //')
+   ```
+
+   If config is missing or invalid:
+   ```
+   Error: Could not read tea config at ~/.config/tea/config.yml
+
+   Please ensure `tea` is installed and configured:
+   1. Install tea
+   2. Log in: tea login add --url https://your-gitea-instance --token YOUR_TOKEN
+   ```
+   **STOP** if config is invalid.
+
+4. **Detect repository info from git remote**:
+   ```bash
+   REMOTE_URL=$(git remote get-url origin)
+   # Parse owner and repo from URL (handles both SSH and HTTPS)
+   OWNER=$(echo "$REMOTE_URL" | sed -E 's#.*[:/]([^/]+)/[^/]+\.git$#\1#')
+   REPO=$(echo "$REMOTE_URL" | sed -E 's#.*/([^/]+)\.git$#\1#')
+   ```
+
+5. **Ensure we're on the PR branch**:
+   ```bash
+   CURRENT_BRANCH=$(git branch --show-current)
+   # Verify this branch corresponds to the PR
+   ```
+
+6. **Respond with**:
+   ```
+   Addressing PR review comments for PR #{PR_NUMBER}...
+
+   Repository: {OWNER}/{REPO}
+   Branch: {CURRENT_BRANCH}
+   Gitea URL: {GITEA_URL}
+   ```
+
+## PR Detection
+
+If no PR number is provided, detect from the current branch:
+
+```bash
+CURRENT_BRANCH=$(git branch --show-current)
+tea pr list --fields index,head --output simple | grep "$CURRENT_BRANCH"
+```
+
+If no PR exists for the current branch, use `AskUserQuestion`:
+
+```
+No PR found for branch '{CURRENT_BRANCH}'.
+
+Would you like to:
+1. Enter a PR number manually
+2. Cancel
+```
+
+## Workflow
+
+### Step 1: Fetch and Parse Comments
+
+Fetch all reviews and their comments:
+
+```bash
+# Fetch reviews (filter out dismissed reviews)
+curl -s -H "Authorization: token $TOKEN" \
+  "$GITEA_URL/api/v1/repos/$OWNER/$REPO/pulls/$PR_NUMBER/reviews" \
+  | jq '[.[] | select(.dismissed != true)]'
+
+# For each review, fetch comments
+curl -s -H "Authorization: token $TOKEN" \
+  "$GITEA_URL/api/v1/repos/$OWNER/$REPO/pulls/$PR_NUMBER/reviews/$REVIEW_ID/comments"
+```
+
+**Filter resolved comments**: When processing comments, skip any that have been marked as resolved. Check the `resolver` field in the comment response - if it's not null, the comment has been resolved and should be skipped.
+
+```bash
+# Example: Filter to only unresolved comments
+jq '[.[] | select(.resolver == null)]'
+```
+
+If no reviews found or all comments are resolved:
+```
+No unresolved reviews found for PR #{PR_NUMBER}.
+Nothing to address.
+```
+**STOP** here.
+
+### Step 2: Categorize Comments
+
+For each comment, categorize it as one of:
+
+| Category | Description | Action |
+|----------|-------------|--------|
+| **actionable** | Requests a code change, addition, or fix | Launch subagent to make change |
+| **question** | Asks for clarification or explanation | Include answer in summary |
+| **acknowledged** | FYI, self-resolved, or "no action needed" noted | Note in summary |
+| **blocked** | Requires external input or is out of scope | Flag for user |
+
+**Categorization heuristics**:
+- Contains "add", "change", "fix", "update", "consider adding", "should be" → **actionable**
+- Contains "?" or "why", "how", "what" → **question**
+- Contains "no need to update", "will be separate", "acknowledged" → **acknowledged**
+- Contains "discuss", "later", "out of scope", "blocked by" → **blocked**
+
+Display the categorization:
+```
+## Comment Analysis
+
+### Actionable (will make changes):
+1. {file}:{line} - "{comment_summary}" → Will add nix note to prerequisites
+
+### Questions (will answer in summary):
+2. {file}:{line} - "{comment_summary}" → Explain CI token approach
+
+### Acknowledged (no action needed):
+3. {file}:{line} - "{comment_summary}" → Reviewer noted separate skill
+
+### Blocked (needs input):
+(none)
+```
+
+### Step 3: User Confirmation
+
+Use `AskUserQuestion` to confirm the plan:
+
+```
+I've categorized {N} comments. My plan:
+
+**Will make changes for:**
+- {file}:{line}: {planned_change}
+
+**Will explain in summary:**
+- {file}:{line}: {planned_explanation}
+
+**No action needed:**
+- {file}:{line}: {reason}
+
+Proceed with this plan?
+```
+
+Options:
+1. **Proceed** - Execute the plan
+2. **Modify** - Let user adjust categorization
+3. **Cancel** - Exit without changes
+
+### Step 4: Address Actionable Comments (Parallel Subagents)
+
+For each actionable comment, launch a subagent using the Task tool:
+
+```
+Launch Task subagent with:
+- subagent_type: "general-purpose"
+- prompt: |
+    You are addressing a PR review comment. Make the requested change and nothing else.
+
+    **File**: {file_path}
+    **Line**: {line_number}
+    **Comment**: {comment_body}
+    **Diff context**:
+    ```
+    {diff_hunk}
+    ```
+
+    Instructions:
+    1. Read the file to understand context
+    2. Make the minimal change to address the comment
+    3. Do NOT commit - just make the edit
+    4. Report what you changed
+
+    Be precise. Only change what's needed to address this specific comment.
+```
+
+**Important**: Launch actionable comment subagents in parallel when they touch different files. For comments on the same file, run sequentially to avoid conflicts.
+
+Wait for all subagents to complete and collect their results.
+
+### Step 5: Commit and Push
+
+After all subagents complete:
+
+1. **Stage changes**:
+   ```bash
+   git add -A
+   ```
+
+2. **Create commit with summary**:
+   ```bash
+   git commit -m "Address PR review comments
+
+   Changes made:
+   - {file1}: {change_summary}
+   - {file2}: {change_summary}
+
+   Addresses comments from review by {reviewer}"
+   ```
+
+3. **Push to remote**:
+   ```bash
+   git push
+   ```
+
+### Step 6: Post Summary Comment
+
+Post a single comment summarizing all actions taken:
+
+```bash
+tea comment $PR_NUMBER "$(cat <<'EOF'
+## Review Comments Addressed
+
+cc @{reviewer1} @{reviewer2}
+
+**Changes made** (commit {SHORT_SHA}):
+- `{file1}:{line}`: {what_was_changed}
+- `{file2}:{line}`: {what_was_changed}
+
+**Responses to questions**:
+- `{file3}:{line}`: {answer_to_question}
+
+**Acknowledged** (no action needed):
+- `{file4}:{line}`: {reason_no_action}
+
+---
+*Automated response via /gitea_pr_review*
+EOF
+)"
+```
+
+### Step 7: Final Summary
+
+Display to user:
+
+```
+## PR Review Complete
+
+**Commit**: {SHA}
+**Changes**: {N} files modified
+
+### Actions Taken:
+- [x] {file1}:{line} - Added nix prerequisite note
+- [x] {file2}:{line} - Explained CI approach in comment
+- [ ] {file3}:{line} - Acknowledged (separate skill)
+
+**Reviewers tagged**: @{reviewer1}, @{reviewer2}
+**Comment posted**: {comment_url}
+
+PR URL: {GITEA_URL}/{OWNER}/{REPO}/pulls/{PR_NUMBER}
+```
+
+**Note**: When posting the summary comment, tag all reviewers who left comments so they receive notifications about the changes.
+
+## Error Handling
+
+### Subagent failed to make change
+
+If a subagent fails:
+```
+Warning: Could not address comment on {file}:{line}
+
+Reason: {error}
+
+Options:
+1. Skip this comment and continue
+2. Retry with manual guidance
+3. Abort all changes
+```
+
+### Push failed
+
+```
+Error pushing changes: {error}
+
+Your changes are committed locally. You may need to:
+1. Pull and resolve conflicts: git pull --rebase
+2. Push again: git push
+```
+
+### No actionable comments
+
+If all comments are questions/acknowledged:
+```
+No code changes needed.
+
+All comments are either questions or acknowledged items.
+Posting summary comment with explanations...
+```
+
+## API Reference
+
+### Endpoints Used
+
+| Action | Method | Endpoint |
+|--------|--------|----------|
+| List reviews | GET | `/api/v1/repos/{owner}/{repo}/pulls/{index}/reviews` |
+| Get review comments | GET | `/api/v1/repos/{owner}/{repo}/pulls/{index}/reviews/{id}/comments` |
+| Create issue comment | POST | via `tea comment` |
+
+### Review States
+
+- `PENDING` - Draft review not yet submitted
+- `COMMENT` - General comment without approval/rejection
+- `APPROVE` - Approving the changes
+- `REQUEST_CHANGES` - Requesting changes before merge
+
+## Shell Command Patterns
+
+Claude Code's bash execution has quirks. Use these patterns for reliability:
+
+### curl requests
+
+**DO** - Use single quotes for URL and header separately:
+```bash
+curl -s 'https://git.example.com/api/v1/repos/owner/repo/pulls/1/reviews' \
+  -H 'Authorization: token YOUR_TOKEN_HERE' | jq .
+```
+
+**DON'T** - Variable expansion in `-H` flag often fails:
+```bash
+# This may fail with "blank argument" errors
+curl -s -H "Authorization: token $TOKEN" "$URL"
+```
+
+### Iterating over reviews
+
+**DO** - Run separate commands for each review ID:
+```bash
+echo "=== Review 4 ===" && curl -s 'URL/reviews/4/comments' -H 'Authorization: token ...' | jq .
+echo "=== Review 5 ===" && curl -s 'URL/reviews/5/comments' -H 'Authorization: token ...' | jq .
+```
+
+**DON'T** - For loops with multiline bodies often fail:
+```bash
+# This may cause syntax errors
+for id in 4 5 6; do
+  curl -s "URL/reviews/$id/comments"
+done
+```
+
+### tea comment
+
+**DO** - Use single-quoted string for comment body:
+```bash
+tea comment 26 '## Summary
+
+Changes made:
+- Item 1
+- Item 2'
+```
+
+**DON'T** - Heredocs may hang or timeout:
+```bash
+# This may hang indefinitely
+tea comment 26 "$(cat <<'EOF'
+...
+EOF
+)"
+```
+
+## Limitations
+
+1. **Thread replies**: Gitea API doesn't support inline thread replies. We post a single summary comment instead.
+
+2. **Complex changes**: For comments requiring significant refactoring, the subagent may need guidance. The skill will flag these as "blocked" for user input.
+
+3. **Merge conflicts**: If the branch is behind, you may need to rebase before changes can be pushed.
+
+## Example Session
+
+```
+User: /gitea_pr_review 26
+Assistant: Addressing PR review comments for PR #26...
+
+Repository: johno/nixos-configs
+Branch: bead/nixos-configs-vru
+Gitea URL: https://git.johnogle.info
+
+## Comment Analysis
+
+### Actionable (will make changes):
+1. gitea_pr_review.md:12 - "could we indicate nix+nixpkgs satisfies this?" 
+   → Will add note that nix users can get tools via nixpkgs
+
+### Questions (will answer in summary):
+(none)
+
+### Acknowledged (no action needed):
+2. gitea_pr_review.md:50 - "we eventually want to run this in CI..."
+   → Reviewer noted this will be a separate skill
+
+Proceed with this plan? [Proceed]
+
+Launching subagent to address comment 1...
+[Subagent completes edit]
+
+Committing changes...
+[abc1234] Address PR review comments
+
+Pushing to remote...
+Done.
+
+Posting summary comment...
+
+## PR Review Complete
+
+**Commit**: abc1234
+**Changes**: 1 file modified
+
+### Actions Taken:
+- [x] gitea_pr_review.md:12 - Added nix prerequisite note  
+- [ ] gitea_pr_review.md:50 - Acknowledged (separate skill)
+
+**Comment posted**: https://git.johnogle.info/.../pulls/26#issuecomment-XXX
+
+PR URL: https://git.johnogle.info/johno/nixos-configs/pulls/26
+```
+
+## See Also
+
+- `tea` CLI: https://gitea.com/gitea/tea
+- Gitea API: https://docs.gitea.com/api/
+- `/beads_workflow` for full development workflow

home/roles/development/commands/import_gitea_issues.md

@@ -0,0 +1,130 @@
+---
+description: Import open Gitea issues as beads, skipping already-imported ones
+---
+
+# Import Gitea Issues as Beads
+
+This skill imports open Gitea issues as beads, checking for duplicates to avoid re-importing already tracked issues.
+
+## Prerequisites
+
+- `tea` CLI must be installed and configured for the repository
+- `bd` (beads) CLI must be installed
+- Must be in a git repository with a Gitea/Forgejo remote
+
+## Workflow
+
+### Step 1: Get open Gitea issues
+
+List all open issues using `tea`:
+
+```bash
+tea issues
+```
+
+This returns a table with columns: INDEX, TITLE, LABELS, MILESTONE
+
+### Step 2: Get existing beads
+
+List all current beads to check what's already imported:
+
+```bash
+bd list
+```
+
+Also check bead notes for issue URLs to identify imports:
+
+```bash
+bd list --json | jq -r '.[] | select(.notes != null) | .notes' | grep -oP 'issues/\K\d+'
+```
+
+### Step 3: Check for already-linked PRs
+
+Check if any open PRs reference beads (skip these issues as they're being worked on):
+
+```bash
+tea pr list
+```
+
+Look for PRs with:
+- Bead ID in title: `[nixos-configs-xxx]`
+- Bead reference in body: `Implements bead:` or `Bead ID:`
+
+### Step 4: For each untracked issue, create a bead
+
+For each issue not already tracked:
+
+1. **Get full issue details**:
+   ```bash
+   tea issue [ISSUE_NUMBER]
+   ```
+
+2. **Determine bead type** based on issue content:
+   - "bug" - if issue mentions bug, error, broken, fix, crash
+   - "feature" - if issue mentions feature, add, new, enhancement
+   - "task" - default for other issues
+
+3. **Create the bead**:
+   ```bash
+   bd add "[ISSUE_TITLE]" \
+     --type=[TYPE] \
+     --priority=P2 \
+     --notes="Gitea issue: [ISSUE_URL]
+
+   Original issue description:
+   [ISSUE_BODY]"
+   ```
+
+   Note: The `--notes` flag accepts multi-line content.
+
+### Step 5: Report results
+
+Present a summary:
+
+```
+## Gitea Issues Import Summary
+
+### Imported as Beads
+| Issue | Title | Bead ID | Type |
+|-------|-------|---------|------|
+| #5 | Add dark mode | nixos-configs-abc | feature |
+| #3 | Config broken on reboot | nixos-configs-def | bug |
+
+### Skipped (Already Tracked)
+| Issue | Title | Reason |
+|-------|-------|--------|
+| #4 | Update flake | Existing bead: nixos-configs-xyz |
+| #2 | Refactor roles | PR #7 references bead |
+
+### Skipped (Other)
+| Issue | Title | Reason |
+|-------|-------|--------|
+| #1 | Discussion: future plans | No actionable work |
+```
+
+## Type Detection Heuristics
+
+Keywords to detect issue type:
+
+**Bug indicators** (case-insensitive):
+- bug, error, broken, fix, crash, fail, issue, problem, wrong, not working
+
+**Feature indicators** (case-insensitive):
+- feature, add, new, enhancement, implement, support, request, want, would be nice
+
+**Task** (default):
+- Anything not matching bug or feature patterns
+
+## Error Handling
+
+- **tea not configured**: Report error and exit
+- **bd not available**: Report error and exit
+- **Issue already has bead**: Skip and report in summary
+- **Issue is a PR**: Skip (tea shows PRs and issues separately)
+
+## Notes
+
+- Default priority is P2; adjust manually after import if needed
+- Issue labels from Gitea are not automatically mapped to bead tags
+- Run this periodically to catch new issues
+- After import, use `bd ready` to see which beads can be worked on

home/roles/development/commands/parallel_beads.md

@@ -0,0 +1,409 @@
+---
+description: Orchestrate parallel bead processing with worktrees, PRs, and reviews
+---
+
+# Parallel Beads Workflow
+
+This skill orchestrates parallel bead processing using subagents. Each bead gets its own worktree, implementation, PR, and review.
+
+## Phase 1: Selection
+
+1. **Get ready beads**: Run `bd ready` to list all beads with no blockers
+
+2. **Filter by plan readiness**:
+   For each ready bead, check if it's ready for batch implementation:
+   - **Has plan** (`thoughts/beads-{id}/plan.md` exists): Include
+   - **type=bug** without plan: Include (simple bugs can implement directly)
+   - **type=feature/task** without plan: Exclude with warning
+
+   ```bash
+   # Check for plan existence
+   ls thoughts/beads-{bead-id}/plan.md 2>/dev/null
+   ```
+
+3. **Report skipped beads**:
+   If any beads were skipped, inform the user:
+   ```
+   Skipped beads (no plan):
+   - {bead-id}: {title} (type: feature) - Run /beads_plan {bead-id} first
+   - {bead-id}: {title} (type: task) - Run /beads_plan {bead-id} first
+   ```
+
+4. **Present selection**: Use `AskUserQuestion` with `multiSelect: true` to let the user choose which beads to work on
+   - Include bead ID and title for each option
+   - Only show beads that passed the plan check
+   - Allow selection of multiple beads
+
+Example:
+```
+AskUserQuestion with:
+- question: "Which beads do you want to work on in parallel?"
+- multiSelect: true
+- options from filtered bd ready output
+```
+
+## Phase 2: Worktree Setup
+
+Before launching implementation subagents, create worktrees for all selected beads:
+
+1. **Get repository name**:
+   ```bash
+   REPO_NAME=$(git remote get-url origin | sed 's|.*/||' | sed 's/\.git$//')
+   ```
+
+2. **For each selected bead**, create its worktree:
+   ```bash
+   BEAD_ID="[bead-id]"
+   # Check if worktree already exists
+   if [ -d "$HOME/wt/${REPO_NAME}/${BEAD_ID}" ]; then
+     echo "Worktree already exists: ~/wt/${REPO_NAME}/${BEAD_ID}"
+     # Ask user: remove and recreate, or skip this bead?
+   else
+     git worktree add -b "bead/${BEAD_ID}" "$HOME/wt/${REPO_NAME}/${BEAD_ID}"
+   fi
+   ```
+
+3. **Track created worktrees**:
+   Maintain a list of (bead_id, worktree_path) pairs for use in subagent instructions.
+
+4. **Report status**:
+   ```
+   Created worktrees:
+   - nixos-configs-abc → ~/wt/nixos-configs/nixos-configs-abc (branch: bead/nixos-configs-abc)
+   - nixos-configs-xyz → ~/wt/nixos-configs/nixos-configs-xyz (branch: bead/nixos-configs-xyz)
+
+   Skipped (existing worktree):
+   - nixos-configs-123 → Ask user for resolution
+   ```
+
+**Note**: If a worktree or branch already exists, ask the user before proceeding:
+- Remove existing worktree and branch, then recreate
+- Skip this bead
+- Use existing worktree as-is (risky - branch may have diverged)
+
+## Phase 3: Parallel Implementation
+
+For each selected bead, launch a subagent using the Task tool. All subagents should be launched in parallel (single message with multiple Task tool calls).
+
+### Subagent Instructions Template
+
+Each implementation subagent should receive these instructions:
+
+```
+Work on bead [BEAD_ID]: [BEAD_TITLE]
+
+Worktree path: [WORKTREE_PATH]
+
+## CRITICAL: Branch Verification (MUST DO FIRST)
+
+1. **Navigate to worktree**:
+   ```bash
+   cd [WORKTREE_PATH]
+   ```
+
+2. **Verify branch** (MANDATORY before ANY modifications):
+   ```bash
+   CURRENT_BRANCH=$(git branch --show-current)
+   echo "Current branch: $CURRENT_BRANCH"
+   pwd
+   ```
+
+   **ABORT CONDITIONS** - If ANY of these are true, STOP IMMEDIATELY:
+   - Branch is `main` or `master`
+   - Branch does not match `bead/[BEAD_ID]`
+
+   If you detect any abort condition:
+   ```
+   ABORTING: Branch verification failed.
+   Expected branch: bead/[BEAD_ID]
+   Actual branch: [CURRENT_BRANCH]
+   Working directory: [pwd output]
+
+   DO NOT PROCEED. Report this error to the orchestrator.
+   ```
+
+## After Verification Passes
+
+3. **Review the bead requirements**:
+   - Run `bd show [BEAD_ID]` to understand the acceptance criteria
+   - Note any external issue references (GitHub issues, Linear tickets, etc.)
+
+4. **Extract validation criteria**:
+   - Check for a plan: `thoughts/beads-[BEAD_ID]/plan.md`
+   - If plan exists:
+     - Read the plan and find the "Automated Verification" section
+     - Extract each verification command (lines starting with `- [ ]` followed by a command)
+     - Example: `- [ ] Tests pass: \`make test\`` → extract `make test`
+     - Note any "Per CONTRIBUTING.md:" requirements for additional validation
+     - Also read the "Manual Verification" section from the plan if present
+     - Save manual verification items for inclusion in the PR description (they won't be executed)
+   - If no plan exists, use best-effort validation:
+     - Check if `Makefile` exists → try `make test` and `make lint`
+     - Check if `flake.nix` exists → try `nix flake check`
+     - Check if `package.json` exists → try `npm test`
+     - **Check for CONTRIBUTING.md** → read and extract testing/linting requirements
+       - Track which requirements can be automated vs need manual review
+       - Automated: commands that can be run (e.g., "run `make test`")
+       - Manual: qualitative checks (e.g., "ensure documentation is updated")
+     - If none found, note "No validation criteria found"
+
+5. **Implement the changes**:
+   - Work in the worktree directory
+   - Complete all acceptance criteria listed in the bead
+
+   After implementation, run validation:
+   - Execute each validation command from step 4
+   - Track results in this format:
+     ```
+     VALIDATION_RESULTS:
+     - make test: PASS
+     - make lint: FAIL (exit code 1: src/foo.ts:23 - missing semicolon)
+     - nix flake check: SKIP (not applicable - no flake.nix)
+     - cargo test: ERROR (command not found)
+     ```
+
+   **Status definitions:**
+   - **PASS**: Check executed successfully with no issues
+   - **FAIL**: Check executed but found issues that need attention
+   - **SKIP**: Check not applicable to this project (e.g., no Makefile for `make test`)
+   - **ERROR**: Check could not execute (missing tool, permission error, command not found)
+
+   - If any validation fails:
+     - Continue with PR creation (don't block)
+     - Document failures in bead notes: `bd update [BEAD_ID] --notes="Validation failures: [list]"`
+
+6. **Commit and push**:
+   - Stage all changes: `git add -A`
+   - Create a descriptive commit message
+   - Push the branch: `git push -u origin bead/[BEAD_ID]`
+
+7. **Create a PR**:
+   - Detect hosting provider from origin URL: `git remote get-url origin`
+   - If URL contains `github.com`, use `gh`; otherwise use `tea` (Gitea/Forgejo)
+   - PR title: "[BEAD_ID] [BEAD_TITLE]"
+   - PR body must include:
+     - Reference to bead ID: "Implements bead: [BEAD_ID]"
+     - Any external issue references from the bead (e.g., "Closes #123")
+     - Summary of changes
+   - For GitHub (`gh`):
+     ```bash
+     gh pr create --title "[BEAD_ID] [BEAD_TITLE]" --body "$(cat <<'EOF'
+     ## Summary
+     [Brief description of changes]
+
+     ## Bead Reference
+     Implements bead: [BEAD_ID]
+
+     ## External Issues
+     [Any linked issues from the bead]
+
+     ## Changes
+     - [List of changes made]
+
+     ## Validation Steps Completed
+
+     ### Automated Checks
+     | Check | Status | Details |
+     |-------|--------|---------|
+     | make test | PASS | |
+     | make lint | FAIL | src/foo.ts:23 - missing semicolon |
+     | nix flake check | SKIP | not applicable - no flake.nix |
+     | cargo test | ERROR | command not found |
+
+     ### Manual Verification Required
+     [If plan has Manual Verification items, list them as unchecked boxes:]
+     - [ ] Verify UI changes match design mockups
+     - [ ] Test on mobile viewport sizes
+     [If no manual verification items: "None specified in plan."]
+
+     ### CONTRIBUTING.md Compliance
+     [If CONTRIBUTING.md requirements were extracted:]
+     - [x] Tests pass (verified via `make test`)
+     - [ ] Documentation updated (needs manual review)
+     [If no CONTRIBUTING.md: "No contribution guidelines found."]
+     EOF
+     )"
+     ```
+   - For Gitea (`tea`):
+     ```bash
+     tea pr create --head bead/[BEAD_ID] --base main \
+       --title "[BEAD_ID] [BEAD_TITLE]" \
+       --description "## Summary
+     [Brief description of changes]
+
+     ## Bead Reference
+     Implements bead: [BEAD_ID]
+
+     ## External Issues
+     [Any linked issues from the bead]
+
+     ## Changes
+     - [List of changes made]
+
+     ## Validation Steps Completed
+
+     ### Automated Checks
+     | Check | Status | Details |
+     |-------|--------|---------|
+     | make test | PASS | |
+     | make lint | FAIL | src/foo.ts:23 - missing semicolon |
+     | nix flake check | SKIP | not applicable - no flake.nix |
+     | cargo test | ERROR | command not found |
+
+     ### Manual Verification Required
+     [If plan has Manual Verification items, list them as unchecked boxes:]
+     - [ ] Verify UI changes match design mockups
+     - [ ] Test on mobile viewport sizes
+     [If no manual verification items: None specified in plan.]
+
+     ### CONTRIBUTING.md Compliance
+     [If CONTRIBUTING.md requirements were extracted:]
+     - [x] Tests pass (verified via make test)
+     - [ ] Documentation updated (needs manual review)
+     [If no CONTRIBUTING.md: No contribution guidelines found.]"
+     ```
+
+8. **Update bead status**:
+   - Mark the bead as "in_review": `bd update [BEAD_ID] --status=in_review`
+   - Add the PR URL to the bead notes: `bd update [BEAD_ID] --notes="$(bd show [BEAD_ID] --json | jq -r '.notes')
+
+PR: [PR_URL]"`
+
+9. **Report results**:
+   - Return:
+     - PR URL
+     - Bead ID
+     - Implementation status (success/failure/blocked)
+     - Validation summary: `X passed, Y failed, Z skipped, W errors`
+     - List of any validation failures or errors with details
+   - If blocked or unable to complete, explain what's blocking progress
+   - If validation failed, include the specific failures so the main agent can summarize them for the user
+```
+
+### Launching Subagents
+
+For each bead, substitute into the template:
+- `[BEAD_ID]` - the bead ID
+- `[BEAD_TITLE]` - the bead title
+- `[WORKTREE_PATH]` - the worktree path created in Phase 2
+
+Use `subagent_type: "general-purpose"` for implementation subagents. Launch all selected beads' subagents in a single message for parallel execution:
+
+```
+<Task calls for each selected bead - all in one message>
+```
+
+**Important**: The worktree paths were created in Phase 2. Use the exact paths that were created, e.g.:
+- `~/wt/nixos-configs/nixos-configs-abc`
+- `~/wt/nixos-configs/nixos-configs-xyz`
+
+Collect results from all subagents before proceeding.
+
+## Phase 4: Parallel Review
+
+After all implementation subagents complete, launch review subagents for each PR.
+
+### Review Subagent Instructions Template
+
+```
+Review PR for bead [BEAD_ID]
+
+1. **Detect hosting provider**: Run `git remote get-url origin` - if it contains `github.com` use `gh`, otherwise use `tea`
+
+2. **Read the PR**:
+   - For GitHub: `gh pr view [PR_NUMBER] --json title,body,additions,deletions,files`
+   - For Gitea: `tea pr view [PR_NUMBER]`
+   - View the diff: `git diff main...bead/[BEAD_ID]`
+
+3. **Review against acceptance criteria**:
+   - Run `bd show [BEAD_ID]` to get the acceptance criteria
+   - Verify each criterion is addressed
+
+4. **Leave review comments**:
+   - For GitHub: `gh pr review [PR_NUMBER] --comment --body "[COMMENTS]"`
+   - For Gitea: `tea pr review [PR_NUMBER] --comment "[COMMENTS]"`
+   - Include:
+     - Acceptance criteria checklist (which are met, which might be missing)
+     - Code quality observations
+     - Suggestions for improvement
+
+5. **Return summary**:
+   - Overall assessment (ready to merge / needs changes)
+   - Key findings
+```
+
+Launch all review subagents in parallel.
+
+## Phase 5: Cleanup and Summary
+
+After reviews complete:
+
+1. **Clean up worktrees**:
+   ```bash
+   git worktree remove ~/wt/[REPO_NAME]/[BEAD_ID] --force
+   ```
+   Do this for each bead's worktree.
+
+2. **Provide final summary**:
+   Present a table or list with:
+   - Bead ID
+   - PR URL
+   - Status (success / failed / blocked)
+   - Validation summary (X/Y passed)
+   - Review summary
+   - Any failures or blockers encountered
+
+   If any validation failures occurred, list them in a "Validation Failures" section so the user can address them.
+
+Example output:
+```
+## Parallel Beads Summary
+
+| Bead | PR | Bead Status | Validation | Review |
+|------|-----|-------------|------------|--------|
+| beads-abc | #123 | in_review | 3/3 passed | Approved |
+| beads-xyz | #124 | in_review | 2/3 passed | Needs changes |
+| beads-123 | - | open (failed) | - | Blocked by missing dependency |
+
+### Validation Failures
+- beads-xyz: `make lint` failed - src/foo.ts:23 missing semicolon
+
+### Failures/Blockers
+- beads-123: Could not complete because [reason]
+
+### Next Steps
+- Fix validation failures before merging
+- Review PRs that need changes
+- Address blockers for failed beads
+- Run `/reconcile_beads` after PRs are merged to close beads
+```
+
+## Error Handling
+
+- **Worktree creation failures** (Phase 2):
+  - If `git worktree add` fails (branch exists, path exists), prompt user:
+    - Remove existing and retry
+    - Skip this bead
+    - Use existing (with warning about potential divergence)
+  - Do NOT proceed to subagent launch until worktree is confirmed
+
+- **Branch verification failures** (subagent reports):
+  - If subagent reports it's on `main` or `master`, do NOT retry
+  - Mark bead as failed with reason "Branch verification failed"
+  - Continue with other beads but flag this as a critical issue
+  - Investigation required: the worktree may have been corrupted or not created properly
+
+- **Subagent failures**: If a subagent fails or times out, note it in the summary but continue with other beads
+- **PR creation failures**: Report the error but continue with reviews of successful PRs
+
+## Resource Limits
+
+- Consider limiting concurrent subagents to 3-5 to avoid overwhelming system resources
+- If user selects more beads than the limit, process them in batches
+
+## Notes
+
+- This workflow integrates with the beads system (`bd` commands)
+- Worktrees are created in `~/wt/[REPO_NAME]/` by convention
+- Each bead gets its own isolated branch and worktree
+- PRs automatically reference the bead ID for traceability

home/roles/development/commands/reconcile_beads.md

@@ -0,0 +1,129 @@
+---
+description: Reconcile beads with merged PRs and close completed beads
+---
+
+# Reconcile Beads Workflow
+
+This skill reconciles beads that are in `in_review` status with their corresponding PRs. If a PR has been merged, the bead is closed and any linked Gitea issue is also closed.
+
+## Prerequisites
+
+- Custom status `in_review` must be configured: `bd config set status.custom "in_review"`
+- Beads in `in_review` status should have a PR URL in their notes
+- `tea` CLI must be configured for closing Gitea issues
+
+## Workflow
+
+### Step 1: Find beads in review
+
+```bash
+bd list --status=in_review
+```
+
+### Step 2: For each bead, check PR status
+
+1. **Get the PR URL from bead notes**:
+   ```bash
+   bd show [BEAD_ID] --json | jq -r '.[0].notes'
+   ```
+   Note: `bd show --json` returns an array, so use `.[0]` to access the first element.
+   Extract the PR URL (look for lines starting with "PR:" or containing pull request URLs).
+   Extract the PR number: `echo "$NOTES" | grep -oP '/pulls/\K\d+'`
+
+2. **Detect hosting provider**:
+   - Run `git remote get-url origin`
+   - If URL contains `github.com`, use `gh`; otherwise use `tea` (Gitea/Forgejo)
+
+3. **Check PR status**:
+   - For GitHub:
+     ```bash
+     gh pr view [PR_NUMBER] --json state,merged
+     ```
+   - For Gitea:
+     ```bash
+     tea pr list --state=closed
+     ```
+     Look for the PR number in the INDEX column with STATE "merged".
+     Note: `tea pr view [PR_NUMBER]` lists all PRs, not a specific one. Use `tea pr list --state=closed` and look for your PR number in the results.
+
+### Step 3: Close merged beads
+
+If the PR is merged:
+```bash
+bd close [BEAD_ID] --reason="PR merged: [PR_URL]"
+```
+
+### Step 3.1: Close corresponding Gitea issue (if any)
+
+After closing a bead, check if it has a linked Gitea issue:
+
+1. **Check for Gitea issue URL in bead notes**:
+   Look for the pattern `Gitea issue: <URL>` in the notes. Extract the URL.
+
+2. **Extract issue number from URL**:
+   ```bash
+   # Example: https://git.johnogle.info/johno/nixos-configs/issues/16 -> 16
+   echo "$GITEA_URL" | grep -oP '/issues/\K\d+'
+   ```
+
+3. **Close the Gitea issue**:
+   ```bash
+   tea issues close [ISSUE_NUMBER]
+   ```
+
+4. **Handle errors gracefully**:
+   - If issue is already closed: Log warning, continue
+   - If issue not found: Log warning, continue
+   - If `tea` fails: Log error, continue with other beads
+
+   Example warning output:
+   ```
+   Warning: Could not close Gitea issue #16: issue already closed
+   ```
+
+### Step 4: Report summary
+
+Present results:
+
+```
+## Beads Reconciliation Summary
+
+### Closed (PR Merged)
+| Bead | PR | Gitea Issue | Title |
+|------|-----|-------------|-------|
+| beads-abc | #123 | #16 closed | Feature X |
+| beads-xyz | #456 | (none) | Bug fix Y |
+
+### Gitea Issues Closed
+| Issue | Bead | Status |
+|-------|------|--------|
+| #16 | beads-abc | Closed successfully |
+| #17 | beads-def | Already closed (skipped) |
+| #99 | beads-ghi | Error: issue not found |
+
+### Still in Review
+| Bead | PR | Status | Title |
+|------|-----|--------|-------|
+| beads-def | #789 | Open | Feature Z |
+
+### Issues Found
+- beads-ghi: No PR URL found in notes
+- beads-jkl: PR #999 not found (may have been deleted)
+```
+
+## Error Handling
+
+- **Missing PR URL**: Skip the bead and report it
+- **PR not found**: Report the error but continue with other beads
+- **API errors**: Report and continue
+- **Gitea issue already closed**: Log warning, continue (not an error)
+- **Gitea issue not found**: Log warning, continue (issue may have been deleted)
+- **No Gitea issue linked**: Normal case, no action needed
+- **tea command fails**: Log error with output, continue with other beads
+
+## Notes
+
+- This skill complements `/parallel_beads` which sets beads to `in_review` status
+- Run this skill periodically or after merging PRs to keep beads in sync
+- Beads with closed (but not merged) PRs are not automatically closed - they may need rework
+- Gitea issues are only closed for beads that have a `Gitea issue: <URL>` in their notes

home/roles/development/default.nix

@@ -5,6 +5,27 @@ with lib;
 let
   cfg = config.home.roles.development;
 
+  # Build beads and gastown from flake inputs using shared package definitions
+  beadsRev = builtins.substring 0 8 (globalInputs.beads.rev or "unknown");
+  beadsPackage = pkgs.callPackage ../../../packages/beads {
+    src = globalInputs.beads;
+    version = "0.52.0-${beadsRev}";
+  };
+
+  gastownRev = builtins.substring 0 8 (globalInputs.gastown.rev or "unknown");
+  gastownPackage = pkgs.callPackage ../../../packages/gastown {
+    src = globalInputs.gastown;
+    version = "unstable-${gastownRev}";
+  };
+
+  # Build perles from flake input using shared package definition
+  perlesRev = builtins.substring 0 8 (globalInputs.perles.rev or "unknown");
+  perlesPackage = pkgs.callPackage ../../../packages/perles {
+    inherit (pkgs.unstable) buildGoModule;
+    src = globalInputs.perles;
+    version = "unstable-${perlesRev}";
+  };
+
   # Fetch the claude-plugins repository (for humanlayer commands/agents)
   # Update the rev to get newer versions of the commands
   claudePluginsRepo = builtins.fetchGit {
@@ -43,8 +64,13 @@ in
 
   config = mkIf cfg.enable {
     home.packages = [
+      beadsPackage
+      gastownPackage
+      perlesPackage
       pkgs.unstable.claude-code
+      pkgs.unstable.claude-code-router
       pkgs.unstable.codex
+      pkgs.unstable.dolt
       pkgs.sqlite
 
       # Custom packages
@@ -103,11 +129,72 @@ in
         fi
       done
 
-      $DRY_RUN_CMD echo "Claude Code plugins installed: humanlayer commands/agents"
+      # Copy local commands from this repo (with retry for race conditions with running Claude)
+      for file in ${./commands}/*.md; do
+        if [ -f "$file" ]; then
+          filename=$(basename "$file" .md)
+          dest="$HOME/.claude/commands/''${filename}.md"
+          # Remove existing file first, then copy with retry on failure
+          rm -f "$dest" 2>/dev/null || true
+          if ! cp "$file" "$dest" 2>/dev/null; then
+            sleep 0.5
+            cp "$file" "$dest" || echo "Warning: Failed to copy $filename.md to commands"
+          fi
+          chmod u+w "$dest" 2>/dev/null || true
+        fi
+      done
+
+      # Copy local skills (reference materials) to skills subdirectory
+      mkdir -p ~/.claude/commands/skills
+      for file in ${./skills}/*.md; do
+        if [ -f "$file" ]; then
+          filename=$(basename "$file" .md)
+          dest="$HOME/.claude/commands/skills/''${filename}.md"
+          rm -f "$dest" 2>/dev/null || true
+          if ! cp "$file" "$dest" 2>/dev/null; then
+            sleep 0.5
+            cp "$file" "$dest" || echo "Warning: Failed to copy $filename.md to skills"
+          fi
+          chmod u+w "$dest" 2>/dev/null || true
+        fi
+      done
+
+      # Copy micro-skills (compact reusable knowledge referenced by formulas)
+      for file in ${./skills/micro}/*.md; do
+        if [ -f "$file" ]; then
+          dest="$HOME/.claude/commands/skills/$(basename "$file")"
+          rm -f "$dest" 2>/dev/null || true
+          cp "$file" "$dest"
+          chmod u+w "$dest" 2>/dev/null || true
+        fi
+      done
+
+      # Install beads formulas to user-level formula directory
+      mkdir -p ~/.beads/formulas
+      for file in ${./formulas}/*.formula.toml; do
+        if [ -f "$file" ]; then
+          dest="$HOME/.beads/formulas/$(basename "$file")"
+          rm -f "$dest" 2>/dev/null || true
+          cp "$file" "$dest"
+          chmod u+w "$dest" 2>/dev/null || true
+        fi
+      done
+
+      $DRY_RUN_CMD echo "Claude Code plugins installed: humanlayer commands/agents + local commands + local skills + formulas"
+    '';
+
+    # Set up beads Claude Code integration (hooks for SessionStart/PreCompact)
+    # This uses the CLI + hooks approach which is recommended over MCP for Claude Code
+    home.activation.claudeCodeBeadsSetup = lib.hm.dag.entryAfter ["writeBoundary" "claudeCodeCommands"] ''
+      # Run bd setup claude to install hooks into ~/.claude/settings.json
+      # This is idempotent - safe to run multiple times
+      ${beadsPackage}/bin/bd setup claude 2>/dev/null || true
+
+      $DRY_RUN_CMD echo "Claude Code beads integration configured (hooks installed)"
     '';
 
     # Configure Claude Code statusline (merge into existing settings.json)
-    home.activation.claudeCodeStatusLine = lib.hm.dag.entryAfter ["writeBoundary"] ''
+    home.activation.claudeCodeStatusLine = lib.hm.dag.entryAfter ["writeBoundary" "claudeCodeBeadsSetup"] ''
       SETTINGS="$HOME/.claude/settings.json"
       mkdir -p "$HOME/.claude"
       if [ -f "$SETTINGS" ]; then
@@ -118,6 +205,46 @@ in
       $DRY_RUN_CMD echo "Claude Code statusline configured"
     '';
 
+    # Beads timer gate checker (Linux only - uses systemd)
+    # Runs every 5 minutes to auto-resolve expired timer gates across all beads projects
+    # This enables self-scheduling molecules (watchers, patrols, etc.)
+    systemd.user.services.beads-gate-check = lib.mkIf pkgs.stdenv.isLinux {
+      Unit = {
+        Description = "Check and resolve expired beads timer gates";
+      };
+      Service = {
+        Type = "oneshot";
+        # Check gates in all workspaces that have running daemons
+        ExecStart = pkgs.writeShellScript "beads-gate-check-all" ''
+          # Get list of workspaces from daemon registry
+          workspaces=$(${beadsPackage}/bin/bd daemon list --json 2>/dev/null | ${pkgs.jq}/bin/jq -r '.[].workspace // empty' 2>/dev/null)
+
+          if [ -z "$workspaces" ]; then
+            exit 0  # No beads workspaces, nothing to do
+          fi
+
+          for ws in $workspaces; do
+            if [ -d "$ws" ]; then
+              cd "$ws" && ${beadsPackage}/bin/bd gate check --type=timer --quiet 2>/dev/null || true
+            fi
+          done
+        '';
+      };
+    };
+
+    systemd.user.timers.beads-gate-check = lib.mkIf pkgs.stdenv.isLinux {
+      Unit = {
+        Description = "Periodic beads timer gate check";
+      };
+      Timer = {
+        OnBootSec = "5min";
+        OnUnitActiveSec = "5min";
+      };
+      Install = {
+        WantedBy = [ "timers.target" ];
+      };
+    };
+
     # Note: modules must be imported at top-level home config
   };
 }

home/roles/development/formulas/quick-fix.formula.toml

@@ -0,0 +1,115 @@
+# Quick Fix Formula
+#
+# Streamlined workflow for well-understood bugs and small fixes.
+# Skips the deep research and planning phases of RPI - get in, fix, get out.
+#
+# Use when:
+#   - Bug is well-understood (you know what's broken)
+#   - Fix is straightforward (no architectural decisions)
+#   - Change is small (< 100 lines)
+#
+# Use RPI instead when:
+#   - Root cause is unclear
+#   - Multiple approaches possible
+#   - Significant design decisions needed
+
+formula = "quick-fix"
+description = """
+Streamlined workflow for bugs and small fixes.
+
+A faster alternative to RPI for well-understood issues:
+1. Quick investigation to confirm understanding
+2. Implement the fix
+3. Verify with tests
+4. Commit and close
+
+No human gates - designed for quick turnaround on obvious fixes.
+"""
+version = 1
+type = "workflow"
+
+# === Variables ===
+
+[vars.title]
+required = true
+description = "Brief description of the bug/fix"
+
+[vars.bead_id]
+description = "Existing bead ID (creates new if not provided)"
+
+[vars.test_cmd]
+default = "make test"
+description = "Command to verify the fix"
+
+# === Steps ===
+
+[[steps]]
+id = "investigate"
+title = "Investigate: {{title}}"
+description = """
+Quick investigation to confirm understanding of the bug.
+
+Goals:
+- Locate the problematic code
+- Confirm root cause matches expectations
+- Identify files that need changes
+
+This is NOT deep research - spend 5-10 minutes max.
+If the bug is more complex than expected, pivot to RPI workflow.
+
+Output: Mental model of what to fix (no artifact needed).
+"""
+
+[[steps]]
+id = "fix"
+title = "Fix: {{title}}"
+needs = ["investigate"]
+description = """
+Implement the fix.
+
+Guidelines:
+- Make minimal changes to fix the issue
+- Follow existing code patterns
+- Add/update tests if appropriate
+- Keep changes focused (no drive-by refactors)
+
+If the fix grows beyond expectations, pause and consider:
+- Should this be an RPI workflow instead?
+- Should we split into multiple changes?
+"""
+
+[[steps]]
+id = "verify"
+title = "Verify fix"
+needs = ["fix"]
+description = """
+Verify the fix works correctly.
+
+Run: {{test_cmd}}
+
+Also check:
+- Bug is actually fixed (manual verification)
+- No obvious regressions introduced
+- Code compiles/builds cleanly
+
+If tests fail, iterate on the fix step.
+"""
+
+[[steps]]
+id = "commit"
+title = "Commit and close"
+needs = ["verify"]
+description = """
+Commit the fix and close the bead.
+
+Actions:
+1. Stage changes: git add -A
+2. Commit with descriptive message: git commit -m "fix: {{title}}"
+3. Push to remote: git push
+4. Close the bead: bd close {{bead_id}}
+
+Commit message should explain:
+- What was broken
+- How it was fixed
+- Any relevant context
+"""

home/roles/development/formulas/rpi.formula.toml

@@ -0,0 +1,124 @@
+# RPI Formula - Research -> Plan -> Implement
+#
+# Universal workflow for feature development with human gates.
+
+formula = "rpi"
+description = """
+Research -> Plan -> Implement workflow.
+
+Usage:
+  bd pour rpi --var title="Add user preferences"
+  bd pour rpi --var title="Auth" --var bead_id="project-abc" --var test_cmd="nix flake check"
+"""
+version = 1
+type = "workflow"
+
+# ─── Variables ───
+
+[vars.title]
+required = true
+description = "What are we building?"
+
+[vars.bead_id]
+description = "Existing bead ID (creates new if not provided)"
+
+[vars.test_cmd]
+default = "make test"
+description = "Command to run tests"
+
+[vars.lint_cmd]
+default = "make lint"
+description = "Command to run linting"
+
+# ─── Research Phase ───
+
+[[steps]]
+id = "research"
+title = "Research: {{title}}"
+skill = "research-agents"
+description = """
+Conduct comprehensive codebase research.
+
+Goals:
+- Understand current implementation
+- Identify patterns to follow
+- Find relevant files and dependencies
+- Document key discoveries
+
+Output: thoughts/beads-{{bead_id}}/research.md
+"""
+
+# ─── Planning Phase ───
+
+[[steps]]
+id = "plan"
+title = "Plan: {{title}}"
+needs = ["research"]
+type = "human"
+skill = "planning"
+description = """
+Create detailed implementation plan based on research.
+
+Goals:
+- Present understanding and clarify requirements
+- Propose design options with tradeoffs
+- Define phases with success criteria
+- Identify what we're NOT doing
+
+Output: thoughts/beads-{{bead_id}}/plan.md
+"""
+
+[steps.gate]
+type = "human"
+reason = "Plan approval before implementation"
+
+# ─── Implementation Phase ───
+
+[[steps]]
+id = "implement"
+title = "Implement: {{title}}"
+needs = ["plan"]
+description = """
+Execute the approved plan phase by phase.
+
+For each phase:
+1. Make the changes
+2. Run verification: {{test_cmd}}, {{lint_cmd}}
+3. Update plan checkboxes for resumability
+
+Stop and ask if encountering unexpected issues.
+"""
+
+# ─── Verification Phase ───
+
+[[steps]]
+id = "verify"
+title = "Manual verification"
+needs = ["implement"]
+type = "human"
+description = """
+Human confirms implementation works correctly.
+
+Check: feature works, edge cases handled, no regressions.
+Tests: {{test_cmd}} | Lint: {{lint_cmd}}
+"""
+
+[steps.gate]
+type = "human"
+reason = "Confirm implementation is correct"
+
+# ─── Completion ───
+
+[[steps]]
+id = "complete"
+title = "Close bead"
+needs = ["verify"]
+skill = "artifact-format"
+description = """
+Mark work as complete.
+
+Actions:
+- bd update {{bead_id}} --notes="Implementation complete"
+- bd close {{bead_id}} --reason="Completed: {{title}}"
+- bd sync && git push
+"""

home/roles/development/skills/bd_workflow.md

@@ -0,0 +1,230 @@
+---
+description: How to use the bd (beads) CLI for issue tracking, dependencies, and workflow orchestration
+---
+
+# BD Workflow
+
+The `bd` CLI is a git-backed issue tracker with first-class dependency support. Use it for multi-session work, blocking relationships, and persistent memory across conversation compaction.
+
+## When to Use BD vs TodoWrite
+
+| Use BD | Use TodoWrite |
+|--------|---------------|
+| Work spans multiple sessions | Single-session tasks |
+| Dependencies between tasks | Independent subtasks |
+| Need audit trail in git | Ephemeral tracking |
+| Cross-repo coordination | Local project only |
+| Resuming after compaction | Simple task lists |
+
+## Core Commands
+
+### Creating Issues
+
+```bash
+bd create "Issue title"                          # Basic task
+bd create "Bug title" --type=bug --priority=1    # P1 bug
+bd create "Feature" --type=feature -d "Details"  # With description
+bd q "Quick capture"                             # Output only ID
+```
+
+### Managing Issues
+
+```bash
+bd show <id>                    # View issue details
+bd show <id> --children         # View children of epic
+bd list                         # List open issues (default 50)
+bd list --all                   # Include closed
+bd list -s in_progress          # Filter by status
+bd list -t bug -p 0             # P0 bugs
+bd list --pretty                # Tree format
+```
+
+### Updating Issues
+
+```bash
+bd update <id> --status=in_progress    # Start work
+bd update <id> --status=blocked        # Mark blocked
+bd update <id> --claim                 # Claim atomically
+bd update <id> --add-label=urgent      # Add label
+bd update <id> -d "New description"    # Update description
+```
+
+### Closing Issues
+
+```bash
+bd close <id>                          # Close issue
+bd close <id> --continue               # Auto-advance to next step
+bd close <id> --suggest-next           # Show newly unblocked
+```
+
+## Finding Work
+
+```bash
+bd ready                     # Ready issues (no blockers)
+bd ready --mol <mol-id>      # Ready steps in molecule
+bd ready -n 5                # Limit to 5
+bd ready --assignee me       # Assigned to me
+bd blocked                   # Show blocked issues
+bd blocked --parent <id>     # Blocked within epic
+```
+
+## Dependency Management
+
+### Creating Dependencies
+
+```bash
+bd dep <blocker> --blocks <blocked>    # A blocks B
+bd dep add <blocked> <blocker>         # Same as above
+bd dep relate <id1> <id2>              # Bidirectional link
+```
+
+### Viewing Dependencies
+
+```bash
+bd dep list <id>             # Show dependencies
+bd dep tree <id>             # Dependency tree
+bd dep cycles                # Detect cycles
+```
+
+### Removing Dependencies
+
+```bash
+bd dep remove <blocked> <blocker>      # Remove dependency
+bd dep unrelate <id1> <id2>            # Remove relation
+```
+
+## Sync Workflow
+
+BD syncs issues via git. The daemon handles this automatically, but manual sync is available:
+
+```bash
+bd sync                      # Full sync (pull, merge, push)
+bd sync --flush-only         # Export to JSONL only
+bd sync --import-only        # Import from JSONL only
+bd sync --status             # Show sync branch diff
+bd sync --squash             # Accumulate without commit
+```
+
+## Formula and Molecule Workflow
+
+Formulas are reusable workflow templates. Molecules are instantiated workflows.
+
+### Formulas
+
+```bash
+bd formula list                        # List available formulas
+bd formula list --type=workflow        # Filter by type
+bd formula show <name>                 # Show formula details
+bd cook <formula>                      # Compile to proto (stdout)
+bd cook <formula> --var name=auth      # With variable substitution
+bd cook <formula> --dry-run            # Preview steps
+bd cook <formula> --persist            # Save to database
+```
+
+### Molecules: Pour vs Wisp
+
+| pour (persistent) | wisp (ephemeral) |
+|-------------------|------------------|
+| Feature implementations | Release workflows |
+| Multi-session work | Patrol cycles |
+| Audit trail needed | Health checks |
+| Git-synced | Local only |
+
+```bash
+# Persistent molecule (liquid phase)
+bd mol pour <proto> --var name=auth
+
+# Ephemeral molecule (vapor phase)
+bd mol wisp <proto> --var version=1.0
+bd mol wisp list                       # List wisps
+bd mol wisp gc                         # Garbage collect
+```
+
+### Tracking Molecule Progress
+
+```bash
+bd mol show <mol-id>                   # Show structure
+bd mol show <mol-id> --parallel        # Parallelizable steps
+bd mol current                         # Where am I?
+bd mol current <mol-id>                # Status for molecule
+bd mol progress <mol-id>               # Progress summary + ETA
+```
+
+### Molecule Lifecycle
+
+```bash
+bd mol squash <mol-id>                 # Condense to digest
+bd mol burn <mol-id>                   # Delete wisp
+bd mol distill <epic-id>               # Extract formula from epic
+```
+
+## Gates and Human Checkpoints
+
+Gates are async wait conditions that block workflow steps:
+
+| Gate Type | Wait Condition |
+|-----------|---------------|
+| human | Manual `bd close` |
+| timer | Timeout expires |
+| gh:run | GitHub workflow completes |
+| gh:pr | PR merges |
+| bead | Cross-rig bead closes |
+
+```bash
+bd gate list                           # Show open gates
+bd gate list --all                     # Include closed
+bd gate check                          # Evaluate all gates
+bd gate check --type=bead              # Check bead gates only
+bd gate resolve <id>                   # Close manually
+```
+
+## Common Patterns
+
+### Starting Work on a Bead
+
+```bash
+bd update <id> --status=in_progress
+# ... do work ...
+bd close <id>
+```
+
+### Creating Related Issues
+
+```bash
+bd create "Main task" --deps "blocks:<other-id>"
+bd dep add <new-id> <blocker-id>
+```
+
+### Working Through a Molecule
+
+```bash
+bd mol pour my-workflow --var name=feature
+bd ready --mol <mol-id>                # Find next step
+bd update <step-id> --claim            # Claim step
+# ... do work ...
+bd close <step-id> --continue          # Close and advance
+```
+
+### Quick Status Check
+
+```bash
+bd ready -n 3                          # Top 3 ready items
+bd list -s in_progress                 # What's in flight?
+bd blocked                             # What's stuck?
+```
+
+## Useful Flags
+
+| Flag | Effect |
+|------|--------|
+| `--json` | JSON output for scripting |
+| `--quiet` | Suppress non-essential output |
+| `--dry-run` | Preview without executing |
+| `--pretty` | Tree format display |
+
+## Integration Notes
+
+- BD auto-syncs via daemon (check with `bd info`)
+- Issues stored in `.beads/` directory
+- JSONL files sync through git
+- Use `bd doctor` if something seems wrong

home/roles/development/skills/micro/artifact-format.md

@@ -0,0 +1,123 @@
+---
+description: How to structure research and plan artifacts in thoughts/
+---
+
+# Artifact Format
+
+Standardized format for thoughts/ artifacts. All beads-related artifacts should follow these conventions for consistency and machine parseability.
+
+## Frontmatter (Required)
+
+Every artifact MUST include YAML frontmatter:
+
+```yaml
+---
+date: 2026-01-15T10:00:00-08:00  # ISO 8601 with timezone
+bead_id: project-abc              # Bead identifier
+bead_title: "Title of the bead"   # Human-readable title
+author: claude                    # Who created this
+git_commit: abc123def             # Commit hash at creation
+branch: main                      # Branch name
+repository: repo-name             # Repository name
+status: draft|complete            # Artifact status
+---
+```
+
+### Gathering Metadata
+
+```bash
+git rev-parse HEAD                           # Current commit
+git branch --show-current                    # Current branch
+basename $(git rev-parse --show-toplevel)    # Repo name
+date -Iseconds                               # ISO timestamp
+```
+
+## Research Artifact Structure
+
+Location: `thoughts/beads-{bead-id}/research.md`
+
+```markdown
+# Research: {bead title}
+
+**Bead**: {bead-id}
+**Date**: {timestamp}
+**Git Commit**: {commit hash}
+
+## Research Question
+{Original question from bead description}
+
+## Summary
+{2-3 sentence overview answering the research question}
+
+## Key Discoveries
+- {Finding with file:line reference}
+- {Pattern or convention found}
+- {Architectural decision documented}
+
+## Architecture
+{Current patterns and conventions in the codebase}
+
+## Code References
+- `path/to/file.py:123` - Description of relevance
+- `another/file.ts:45-67` - Description of relevance
+
+## Open Questions
+{Areas needing further investigation or human clarification}
+```
+
+## Plan Artifact Structure
+
+Location: `thoughts/beads-{bead-id}/plan.md`
+
+```markdown
+# {Title} Implementation Plan
+
+## Overview
+{What we're implementing and why - 1-2 sentences}
+
+## Current State
+{What exists now, key constraints discovered}
+
+### Key Discoveries
+- {Finding with file:line reference}
+- {Pattern to follow}
+
+## Desired End State
+{Specification of what success looks like}
+
+## What We're NOT Doing
+{Explicitly list out-of-scope items}
+
+## Phase 1: {Descriptive Name}
+
+### Overview
+{What this phase accomplishes}
+
+### Changes
+- [ ] {Specific change with file path}
+- [ ] {Another change}
+
+### Success Criteria
+
+#### Automated
+- [ ] Tests pass: `{test command}`
+- [ ] Lint passes: `{lint command}`
+
+#### Manual
+- [ ] {Human verification step}
+
+## Phase 2: {Descriptive Name}
+{Repeat structure...}
+
+## References
+- Bead: {bead-id}
+- Research: `thoughts/beads-{bead-id}/research.md`
+```
+
+## Key Principles
+
+1. **Always include file:line references** - Makes artifacts actionable
+2. **Separate automated vs manual verification** - Enables agent autonomy
+3. **Use checkboxes for phases** - Enables resumability after interruption
+4. **Keep frontmatter machine-parseable** - Enables tooling integration
+5. **Link related artifacts** - Research links to plan, plan links to bead

home/roles/development/skills/micro/planning.md

@@ -0,0 +1,121 @@
+---
+description: How to create effective implementation plans with phased delivery and clear success criteria
+---
+
+# Planning
+
+Create implementation plans that enable incremental, verifiable progress.
+
+## Core Principles
+
+1. **Incremental delivery**: Each phase should produce working, testable changes
+2. **Clear checkpoints**: Success criteria that can be verified without ambiguity
+3. **Buy-in before detail**: Confirm understanding and approach before writing specifics
+4. **Explicit scope**: State what we're NOT doing to prevent scope creep
+
+## Plan Document Structure
+
+```markdown
+# {Feature} Implementation Plan
+
+## Overview
+{1-2 sentences: what we're building and why}
+
+## Current State Analysis
+{What exists now, key constraints, file:line references}
+
+## Desired End State
+{Specification of outcome and how to verify it}
+
+## What We're NOT Doing
+{Explicit out-of-scope items}
+
+## Phase 1: {Descriptive Name}
+### Overview
+{What this phase accomplishes - should be independently valuable}
+
+### Changes Required
+{Specific files and modifications with code snippets}
+
+### Success Criteria
+#### Automated Verification
+- [ ] Tests pass: `{test command}`
+- [ ] Lint passes: `{lint command}`
+
+#### Manual Verification
+- [ ] {Human-observable outcome}
+
+## Testing Strategy
+{Unit tests, integration tests, manual testing steps}
+
+## References
+{Links to research, related files, similar implementations}
+```
+
+## Phase Design
+
+Good phases are:
+- **Self-contained**: Completable in one session
+- **Testable**: Has clear pass/fail criteria
+- **Reversible**: Can be rolled back if needed
+- **Incremental**: Builds on previous phases without requiring all phases
+
+Bad phases are:
+- "Refactor everything" (too broad)
+- "Add helper function" (too granular)
+- Phases that only work if ALL phases complete
+
+## Success Criteria Guidelines
+
+**Automated Verification** (agent-runnable):
+- Test commands: `make test`, `npm test`, `nix flake check`
+- Lint/format: `make lint`, `cargo fmt --check`
+- Type checking: `make typecheck`, `tsc --noEmit`
+- Build verification: `make build`, `nix build`
+
+**Manual Verification** (requires human):
+- UI/UX functionality and appearance
+- Performance under realistic conditions
+- Edge cases hard to automate
+- Integration with external systems
+
+**From Contribution Guidelines** (if CONTRIBUTING.md exists):
+- Include any testing requirements specified
+- Reference the guideline: "Per CONTRIBUTING.md: {requirement}"
+
+## Presenting Understanding
+
+Before writing the plan, confirm alignment:
+
+```
+Based on the requirements and my research, I understand we need to [summary].
+
+I've found that:
+- [Current implementation detail with file:line]
+- [Relevant pattern or constraint]
+- [Potential complexity identified]
+
+Questions my research couldn't answer:
+- [Specific technical question requiring judgment]
+```
+
+Only ask questions you genuinely cannot answer through code investigation.
+
+## Design Options Pattern
+
+When multiple approaches exist:
+
+```
+**Design Options:**
+1. [Option A] - [1-sentence description]
+   - Pro: [benefit]
+   - Con: [drawback]
+
+2. [Option B] - [1-sentence description]
+   - Pro: [benefit]
+   - Con: [drawback]
+
+Which approach aligns best with [relevant consideration]?
+```
+
+Get buy-in on approach before detailing phases.

home/roles/development/skills/micro/pr-description.md

@@ -0,0 +1,68 @@
+---
+description: How to write comprehensive PR descriptions that help reviewers understand changes
+---
+
+# PR Description
+
+Write PR descriptions that help reviewers understand what changed and why.
+
+## Structure
+
+Use this standard structure for PR descriptions:
+
+```markdown
+## Summary
+<1-3 bullet points of what changed and why>
+
+## Context
+<Why this change was needed - the problem being solved>
+<Link to related issues/tickets>
+
+## Changes
+<Detailed breakdown by area/component>
+- Area 1: What changed and why
+- Area 2: What changed and why
+
+## Testing
+<How this was verified>
+- Automated: Tests added/updated, CI status
+- Manual: Steps to verify functionality
+
+## Screenshots (if UI changes)
+<Before/after screenshots if applicable>
+```
+
+## Guidelines
+
+### Lead with WHY, not WHAT
+- The diff shows WHAT changed - your description explains WHY
+- Start with the problem being solved
+- Explain the approach chosen and alternatives considered
+
+### Link to context
+- Reference related issues: `Fixes #123` or `Relates to #456`
+- Link to design docs or discussions
+- Mention dependent PRs if any
+
+### Call out review areas
+- Highlight areas needing careful review
+- Note any tricky or non-obvious code
+- Point out architectural decisions
+
+### Note breaking changes prominently
+- Use a dedicated "Breaking Changes" section if applicable
+- Explain migration path for consumers
+- List any deprecations
+
+### Be scannable
+- Use bullet points over paragraphs
+- Keep sections focused and concise
+- Put the most important info first
+
+## Anti-patterns to Avoid
+
+- Empty descriptions or just "fixes bug"
+- Repeating the commit messages verbatim
+- Including irrelevant implementation details
+- Missing context on why the change was made
+- Forgetting to mention breaking changes

home/roles/development/skills/micro/research-agents.md

@@ -0,0 +1,49 @@
+---
+description: How to spawn and coordinate research sub-agents
+---
+
+# Research Agents
+
+Use parallel sub-agents for efficient codebase research.
+
+## Available Agents
+
+| Agent | Purpose |
+|-------|---------|
+| codebase-locator | Find WHERE files and components live |
+| codebase-analyzer | Understand HOW specific code works |
+| codebase-pattern-finder | Find examples of existing patterns |
+| thoughts-locator | Discover relevant documents in thoughts/ |
+
+## Spawning Protocol
+
+1. **Decompose** - Break the research question into 3-5 specific questions
+2. **Spawn parallel** - Use one Task call with multiple agents
+3. **Be specific** - Include directories and file patterns in prompts
+4. **Wait for all** - Do not synthesize until ALL agents complete
+5. **Synthesize** - Combine findings into coherent summary with file:line references
+
+## Example
+
+```
+Task(codebase-locator, "Find all files related to authentication in src/")
+Task(codebase-analyzer, "Explain how JWT tokens are validated in src/auth/")
+Task(codebase-pattern-finder, "Find examples of middleware patterns in src/")
+Task(thoughts-locator, "Find documents about auth design decisions in thoughts/")
+```
+
+## Key Principles
+
+- **Parallel when different** - Run agents in parallel when searching for different things
+- **WHAT not HOW** - Each agent knows its job; tell it what you need, not how to search
+- **Document, don't evaluate** - Agents should describe what exists, not critique it
+- **Specific directories** - Always scope searches to relevant directories
+- **File references** - Include specific file:line references in synthesis
+
+## Agent Prompts
+
+When spawning agents, include:
+- The specific question or goal
+- Relevant directories to search
+- Reminder to document (not evaluate) what they find
+- Request for file:line references in findings

home/roles/emacs/default.nix

@@ -1,9 +1,4 @@
-{
+{ config, lib, pkgs, ... }:
-  config,
-  lib,
-  pkgs,
-  ...
-}:
 
 with lib;
 
@@ -25,10 +20,9 @@ let
 
   # Default emacs configuration with vterm support
   defaultEmacsPackage =
-    if pkgs.stdenv.isDarwin then
+    if pkgs.stdenv.isDarwin
-      pkgs.emacs-macport.pkgs.withPackages emacsPackages
+    then pkgs.emacs-macport.pkgs.withPackages emacsPackages
-    else
+    else pkgs.emacs.pkgs.withPackages emacsPackages;
-      pkgs.emacs.pkgs.withPackages emacsPackages;
 
   # Path to doom config directory (relative to this file)
   doomConfigDir = ./doom;
@@ -62,8 +56,8 @@ in
         pkgs.nerd-fonts.fira-code
         pkgs.nerd-fonts.droid-sans-mono
         pkgs.nil # nix lsp language server
-        pkgs.nixfmt
+        pkgs.nixfmt-rfc-style
-        (pkgs.ripgrep.override { withPCRE2 = true; })
+        (pkgs.ripgrep.override {withPCRE2 = true;})
         pkgs.pipenv
         pkgs.poetry
         pkgs.python3
@@ -94,7 +88,7 @@ in
       };
 
       # TODO: Use mkOutOfStoreSymlink instead?
-      home.activation.doomConfig = lib.hm.dag.entryAfter [ "writeBoundary" ] ''
+      home.activation.doomConfig = lib.hm.dag.entryAfter ["writeBoundary"] ''
         # Always remove and recreate the symlink to ensure it points to the source directory
         rm -rf "${config.xdg.configHome}/doom"
         ln -sf "${config.home.homeDirectory}/nixos-configs/home/roles/emacs/doom" "${config.xdg.configHome}/doom"

home/roles/emacs/doom/config.el

@@ -306,6 +306,20 @@ rbw is unavailable or the entry is not found."
         claude-code-ide-window-side 'right
         claude-code-ide-window-width 90))
 
+(use-package! beads
+  :commands (beads)
+  :init
+  (map! :leader
+        (:prefix ("o" . "open")
+         (:prefix ("B" . "beads")
+          :desc "List issues"      "B" (cmd! (require 'beads) (beads-list))
+          :desc "Project issues"   "p" (cmd! (require 'beads) (beads-project-list))
+          :desc "Activity feed"    "a" (cmd! (require 'beads) (beads-activity))
+          :desc "Stale issues"     "s" (cmd! (require 'beads) (beads-stale))
+          :desc "Orphaned issues"  "o" (cmd! (require 'beads) (beads-orphans))
+          :desc "Find duplicates"  "d" (cmd! (require 'beads) (beads-duplicates))
+          :desc "Lint issues"      "l" (cmd! (require 'beads) (beads-lint))))))
+
 (after! gptel
   (require 'gptel-tool-library)
   (setq gptel-tool-library-use-maybe-safe t

home/roles/emacs/doom/packages.el

@@ -68,6 +68,11 @@
            :files ("*.el"))
   :pin "baffc3b0d74a2b7cbda0d5cd6dd7726d6ccaca83")
 
+(package! beads
+  :recipe (:type git :repo "https://codeberg.org/ctietze/beads.el.git"
+           :files ("lisp/*.el"))
+  :pin "f40a6461d3c0fa0969311bbb6a1e30d1bba86c88")
+
 (package! pi-coding-agent
   :recipe (:host github :repo "dnouri/pi-coding-agent"
            :files ("*.el"))

machines/boxy/configuration.nix

@@ -22,11 +22,12 @@ with lib;
       sddm = true;
       wayland = true;
     };
-    plasma-bigscreen = {
+    kodi = {
       enable = true;
       autologin = true;
-      jellyfinScaleFactor = 1.0;
+      wayland = true;
       appLauncherServer.enable = true;
+      jellyfinScaleFactor = 1.0;
     };
     nfs-mounts.enable = true;
     users.enable = true;
@@ -71,3 +72,4 @@ with lib;
   system.stateVersion = "24.05"; # Did you read the comment?
 
 }
+

machines/gym-box/configuration.nix

@@ -1,74 +0,0 @@
-# Edit this configuration file to define what should be installed on
-# your system. Help is available in the configuration.nix(5) man page, on
-# https://search.nixos.org/options and in the NixOS manual (`nixos-help`).
-
-{ lib, pkgs, ... }:
-
-with lib;
-
-{
-  imports = [
-    # Include the results of the hardware scan.
-    ./hardware-configuration.nix
-  ];
-
-  roles = {
-    audio.enable = true;
-    bluetooth.enable = true;
-    desktop = {
-      enable = true;
-      gaming.enable = true;
-      kde = true;
-      sddm = true;
-      wayland = true;
-    };
-    plasma-bigscreen = {
-      enable = true;
-      autologin = true;
-      jellyfinScaleFactor = 1.0;
-      appLauncherServer.enable = true;
-    };
-    nfs-mounts.enable = true;
-    users.enable = true;
-  };
-
-  # Enable KDE Wallet PAM integration for auto-unlock
-  security.pam.services.sddm = {
-    kwallet = {
-      enable = true;
-      package = pkgs.kdePackages.kwallet-pam;
-    };
-  };
-
-  # Use the systemd-boot EFI boot loader.
-  boot.loader.systemd-boot.enable = true;
-  boot.loader.efi.canTouchEfiVariables = true;
-
-  networking.hostName = "gym-box";
-  networking.networkmanager.enable = true;
-
-  services.xserver.videoDrivers = [ "amdgpu" ];
-  hardware.graphics.enable = true;
-  hardware.graphics.enable32Bit = true;
-  # RADV (AMD's Vulkan driver) is now enabled by default, amdvlk was removed
-
-  # This option defines the first version of NixOS you have installed on this particular machine,
-  # and is used to maintain compatibility with application data (e.g. databases) created on older NixOS versions.
-  #
-  # Most users should NEVER change this value after the initial install, for any reason,
-  # even if you've upgraded your system to a new NixOS release.
-  #
-  # This value does NOT affect the Nixpkgs version your packages and OS are pulled from,
-  # so changing it will NOT upgrade your system - see https://nixos.org/manual/nixos/stable/#sec-upgrading for how
-  # to actually do that.
-  #
-  # This value being lower than the current NixOS release does NOT mean your system is
-  # out of date, out of support, or vulnerable.
-  #
-  # Do NOT change this value unless you have manually inspected all the changes it would make to your configuration,
-  # and migrated your data accordingly.
-  #
-  # For more information, see `man configuration.nix` or https://nixos.org/manual/nixos/stable/options#opt-system.stateVersion .
-  system.stateVersion = "24.05"; # Did you read the comment?
-
-}

machines/gym-box/hardware-configuration.nix

@@ -1,47 +0,0 @@
-# Do not modify this file!  It was generated by ‘nixos-generate-config’
-# and may be overwritten by future invocations.  Please make changes
-# to /etc/nixos/configuration.nix instead.
-{
-  config,
-  lib,
-  pkgs,
-  modulesPath,
-  ...
-}:
-
-{
-  imports = [
-    (modulesPath + "/installer/scan/not-detected.nix")
-  ];
-
-  boot.initrd.availableKernelModules = [
-    "nvme"
-    "xhci_pci"
-    "thunderbolt"
-    "usbhid"
-    "uas"
-    "sd_mod"
-  ];
-  boot.initrd.kernelModules = [ ];
-  boot.kernelModules = [ "kvm-amd" ];
-  boot.extraModulePackages = [ ];
-
-  fileSystems."/" = {
-    device = "/dev/disk/by-uuid/0e75a66e-6c9e-471e-8bd2-fee7b27b74a1";
-    fsType = "btrfs";
-  };
-
-  fileSystems."/boot" = {
-    device = "/dev/disk/by-uuid/9E2C-F187";
-    fsType = "vfat";
-    options = [
-      "fmask=0022"
-      "dmask=0022"
-    ];
-  };
-
-  swapDevices = [ { device = "/.swapfile"; } ];
-
-  nixpkgs.hostPlatform = lib.mkDefault "x86_64-linux";
-  hardware.cpu.amd.updateMicrocode = lib.mkDefault config.hardware.enableRedistributableFirmware;
-}

packages/beads/default.nix

@@ -0,0 +1,26 @@
+# Beads package - issue tracker for AI-supervised coding workflows
+# Takes src as argument so it can be called from both overlay and flake packages
+{ lib
+, buildGoModule
+, git
+, pkg-config
+, icu
+, src
+, version ? "unknown"
+}:
+
+buildGoModule {
+  pname = "beads";
+  inherit version src;
+  subPackages = [ "cmd/bd" ];
+  doCheck = false;
+  vendorHash = "sha256-XAhe4yuLzP9vQ3IFhWAO5fN/3OOfokcRxfeGKaRYEws=";
+  nativeBuildInputs = [ git pkg-config ];
+  buildInputs = [ icu ];
+  meta = with lib; {
+    description = "beads (bd) - An issue tracker designed for AI-supervised coding workflows";
+    homepage = "https://github.com/steveyegge/beads";
+    license = licenses.mit;
+    mainProgram = "bd";
+  };
+}

packages/default.nix

@@ -1,11 +1,9 @@
 { pkgs, ... }:
 {
-  tea-rbw = pkgs.callPackage ./tea-rbw { };
+  tea-rbw = pkgs.callPackage ./tea-rbw {};
-  app-launcher-server = pkgs.callPackage ./app-launcher-server { };
+  app-launcher-server = pkgs.callPackage ./app-launcher-server {};
-  claude-code = pkgs.callPackage ./claude-code { };
+  claude-code = pkgs.callPackage ./claude-code {};
-  mcrcon-rbw = pkgs.callPackage ./mcrcon-rbw { };
+  mcrcon-rbw = pkgs.callPackage ./mcrcon-rbw {};
-  rclone-torbox-setup = pkgs.callPackage ./rclone-torbox-setup { };
+  rclone-torbox-setup = pkgs.callPackage ./rclone-torbox-setup {};
-  pi-coding-agent = pkgs.callPackage ./pi-coding-agent { };
+  pi-coding-agent = pkgs.callPackage ./pi-coding-agent {};
-  nextcloud-talk-desktop = pkgs.callPackage ./nextcloud-talk-desktop { };
-  opencode = pkgs.callPackage ./opencode { };
 }

packages/gastown/default.nix

@@ -0,0 +1,31 @@
+# Gastown package - multi-agent workspace manager
+# Takes src as argument so it can be called from both overlay and flake packages
+{ lib
+, buildGoModule
+, src
+, version ? "unknown"
+}:
+
+buildGoModule {
+  pname = "gastown";
+  inherit version src;
+  vendorHash = "sha256-8SdvSASP+bJjMooqEQvkCzG+J6CbsK+HCQulrPnJZ1Y=";
+  subPackages = [ "cmd/gt" ];
+  doCheck = false;
+
+  # Must match ldflags from gastown Makefile - BuiltProperly=1 is required
+  # or gt will error with "This binary was built with 'go build' directly"
+  ldflags = [
+    "-X github.com/steveyegge/gastown/internal/cmd.Version=${version}"
+    "-X github.com/steveyegge/gastown/internal/cmd.Commit=${version}"
+    "-X github.com/steveyegge/gastown/internal/cmd.BuildTime=nix-build"
+    "-X github.com/steveyegge/gastown/internal/cmd.BuiltProperly=1"
+  ];
+
+  meta = with lib; {
+    description = "Gas Town - multi-agent workspace manager by Steve Yegge";
+    homepage = "https://github.com/steveyegge/gastown";
+    license = licenses.mit;
+    mainProgram = "gt";
+  };
+}

packages/nextcloud-talk-desktop/default.nix

@@ -1,60 +0,0 @@
-# Patched Nextcloud Talk Desktop with Wayland screen sharing support
-# Applies the core change from upstream draft PR #1022:
-# https://github.com/nextcloud/talk-desktop/pull/1022
-#
-# Patches the webpack bundle in app.asar to add setDisplayMediaRequestHandler
-# with useSystemPicker: true, enabling native PipeWire/portal-based
-# screen sharing on Wayland (Sway, Hyprland, etc.)
-{ lib
-, nextcloud-talk-desktop
-, nodejs
-, asar
-}:
-
-nextcloud-talk-desktop.overrideAttrs (old: {
-  pname = "nextcloud-talk-desktop-patched";
-
-  nativeBuildInputs = (old.nativeBuildInputs or []) ++ [ asar nodejs ];
-
-  # Patch the asar after the main installPhase creates the output
-  postFixup = (old.postFixup or "") + ''
-    echo "Patching app.asar for Wayland screen sharing..."
-    ASAR_PATH="$out/opt/Nextcloud Talk-linux-x64/resources/app.asar"
-
-    WORK=$(mktemp -d)
-    asar extract "$ASAR_PATH" "$WORK/app"
-
-    # In the webpack bundle:
-    #   session = l, desktopCapturer = a, app = n
-    # We inject setDisplayMediaRequestHandler right after n.whenReady().then((async()=>{
-    # useSystemPicker: true makes Electron use the native system picker
-    # (PipeWire/xdg-desktop-portal on Wayland)
-    node -e "
-      const fs = require('fs');
-      const p = '$WORK/app/.webpack/main/index.js';
-      let c = fs.readFileSync(p, 'utf8');
-
-      if (c.includes('setDisplayMediaRequestHandler')) {
-        console.log('Already patched');
-        process.exit(0);
-      }
-
-      const marker = 'n.whenReady().then((async()=>{';
-      const idx = c.indexOf(marker);
-      if (idx === -1) {
-        console.error('ERROR: Could not find whenReady marker in webpack bundle');
-        process.exit(1);
-      }
-
-      // Inject after the marker
-      const injection = 'l.defaultSession.setDisplayMediaRequestHandler(async(e,t)=>{const s=await a.getSources({types:[\"screen\",\"window\"]});s.length>0?t({video:s[0]}):t({})},{useSystemPicker:!0});';
-
-      c = c.slice(0, idx + marker.length) + injection + c.slice(idx + marker.length);
-      fs.writeFileSync(p, c, 'utf8');
-      console.log('Successfully patched main bundle for Wayland screen sharing');
-    "
-
-    asar pack "$WORK/app" "$ASAR_PATH"
-    rm -rf "$WORK"
-  '';
-})

packages/opencode/default.nix

@@ -1,82 +0,0 @@
-{
-  lib,
-  stdenv,
-  fetchzip,
-  patchelf,
-  glibc,
-}:
-
-let
-  version = "1.4.0";
-
-  srcs = {
-    aarch64-darwin = {
-      url = "https://github.com/anomalyco/opencode/releases/download/v${version}/opencode-darwin-arm64.zip";
-      sha256 = "0m97j2vln8yhhvnsjl92phx6dac24y7hgh75csmbkbhawkz9xm4l";
-    };
-    x86_64-darwin = {
-      url = "https://github.com/anomalyco/opencode/releases/download/v${version}/opencode-darwin-x64.zip";
-      sha256 = "17n04j06pdc2raxjm91y6p87gwpnra0liabpbjwdmyd1iqgqv0q8";
-    };
-    x86_64-linux = {
-      url = "https://github.com/anomalyco/opencode/releases/download/v${version}/opencode-linux-x64.tar.gz";
-      sha256 = "16117lwfj2lb8wjbq5cyf77vhi52ada5ys3212hjqw3qw3wrcc0r";
-    };
-    aarch64-linux = {
-      url = "https://github.com/anomalyco/opencode/releases/download/v${version}/opencode-linux-arm64.tar.gz";
-      sha256 = "06lvm1qiji74xdd3psqn6lwxak65gqsbmkib1pjb4n65f9246jwm";
-    };
-  };
-
-  src =
-    srcs.${stdenv.hostPlatform.system} or (throw "Unsupported system: ${stdenv.hostPlatform.system}");
-
-in
-stdenv.mkDerivation {
-  pname = "opencode";
-  inherit version;
-
-  src = fetchzip {
-    inherit (src) url sha256;
-  };
-
-  # Bun standalone binaries have JS code appended after the ELF sections
-  # stripping/patching would remove or corrupt this appended data
-  dontStrip = true;
-  dontPatchELF = true;
-
-  nativeBuildInputs = lib.optionals stdenv.isLinux [ patchelf ];
-
-  installPhase = ''
-    runHook preInstall
-
-    install -Dm755 $src/opencode $out/bin/opencode
-
-    runHook postInstall
-  '';
-
-  # Manually patch the interpreter for bun standalone binaries on Linux
-  postFixup = lib.optionalString stdenv.isLinux ''
-    interpreter="${glibc}/lib/${
-      if stdenv.hostPlatform.system == "aarch64-linux" then
-        "ld-linux-aarch64.so.1"
-      else
-        "ld-linux-x86-64.so.2"
-    }"
-    patchelf --set-interpreter "$interpreter" $out/bin/opencode
-  '';
-
-  meta = with lib; {
-    description = "Terminal-based AI coding assistant";
-    homepage = "https://opencode.ai";
-    license = licenses.mit;
-    maintainers = [ ];
-    platforms = [
-      "aarch64-darwin"
-      "x86_64-darwin"
-      "x86_64-linux"
-      "aarch64-linux"
-    ];
-    mainProgram = "opencode";
-  };
-}

packages/opencode/update.sh

@@ -1,148 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-DRY_RUN=false
-
-while [[ $# -gt 0 ]]; do
-    case $1 in
-        --dry-run|-n)
-            DRY_RUN=true
-            shift
-            ;;
-        --help|-h)
-            echo "Usage: $0 [OPTIONS]"
-            echo ""
-            echo "Options:"
-            echo "  --dry-run, -n    Show what would be updated without making changes"
-            echo "  --help, -h       Show this help message"
-            exit 0
-            ;;
-        *)
-            echo "Unknown option: $1"
-            echo "Use --help for usage information"
-            exit 1
-            ;;
-    esac
-done
-
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-YELLOW='\033[1;33m'
-NC='\033[0m'
-
-REPO_ROOT="${REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"
-NIX_FILE="$REPO_ROOT/packages/opencode/default.nix"
-
-echo "Fetching latest opencode version from GitHub API..."
-
-RELEASE_INFO=$(curl -fsSL https://api.github.com/repos/anomalyco/opencode/releases/latest)
-NEW_VERSION=$(echo "$RELEASE_INFO" | jq -r '.tag_name' | sed 's/^v//')
-
-if [ -z "$NEW_VERSION" ] || [ "$NEW_VERSION" = "null" ]; then
-    echo -e "${RED}Error: Failed to fetch version from GitHub API${NC}"
-    exit 1
-fi
-
-CURRENT_VERSION=$(grep -m1 'version = ' "$NIX_FILE" | sed -E 's/.*version = "([^"]+)".*/\1/')
-
-if [ "$CURRENT_VERSION" = "$NEW_VERSION" ]; then
-    echo -e "${GREEN}Already up to date: $CURRENT_VERSION${NC}"
-    exit 0
-fi
-
-echo -e "${YELLOW}Updating from $CURRENT_VERSION to $NEW_VERSION${NC}"
-
-# Compute SHA256 hashes for each platform
-# fetchzip hashes the unpacked directory, so we need to extract and hash
-compute_unpacked_hash() {
-    local url="$1"
-    local ext="$2"
-    local tmpdir=$(mktemp -d)
-    local archive="/tmp/opencode-archive.$ext"
-    
-    curl -fsSL "$url" -o "$archive"
-    
-    if [ "$ext" = "zip" ]; then
-        (cd "$tmpdir" && unzip -q "$archive")
-    else
-        (cd "$tmpdir" && tar xzf "$archive")
-    fi
-    
-    local sri_hash=$(nix hash path "$tmpdir")
-    local nix32_hash=$(nix hash convert --hash-algo sha256 --to nix32 "$sri_hash")
-    
-    rm -rf "$tmpdir" "$archive"
-    echo "$nix32_hash"
-}
-
-echo "Computing SHA256 hashes (this may take a moment)..."
-
-SHA_DARWIN_ARM=$(compute_unpacked_hash "https://github.com/anomalyco/opencode/releases/download/v${NEW_VERSION}/opencode-darwin-arm64.zip" "zip")
-echo "  aarch64-darwin: $SHA_DARWIN_ARM"
-
-SHA_DARWIN_X64=$(compute_unpacked_hash "https://github.com/anomalyco/opencode/releases/download/v${NEW_VERSION}/opencode-darwin-x64.zip" "zip")
-echo "  x86_64-darwin: $SHA_DARWIN_X64"
-
-SHA_LINUX_X64=$(compute_unpacked_hash "https://github.com/anomalyco/opencode/releases/download/v${NEW_VERSION}/opencode-linux-x64.tar.gz" "tar.gz")
-echo "  x86_64-linux: $SHA_LINUX_X64"
-
-SHA_LINUX_ARM64=$(compute_unpacked_hash "https://github.com/anomalyco/opencode/releases/download/v${NEW_VERSION}/opencode-linux-arm64.tar.gz" "tar.gz")
-echo "  aarch64-linux: $SHA_LINUX_ARM64"
-
-if [ "$DRY_RUN" = true ]; then
-    echo -e "${YELLOW}DRY RUN - No changes will be made${NC}"
-    echo ""
-    echo "Would update:"
-    echo "  Version: $CURRENT_VERSION -> $NEW_VERSION"
-    echo "  aarch64-darwin SHA: $SHA_DARWIN_ARM"
-    echo "  x86_64-darwin SHA:  $SHA_DARWIN_X64"
-    echo "  x86_64-linux SHA:   $SHA_LINUX_X64"
-    echo "  aarch64-linux SHA:  $SHA_LINUX_ARM64"
-    exit 0
-fi
-
-# Update version
-sed -i.tmp "s/version = \".*\";/version = \"$NEW_VERSION\";/" "$NIX_FILE"
-
-# Update SHA256 hashes using awk
-awk -v sha_arm="$SHA_DARWIN_ARM" -v sha_x64="$SHA_DARWIN_X64" -v sha_linux_x64="$SHA_LINUX_X64" -v sha_linux_arm="$SHA_LINUX_ARM64" '
-/aarch64-darwin = {/ { in_arm = 1 }
-/x86_64-darwin = {/ { in_x64 = 1; in_arm = 0 }
-/x86_64-linux = {/ { in_linux_x64 = 1; in_x64 = 0 }
-/aarch64-linux = {/ { in_linux_arm = 1; in_linux_x64 = 0 }
-/};/ {
-  in_arm = 0
-  in_x64 = 0
-  in_linux_x64 = 0
-  in_linux_arm = 0
-}
-/sha256 = / {
-  if (in_arm) {
-    sub(/sha256 = ".*";/, "sha256 = \"" sha_arm "\";")
-  } else if (in_x64) {
-    sub(/sha256 = ".*";/, "sha256 = \"" sha_x64 "\";")
-  } else if (in_linux_x64) {
-    sub(/sha256 = ".*";/, "sha256 = \"" sha_linux_x64 "\";")
-  } else if (in_linux_arm) {
-    sub(/sha256 = ".*";/, "sha256 = \"" sha_linux_arm "\";")
-  }
-}
-{ print }
-' "$NIX_FILE" > "$NIX_FILE.new"
-
-mv "$NIX_FILE.new" "$NIX_FILE"
-rm -f "$NIX_FILE.tmp"
-
-echo -e "${GREEN}Successfully updated to version $NEW_VERSION${NC}"
-echo ""
-echo "Updated SHA256 hashes:"
-echo "  aarch64-darwin: $SHA_DARWIN_ARM"
-echo "  x86_64-darwin:  $SHA_DARWIN_X64"
-echo "  x86_64-linux:   $SHA_LINUX_X64"
-echo "  aarch64-linux:  $SHA_LINUX_ARM64"
-echo ""
-echo "Next steps:"
-echo "  1. Review changes: git diff $NIX_FILE"
-echo "  2. Test build: nix build .#custom-opencode"
-echo "  3. Verify version: ./result/bin/opencode --version"
-echo "  4. Commit: git add $NIX_FILE && git commit -m 'opencode: Update to version $NEW_VERSION'"

packages/perles/default.nix

@@ -0,0 +1,25 @@
+# Perles - Terminal UI for beads issue tracking
+# Takes src as argument so it can be called from both overlay and flake packages
+{ lib
+, buildGoModule
+, src
+, version ? "unknown"
+}:
+
+buildGoModule {
+  pname = "perles";
+  inherit version src;
+  doCheck = false;
+  vendorHash = "sha256-A5LE9Cor/DRcJtVpiScSoqDYhJIKyaq0cbK+OGmr4XU=";
+
+  ldflags = [
+    "-X main.version=${version}"
+  ];
+
+  meta = with lib; {
+    description = "Perles - Terminal UI for beads issue tracking";
+    homepage = "https://github.com/zjrosen/perles";
+    license = licenses.mit;
+    mainProgram = "perles";
+  };
+}

renovate.json

@@ -13,7 +13,7 @@
   "lockFileMaintenance": {
     "enabled": true,
     "schedule": [
-      "after 5pm and before 7pm on Saturday"
+      "after 2pm and before 4pm on Saturday"
     ]
   },
   "dependencyDashboard": true,
@@ -39,7 +39,7 @@
         "/^nix-darwin$/"
       ],
       "schedule": [
-        "after 5pm and before 7pm on Saturday"
+        "after 2pm and before 4pm on Saturday"
       ]
     },
     {
@@ -53,7 +53,7 @@
         "/home-manager-unstable/"
       ],
       "schedule": [
-        "after 5pm and before 7pm on Saturday"
+        "after 2pm and before 4pm on Saturday"
       ]
     },
     {
@@ -65,7 +65,7 @@
         "/nixpkgs-qt/"
       ],
       "schedule": [
-        "after 7pm and before 9pm on Saturday"
+        "after 4pm and before 6pm on Saturday"
       ]
     },
     {
@@ -77,6 +77,32 @@
       "matchPackageNames": [
         "/google-cookie-retrieval/"
       ]
+    },
+    {
+      "description": "Gastown is under active development - check for updates daily",
+      "matchManagers": [
+        "nix"
+      ],
+      "matchPackageNames": [
+        "/gastown/"
+      ],
+      "schedule": [
+        "before 6am"
+      ],
+      "automerge": false
+    },
+    {
+      "description": "Beads is under active development - check for updates daily",
+      "matchManagers": [
+        "nix"
+      ],
+      "matchPackageNames": [
+        "/beads/"
+      ],
+      "schedule": [
+        "before 6am"
+      ],
+      "automerge": false
     }
   ]
 }

roles/default.nix

@@ -12,7 +12,6 @@ with lib;
     ./k3s-node
     ./kodi
     ./nfs-mounts
-    ./plasma-bigscreen
     ./nvidia
     ./printing
     ./rclone-mount

roles/plasma-bigscreen/default.nix

@@ -1,134 +0,0 @@
-{ config, lib, pkgs, ... }:
-
-with lib;
-
-let
-  cfg = config.roles.plasma-bigscreen;
-
-  # Plasma Bigscreen package — not yet in nixpkgs, built from upstream master.
-  # TODO: Replace with pkgs.kdePackages.plasma-bigscreen once available.
-  plasma-bigscreen = pkgs.kdePackages.callPackage ./package.nix {};
-
-  jellyfinMediaPlayerPkg =
-    if cfg.jellyfinScaleFactor != null
-    then pkgs.symlinkJoin {
-      name = "jellyfin-media-player-scaled";
-      paths = [ pkgs.qt-pinned.jellyfin-media-player ];
-      nativeBuildInputs = [ pkgs.makeWrapper ];
-      postBuild = ''
-        mkdir -p $out/bin
-        rm -f $out/bin/jellyfin-desktop
-        makeWrapper ${pkgs.qt-pinned.jellyfin-media-player}/bin/jellyfin-desktop $out/bin/jellyfin-desktop \
-          --add-flags "--tv --scale-factor ${toString cfg.jellyfinScaleFactor}"
-
-        # Update .desktop file to include scale factor and TV mode arguments
-        mkdir -p $out/share/applications
-        rm -f $out/share/applications/org.jellyfin.JellyfinDesktop.desktop
-        substitute ${pkgs.qt-pinned.jellyfin-media-player}/share/applications/org.jellyfin.JellyfinDesktop.desktop \
-          $out/share/applications/org.jellyfin.JellyfinDesktop.desktop \
-          --replace-fail "Exec=jellyfin-desktop" "Exec=jellyfin-desktop --tv --scale-factor ${toString cfg.jellyfinScaleFactor}"
-      '';
-    }
-    else pkgs.qt-pinned.jellyfin-media-player;
-in
-{
-  options.roles.plasma-bigscreen = {
-    enable = mkEnableOption "Plasma Bigscreen TV interface";
-
-    autologin = mkOption {
-      type = types.bool;
-      default = false;
-      description = "Auto-login to Plasma Bigscreen session";
-    };
-
-    user = mkOption {
-      type = types.str;
-      default = "kodi";
-      description = "User account for the Bigscreen session";
-    };
-
-    jellyfinScaleFactor = mkOption {
-      type = types.nullOr types.float;
-      default = null;
-      description = "Scale factor for Jellyfin Media Player UI (e.g., 1.0 for 100% scaling)";
-    };
-
-    appLauncherServer = {
-      enable = mkOption {
-        type = types.bool;
-        default = false;
-        description = "Enable HTTP app launcher server for remote control";
-      };
-      port = mkOption {
-        type = types.int;
-        default = 8081;
-        description = "Port for the app launcher HTTP server";
-      };
-    };
-  };
-
-  config = mkIf cfg.enable {
-    # Create the bigscreen user
-    users.extraUsers.${cfg.user} = {
-      isNormalUser = true;
-      extraGroups = [ "wheel" "networkmanager" "audio" "video" ];
-    };
-
-    # Plasma Bigscreen is a Plasma 6 shell — needs Plasma 6 desktop manager
-    services.desktopManager.plasma6.enable = true;
-
-    # Register the bigscreen session with the display manager
-    services.displayManager = {
-      sessionPackages = [ plasma-bigscreen ];
-    } // optionalAttrs cfg.autologin {
-      autoLogin.enable = true;
-      autoLogin.user = cfg.user;
-      defaultSession = "plasma-bigscreen-wayland";
-    };
-    xdg.portal.configPackages = [ plasma-bigscreen ];
-
-    # Fix homescreen not being focused after quitting app or on boot
-    # xwaylandvideobridge can interfere with focus; exclude if present
-    environment.plasma6.excludePackages =
-      lib.optional (pkgs.kdePackages ? xwaylandvideobridge) pkgs.kdePackages.xwaylandvideobridge;
-
-    # Firewall for remote control
-    networking.firewall = {
-      allowedTCPPorts = optional cfg.appLauncherServer.enable cfg.appLauncherServer.port;
-    };
-
-    environment.systemPackages = with pkgs; [
-      plasma-bigscreen
-      firefox
-      jellyfinMediaPlayerPkg
-      qt-pinned.stremio
-      wget
-    ] ++ optional cfg.appLauncherServer.enable pkgs.custom.app-launcher-server;
-
-    nixpkgs.config.permittedInsecurePackages = lib.warn
-      "Allowing insecure package qtwebengine-5.15.19 as a jellyfin-media-player/stremio dependency."
-      [
-        "qtwebengine-5.15.19"
-      ];
-
-    programs.kdeconnect.enable = true;
-
-    systemd.user.services = mkIf cfg.appLauncherServer.enable {
-      app-launcher-server = {
-        description = "HTTP App Launcher Server";
-        wantedBy = [ "graphical-session.target" ];
-        after = [ "graphical-session.target" ];
-        serviceConfig = {
-          Type = "simple";
-          ExecStart = "${pkgs.custom.app-launcher-server}/bin/app-launcher-server ${toString cfg.appLauncherServer.port}";
-          Restart = "always";
-          RestartSec = "5s";
-          Environment = [
-            "PATH=${pkgs.firefox}/bin:/run/current-system/sw/bin"
-          ];
-        };
-      };
-    };
-
-  };
-}

roles/plasma-bigscreen/package.nix

@@ -1,120 +0,0 @@
-# Plasma Bigscreen — TV interface for Plasma 6
-# Not yet released or packaged in nixpkgs; built from upstream master.
-#
-# TODO: Remove this file once plasma-bigscreen lands in nixpkgs.
-#   Tracking issue: https://github.com/NixOS/nixpkgs/issues/428077
-#   Draft nixpkgs PR: https://github.com/NixOS/nixpkgs/pull/428353
-#   When available, switch to pkgs.kdePackages.plasma-bigscreen.
-#
-# Upstream: https://invent.kde.org/plasma/plasma-bigscreen
-{
-  mkKdeDerivation,
-  lib,
-  fetchFromGitLab,
-  pkg-config,
-  # KDE Frameworks 6
-  ki18n,
-  kdeclarative,
-  kcmutils,
-  knotifications,
-  kio,
-  kwayland,
-  kwindowsystem,
-  ksvg,
-  kiconthemes,
-  kglobalaccel,
-  kdbusaddons,
-  # KDE Plasma 6
-  plasma-workspace,
-  plasma-nano,
-  plasma-nm,
-  plasma-activities,
-  plasma-activities-stats,
-  milou,
-  libkscreen,
-  kdeconnect-kde,
-  # Qt 6
-  qtdeclarative, # needed for Qt6::QmlPrivate — see QCoro workaround in postPatch
-  qtmultimedia,
-  qtwebengine,
-  # Other
-  bluez-qt,
-  qcoro,
-  plasma-wayland-protocols,
-  wayland,
-  sdl3,
-}:
-
-mkKdeDerivation {
-  pname = "plasma-bigscreen";
-  version = "unstable-2026-03-07";
-
-  src = fetchFromGitLab {
-    domain = "invent.kde.org";
-    owner = "plasma";
-    repo = "plasma-bigscreen";
-    rev = "bd143fea7e386bac1652b8150a3ed3d5ef7cf93c";
-    hash = "sha256-y439IX7e0+XqxqFj/4+P5le0hA7DiwA+smDsD0UH/fI=";
-  };
-
-  extraNativeBuildInputs = [
-    pkg-config
-  ];
-
-  extraBuildInputs = [
-    # KDE Frameworks (auto-injected by mkKdeDerivation: ki18n, kcmutils,
-    # knotifications, kio, kwayland, kwindowsystem, ksvg, kiconthemes)
-    kdeclarative
-    kglobalaccel
-    kdbusaddons
-    # Plasma (auto-injected: plasma-workspace, plasma-activities,
-    # plasma-activities-stats, libkscreen)
-    plasma-nano
-    plasma-nm
-    milou
-    kdeconnect-kde
-    # Qt — qtdeclarative is needed for Qt6::QmlPrivate (see postPatch)
-    qtdeclarative
-    qtmultimedia
-    qtwebengine
-    # Other (auto-injected: bluez-qt)
-    qcoro
-    plasma-wayland-protocols
-    wayland
-    sdl3
-  ];
-
-  postPatch = ''
-        substituteInPlace bin/plasma-bigscreen-wayland.in \
-          --replace @KDE_INSTALL_FULL_LIBEXECDIR@ "${plasma-workspace}/libexec"
-
-        # WORKAROUND: Plasma version numbers must match; we're building an
-        # unreleased package against a stable Plasma release. Remove once
-        # bigscreen is part of the Plasma release cycle.
-        substituteInPlace CMakeLists.txt \
-          --replace-fail 'set(PROJECT_VERSION "6.5.80")' 'set(PROJECT_VERSION "${plasma-workspace.version}")'
-
-        # WORKAROUND: QCoro6Qml's cmake config links against Qt6::QmlPrivate but
-        # doesn't call find_package to import the target. This is arguably a QCoro
-        # packaging bug in nixpkgs (it should propagate qtdeclarative). Remove
-        # once QCoro or the nixpkgs plasma-bigscreen package is fixed upstream.
-        substituteInPlace CMakeLists.txt \
-          --replace-fail 'find_package(QCoro6' 'find_package(Qt6 ''${QT_MIN_VERSION} CONFIG REQUIRED COMPONENTS QmlPrivate)
-    find_package(QCoro6'
-  '';
-
-  preFixup = ''
-    wrapQtApp $out/bin/plasma-bigscreen-wayland
-  '';
-
-  passthru.providedSessions = [
-    "plasma-bigscreen-wayland"
-  ];
-
-  meta = {
-    description = "Plasma shell for TVs (Plasma Bigscreen)";
-    homepage = "https://plasma-bigscreen.org";
-    license = lib.licenses.gpl2Plus;
-    platforms = lib.platforms.linux;
-  };
-}