@chankov/agent-fleet 0.0.10 → 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (690) hide show
  1. package/.pi/extensions/agent-fleet-update-check/README.md +4 -4
  2. package/.pi/extensions/btw/README.md +29 -27
  3. package/.pi/extensions/btw/index.ts +80 -83
  4. package/.pi/extensions/pi-voice-stt/README.md +7 -3
  5. package/.pi/extensions/pi-voice-stt/config.ts +1 -1
  6. package/.pi/harnesses/agent-hub/README.md +109 -54
  7. package/.pi/harnesses/agent-hub/backend-policy.js +25 -4
  8. package/.pi/harnesses/agent-hub/footer.ts +4 -0
  9. package/.pi/harnesses/agent-hub/helpers.ts +18 -0
  10. package/.pi/harnesses/agent-hub/index.ts +537 -369
  11. package/.pi/harnesses/agent-hub/monitor-session-bridge.ts +10 -1
  12. package/.pi/harnesses/agent-hub/package.json +1 -1
  13. package/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
  14. package/.pi/harnesses/agent-hub/posture.ts +103 -0
  15. package/.pi/harnesses/ask-user-remote/README.md +37 -3
  16. package/.pi/harnesses/ask-user-remote/index.ts +173 -17
  17. package/.pi/harnesses/coms/package.json +1 -1
  18. package/.pi/harnesses/damage-control-continue/package.json +1 -1
  19. package/.pi/harnesses/lib/fleet-dashboard-ops.ts +118 -0
  20. package/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
  21. package/.pi/harnesses/lib/fleet-detail-view.ts +43 -0
  22. package/.pi/harnesses/lib/fleet-overlay.ts +26 -0
  23. package/.pi/harnesses/lib/fleet-panel.ts +34 -0
  24. package/.pi/harnesses/lib/fleet-read-model.ts +131 -0
  25. package/.pi/harnesses/lib/fleet-selection.ts +24 -0
  26. package/.pi/harnesses/package-lock.json +2011 -0
  27. package/.pi/harnesses/package.json +1 -0
  28. package/.versions/0.0.11/.pi/agents/dispatch-policy.yaml +32 -0
  29. package/.versions/0.0.11/.pi/agents/model-profiles.yaml +27 -0
  30. package/.versions/0.0.11/.pi/agents/peers.yaml +142 -0
  31. package/.versions/0.0.11/.pi/agents/teams.yaml +41 -0
  32. package/.versions/0.0.11/.pi/damage-control-rules.yaml +297 -0
  33. package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/README.md +57 -0
  34. package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  35. package/.versions/0.0.11/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  36. package/.versions/0.0.11/.pi/extensions/btw/README.md +119 -0
  37. package/.versions/0.0.11/.pi/extensions/btw/index.ts +917 -0
  38. package/.versions/0.0.11/.pi/extensions/btw/package.json +6 -0
  39. package/.versions/0.0.11/.pi/extensions/btw/state.js +179 -0
  40. package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
  41. package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  42. package/.versions/0.0.11/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  43. package/.versions/0.0.11/.pi/extensions/compact-and-continue/README.md +42 -0
  44. package/.versions/0.0.11/.pi/extensions/compact-and-continue/index.ts +120 -0
  45. package/.versions/0.0.11/.pi/extensions/compact-and-continue/package.json +6 -0
  46. package/.versions/0.0.11/.pi/extensions/mcp-bridge/README.md +46 -0
  47. package/.versions/0.0.11/.pi/extensions/mcp-bridge/index.ts +206 -0
  48. package/.versions/0.0.11/.pi/extensions/mcp-bridge/package.json +6 -0
  49. package/.versions/0.0.11/.pi/extensions/package-lock.json +1143 -0
  50. package/.versions/0.0.11/.pi/extensions/package.json +9 -0
  51. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/README.md +205 -0
  52. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/config.ts +198 -0
  53. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  54. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/index.ts +248 -0
  55. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/package.json +6 -0
  56. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  57. package/.versions/0.0.11/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  58. package/.versions/0.0.11/.pi/harnesses/agent-hub/README.md +1004 -0
  59. package/.versions/0.0.11/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  60. package/.versions/0.0.11/.pi/harnesses/agent-hub/artifacts.js +146 -0
  61. package/.versions/0.0.11/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  62. package/.versions/0.0.11/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  63. package/.versions/0.0.11/.pi/harnesses/agent-hub/context-window.js +106 -0
  64. package/.versions/0.0.11/.pi/harnesses/agent-hub/delegate.ts +435 -0
  65. package/.versions/0.0.11/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  66. package/.versions/0.0.11/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
  67. package/.versions/0.0.11/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  68. package/.versions/0.0.11/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  69. package/.versions/0.0.11/.pi/harnesses/agent-hub/footer.ts +31 -0
  70. package/.versions/0.0.11/.pi/harnesses/agent-hub/helpers.ts +248 -0
  71. package/.versions/0.0.11/.pi/harnesses/agent-hub/index.ts +9111 -0
  72. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  73. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  74. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  75. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  76. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  77. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  78. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  79. package/.versions/0.0.11/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
  80. package/.versions/0.0.11/.pi/harnesses/agent-hub/package.json +7 -0
  81. package/.versions/0.0.11/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  82. package/.versions/0.0.11/.pi/harnesses/agent-hub/research-retention.js +34 -0
  83. package/.versions/0.0.11/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  84. package/.versions/0.0.11/.pi/harnesses/agent-hub/return-contract.js +293 -0
  85. package/.versions/0.0.11/.pi/harnesses/agent-hub/return-extract.js +75 -0
  86. package/.versions/0.0.11/.pi/harnesses/agent-hub/review-findings.js +102 -0
  87. package/.versions/0.0.11/.pi/harnesses/agent-hub/run-budget.js +479 -0
  88. package/.versions/0.0.11/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  89. package/.versions/0.0.11/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  90. package/.versions/0.0.11/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  91. package/.versions/0.0.11/.pi/harnesses/agent-hub/session-health.js +110 -0
  92. package/.versions/0.0.11/.pi/harnesses/agent-hub/spawn.ts +354 -0
  93. package/.versions/0.0.11/.pi/harnesses/agent-hub/version.ts +42 -0
  94. package/.versions/0.0.11/.pi/harnesses/ask-user-remote/README.md +53 -0
  95. package/.versions/0.0.11/.pi/harnesses/ask-user-remote/index.ts +477 -0
  96. package/.versions/0.0.11/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  97. package/.versions/0.0.11/.pi/harnesses/coms/README.md +100 -0
  98. package/.versions/0.0.11/.pi/harnesses/coms/index.ts +1767 -0
  99. package/.versions/0.0.11/.pi/harnesses/coms/package.json +7 -0
  100. package/.versions/0.0.11/.pi/harnesses/coms/version.ts +42 -0
  101. package/.versions/0.0.11/.pi/harnesses/damage-control-continue/README.md +124 -0
  102. package/.versions/0.0.11/.pi/harnesses/damage-control-continue/index.ts +536 -0
  103. package/.versions/0.0.11/.pi/harnesses/damage-control-continue/package.json +7 -0
  104. package/.versions/0.0.11/.pi/harnesses/damage-control-continue/version.ts +42 -0
  105. package/.versions/0.0.11/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  106. package/.versions/0.0.11/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  107. package/.versions/0.0.11/.pi/harnesses/lib/herdr-client.ts +472 -0
  108. package/.versions/0.0.11/.pi/harnesses/lib/herdr-presence.ts +399 -0
  109. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  110. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  111. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  112. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  113. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  114. package/.versions/0.0.11/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  115. package/.versions/0.0.11/.pi/harnesses/lib/spawned-peers.js +190 -0
  116. package/.versions/0.0.11/.pi/harnesses/package-lock.json +2046 -0
  117. package/.versions/0.0.11/.pi/harnesses/package.json +10 -0
  118. package/.versions/0.0.11/.pi/prompts/af-build.md +24 -0
  119. package/{.claude/commands/code-simplify.md → .versions/0.0.11/.pi/prompts/af-code-simplify.md} +3 -3
  120. package/{.claude/commands/plan.md → .versions/0.0.11/.pi/prompts/af-plan.md} +1 -1
  121. package/{.claude/commands/review.md → .versions/0.0.11/.pi/prompts/af-review.md} +3 -3
  122. package/.versions/0.0.11/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  123. package/.versions/0.0.11/.pi/prompts/af-ship.md +17 -0
  124. package/{.claude/commands/spec.md → .versions/0.0.11/.pi/prompts/af-spec.md} +1 -1
  125. package/{.claude/commands/test.md → .versions/0.0.11/.pi/prompts/af-test.md} +2 -2
  126. package/.versions/0.0.11/.pi/skills/bowser/SKILL.md +145 -0
  127. package/.versions/0.0.11/.version +1 -0
  128. package/.versions/0.0.11/agents/architect.md +24 -0
  129. package/.versions/0.0.11/agents/bowser.md +27 -0
  130. package/.versions/0.0.11/agents/builder.md +54 -0
  131. package/.versions/0.0.11/agents/code-reviewer.md +208 -0
  132. package/.versions/0.0.11/agents/deep-researcher.md +32 -0
  133. package/.versions/0.0.11/agents/documenter.md +18 -0
  134. package/.versions/0.0.11/agents/orchestrator.md +72 -0
  135. package/.versions/0.0.11/agents/plan-reviewer.md +83 -0
  136. package/.versions/0.0.11/agents/planner.md +70 -0
  137. package/.versions/0.0.11/agents/releaser.md +24 -0
  138. package/.versions/0.0.11/agents/researcher.md +28 -0
  139. package/.versions/0.0.11/agents/security-auditor.md +167 -0
  140. package/.versions/0.0.11/agents/test-engineer.md +153 -0
  141. package/.versions/0.0.11/agents/web-debugger.md +43 -0
  142. package/.versions/0.0.11/agents/web-performance-auditor.md +193 -0
  143. package/.versions/0.0.11/codex/CONDUCTOR.md +148 -0
  144. package/.versions/0.0.11/docs/ARCHITECTURE.md +301 -0
  145. package/.versions/0.0.11/docs/agent-fleet-setup.md +351 -0
  146. package/.versions/0.0.11/docs/claude-code-coms-bridge.md +127 -0
  147. package/.versions/0.0.11/docs/codex-remote-conductor.md +170 -0
  148. package/.versions/0.0.11/docs/coms-hermes-bridge.md +189 -0
  149. package/.versions/0.0.11/docs/getting-started.md +43 -0
  150. package/.versions/0.0.11/docs/npm-install.md +96 -0
  151. package/.versions/0.0.11/docs/pi-extensions.md +368 -0
  152. package/.versions/0.0.11/docs/pi-setup.md +57 -0
  153. package/.versions/0.0.11/docs/skill-anatomy.md +150 -0
  154. package/.versions/0.0.11/hermes/README.md +347 -0
  155. package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  156. package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  157. package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  158. package/.versions/0.0.11/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  159. package/.versions/0.0.11/hermes/gates/gate-o-capability.md +8 -0
  160. package/.versions/0.0.11/hermes/gates/gate-o-validator-fixtures.json +1 -0
  161. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  162. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  163. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  164. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  165. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  166. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  167. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  168. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  169. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  170. package/.versions/0.0.11/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  171. package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  172. package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  173. package/.versions/0.0.11/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  174. package/.versions/0.0.11/hermes/skills/hub-conductor/SKILL.md +84 -0
  175. package/.versions/0.0.11/hermes/skills/hub-liaison/SKILL.md +84 -0
  176. package/.versions/0.0.11/hermes/skills/hub-watchdog/SKILL.md +76 -0
  177. package/.versions/0.0.11/hermes/skills/hub-watchdog/manifest.json +1 -0
  178. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  179. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  180. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  181. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  182. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  183. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  184. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  185. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  186. package/.versions/0.0.11/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  187. package/.versions/0.0.11/hermes/watchdog-tests/__init__.py +0 -0
  188. package/.versions/0.0.11/hooks/coms-stop-hook.mjs +84 -0
  189. package/.versions/0.0.11/install-manifest.json +2743 -0
  190. package/.versions/0.0.11/justfile +261 -0
  191. package/.versions/0.0.11/manifest-meta.json +881 -0
  192. package/.versions/0.0.11/references/accessibility-checklist.md +160 -0
  193. package/.versions/0.0.11/references/definition-of-done.md +67 -0
  194. package/.versions/0.0.11/references/fleet-coordination-patterns.md +151 -0
  195. package/.versions/0.0.11/references/observability-checklist.md +91 -0
  196. package/.versions/0.0.11/references/orchestration-patterns.md +370 -0
  197. package/.versions/0.0.11/references/performance-checklist.md +153 -0
  198. package/.versions/0.0.11/references/prompting-patterns.md +380 -0
  199. package/.versions/0.0.11/references/security-checklist.md +179 -0
  200. package/.versions/0.0.11/references/testing-patterns.md +236 -0
  201. package/.versions/0.0.11/scripts/codex-conductor.ts +41 -0
  202. package/.versions/0.0.11/scripts/codex-remote-control.ts +167 -0
  203. package/.versions/0.0.11/scripts/coms-claude-bridge.ts +401 -0
  204. package/.versions/0.0.11/scripts/coms-cli.ts +484 -0
  205. package/.versions/0.0.11/scripts/coms-hermes-bridge.ts +413 -0
  206. package/.versions/0.0.11/scripts/fleet.ts +168 -0
  207. package/.versions/0.0.11/scripts/hermes-monitor-capability-runner.ts +25 -0
  208. package/.versions/0.0.11/scripts/hermes-monitor-scenario.ts +474 -0
  209. package/.versions/0.0.11/scripts/hermes-watchdog-capability-probe.ts +45 -0
  210. package/.versions/0.0.11/scripts/install-hermes-plugin.sh +180 -0
  211. package/.versions/0.0.11/scripts/lib/claude-bridge-core.ts +165 -0
  212. package/.versions/0.0.11/scripts/lib/codex-conductor.ts +88 -0
  213. package/.versions/0.0.11/scripts/lib/codex-remote-control.ts +480 -0
  214. package/.versions/0.0.11/scripts/lib/coms-envelope.ts +582 -0
  215. package/.versions/0.0.11/scripts/lib/fake-herdr-server.ts +88 -0
  216. package/.versions/0.0.11/scripts/lib/fleet-command.ts +119 -0
  217. package/.versions/0.0.11/scripts/lib/herdr-layout.ts +281 -0
  218. package/.versions/0.0.11/scripts/lib/hermes-bridge-core.ts +241 -0
  219. package/.versions/0.0.11/scripts/lib/hermes-monitor-events.ts +1 -0
  220. package/.versions/0.0.11/scripts/lib/hermes-monitor-herdr.ts +2 -0
  221. package/.versions/0.0.11/scripts/lib/hermes-monitor-model.ts +3 -0
  222. package/.versions/0.0.11/scripts/lib/hermes-monitor-registry.ts +2 -0
  223. package/.versions/0.0.11/scripts/lib/hermes-monitor-socket.ts +2 -0
  224. package/.versions/0.0.11/scripts/lib/hermes-monitor-store.ts +2 -0
  225. package/.versions/0.0.11/scripts/lib/monitor-env.ts +146 -0
  226. package/.versions/0.0.11/scripts/lib/peer-launch.ts +314 -0
  227. package/.versions/0.0.11/scripts/lib/persona-banner.ts +62 -0
  228. package/.versions/0.0.11/scripts/lib/spawn-stagger.ts +101 -0
  229. package/.versions/0.0.11/scripts/lib/team-project.ts +193 -0
  230. package/.versions/0.0.11/scripts/lib/team-snapshot.ts +147 -0
  231. package/.versions/0.0.11/scripts/peer-banner.ts +40 -0
  232. package/.versions/0.0.11/scripts/peer-launch.ts +259 -0
  233. package/.versions/0.0.11/scripts/team-snapshot.ts +237 -0
  234. package/.versions/0.0.11/scripts/team-up.ts +360 -0
  235. package/.versions/0.0.11/skills/_internal/grilling.md +11 -0
  236. package/.versions/0.0.11/skills/browser-testing-with-devtools/SKILL.md +351 -0
  237. package/.versions/0.0.11/skills/code-review-and-quality/SKILL.md +381 -0
  238. package/.versions/0.0.11/skills/compound-learning/SKILL.md +137 -0
  239. package/.versions/0.0.11/skills/context-engineering/SKILL.md +291 -0
  240. package/.versions/0.0.11/skills/deprecation-and-migration/SKILL.md +206 -0
  241. package/.versions/0.0.11/skills/designing-agents/SKILL.md +394 -0
  242. package/.versions/0.0.11/skills/designing-agents/pi-harness-authoring.md +222 -0
  243. package/.versions/0.0.11/skills/frontend-ui-engineering/SKILL.md +328 -0
  244. package/.versions/0.0.11/skills/git-workflow-and-versioning/SKILL.md +316 -0
  245. package/.versions/0.0.11/skills/idea-refine/SKILL.md +182 -0
  246. package/.versions/0.0.11/skills/idea-refine/examples.md +238 -0
  247. package/.versions/0.0.11/skills/idea-refine/frameworks.md +99 -0
  248. package/.versions/0.0.11/skills/idea-refine/refinement-criteria.md +113 -0
  249. package/.versions/0.0.11/skills/idea-refine/scripts/idea-refine.sh +15 -0
  250. package/.versions/0.0.11/skills/incremental-implementation/SKILL.md +287 -0
  251. package/.versions/0.0.11/skills/interview-me/SKILL.md +226 -0
  252. package/.versions/0.0.11/skills/orchestration-verification/SKILL.md +181 -0
  253. package/.versions/0.0.11/skills/peer-coms/SKILL.md +90 -0
  254. package/.versions/0.0.11/skills/performance-optimization/SKILL.md +350 -0
  255. package/.versions/0.0.11/skills/planning-and-task-breakdown/SKILL.md +254 -0
  256. package/.versions/0.0.11/skills/security-and-hardening/SKILL.md +461 -0
  257. package/.versions/0.0.11/skills/spec-driven-development/SKILL.md +257 -0
  258. package/.versions/0.0.11/skills/using-agent-skills/SKILL.md +199 -0
  259. package/.versions/0.0.11/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  260. package/.versions/0.0.11/vendor/agent-skills-upstream/LICENSE +21 -0
  261. package/.versions/0.0.11/vendor/agent-skills-upstream/README.md +11 -0
  262. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  263. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  264. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  265. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  266. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  267. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  268. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  269. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  270. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  271. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  272. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  273. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  274. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  275. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  276. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  277. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  278. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  279. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  280. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  281. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  282. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  283. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  284. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  285. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  286. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  287. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  288. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  289. package/.versions/0.0.11/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  290. package/.versions/1.0.0/.pi/agents/dispatch-policy.yaml +32 -0
  291. package/.versions/1.0.0/.pi/agents/model-profiles.yaml +27 -0
  292. package/.versions/1.0.0/.pi/agents/peers.yaml +142 -0
  293. package/.versions/1.0.0/.pi/agents/teams.yaml +41 -0
  294. package/.versions/1.0.0/.pi/damage-control-rules.yaml +297 -0
  295. package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/README.md +57 -0
  296. package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  297. package/.versions/1.0.0/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  298. package/.versions/1.0.0/.pi/extensions/btw/README.md +120 -0
  299. package/.versions/1.0.0/.pi/extensions/btw/index.ts +914 -0
  300. package/.versions/1.0.0/.pi/extensions/btw/package.json +6 -0
  301. package/.versions/1.0.0/.pi/extensions/btw/state.js +179 -0
  302. package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
  303. package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  304. package/.versions/1.0.0/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  305. package/.versions/1.0.0/.pi/extensions/compact-and-continue/README.md +42 -0
  306. package/.versions/1.0.0/.pi/extensions/compact-and-continue/index.ts +120 -0
  307. package/.versions/1.0.0/.pi/extensions/compact-and-continue/package.json +6 -0
  308. package/.versions/1.0.0/.pi/extensions/mcp-bridge/README.md +46 -0
  309. package/.versions/1.0.0/.pi/extensions/mcp-bridge/index.ts +206 -0
  310. package/.versions/1.0.0/.pi/extensions/mcp-bridge/package.json +6 -0
  311. package/.versions/1.0.0/.pi/extensions/package-lock.json +1143 -0
  312. package/.versions/1.0.0/.pi/extensions/package.json +9 -0
  313. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/README.md +205 -0
  314. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/config.ts +198 -0
  315. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  316. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/index.ts +248 -0
  317. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/package.json +6 -0
  318. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  319. package/.versions/1.0.0/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  320. package/.versions/1.0.0/.pi/harnesses/agent-hub/README.md +1056 -0
  321. package/.versions/1.0.0/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  322. package/.versions/1.0.0/.pi/harnesses/agent-hub/artifacts.js +146 -0
  323. package/.versions/1.0.0/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  324. package/.versions/1.0.0/.pi/harnesses/agent-hub/backend-policy.js +174 -0
  325. package/.versions/1.0.0/.pi/harnesses/agent-hub/context-window.js +106 -0
  326. package/.versions/1.0.0/.pi/harnesses/agent-hub/delegate.ts +435 -0
  327. package/.versions/1.0.0/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  328. package/.versions/1.0.0/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
  329. package/.versions/1.0.0/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  330. package/.versions/1.0.0/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  331. package/.versions/1.0.0/.pi/harnesses/agent-hub/footer.ts +35 -0
  332. package/.versions/1.0.0/.pi/harnesses/agent-hub/helpers.ts +266 -0
  333. package/.versions/1.0.0/.pi/harnesses/agent-hub/index.ts +9279 -0
  334. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  335. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  336. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  337. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  338. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  339. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  340. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  341. package/.versions/1.0.0/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
  342. package/.versions/1.0.0/.pi/harnesses/agent-hub/package.json +7 -0
  343. package/.versions/1.0.0/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
  344. package/.versions/1.0.0/.pi/harnesses/agent-hub/posture.ts +103 -0
  345. package/.versions/1.0.0/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  346. package/.versions/1.0.0/.pi/harnesses/agent-hub/research-retention.js +34 -0
  347. package/.versions/1.0.0/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  348. package/.versions/1.0.0/.pi/harnesses/agent-hub/return-contract.js +293 -0
  349. package/.versions/1.0.0/.pi/harnesses/agent-hub/return-extract.js +75 -0
  350. package/.versions/1.0.0/.pi/harnesses/agent-hub/review-findings.js +102 -0
  351. package/.versions/1.0.0/.pi/harnesses/agent-hub/run-budget.js +479 -0
  352. package/.versions/1.0.0/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  353. package/.versions/1.0.0/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  354. package/.versions/1.0.0/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  355. package/.versions/1.0.0/.pi/harnesses/agent-hub/session-health.js +110 -0
  356. package/.versions/1.0.0/.pi/harnesses/agent-hub/spawn.ts +354 -0
  357. package/.versions/1.0.0/.pi/harnesses/agent-hub/version.ts +42 -0
  358. package/.versions/1.0.0/.pi/harnesses/ask-user-remote/README.md +53 -0
  359. package/.versions/1.0.0/.pi/harnesses/ask-user-remote/index.ts +477 -0
  360. package/.versions/1.0.0/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  361. package/.versions/1.0.0/.pi/harnesses/coms/README.md +100 -0
  362. package/.versions/1.0.0/.pi/harnesses/coms/index.ts +1767 -0
  363. package/.versions/1.0.0/.pi/harnesses/coms/package.json +7 -0
  364. package/.versions/1.0.0/.pi/harnesses/coms/version.ts +42 -0
  365. package/.versions/1.0.0/.pi/harnesses/damage-control-continue/README.md +124 -0
  366. package/.versions/1.0.0/.pi/harnesses/damage-control-continue/index.ts +536 -0
  367. package/.versions/1.0.0/.pi/harnesses/damage-control-continue/package.json +7 -0
  368. package/.versions/1.0.0/.pi/harnesses/damage-control-continue/version.ts +42 -0
  369. package/.versions/1.0.0/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  370. package/.versions/1.0.0/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  371. package/.versions/1.0.0/.pi/harnesses/lib/fleet-dashboard-ops.ts +118 -0
  372. package/.versions/1.0.0/.pi/harnesses/lib/fleet-dashboard-view.ts +140 -0
  373. package/.versions/1.0.0/.pi/harnesses/lib/fleet-detail-view.ts +43 -0
  374. package/.versions/1.0.0/.pi/harnesses/lib/fleet-overlay.ts +26 -0
  375. package/.versions/1.0.0/.pi/harnesses/lib/fleet-panel.ts +34 -0
  376. package/.versions/1.0.0/.pi/harnesses/lib/fleet-read-model.ts +131 -0
  377. package/.versions/1.0.0/.pi/harnesses/lib/fleet-selection.ts +24 -0
  378. package/.versions/1.0.0/.pi/harnesses/lib/herdr-client.ts +472 -0
  379. package/.versions/1.0.0/.pi/harnesses/lib/herdr-presence.ts +399 -0
  380. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  381. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  382. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  383. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  384. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  385. package/.versions/1.0.0/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  386. package/.versions/1.0.0/.pi/harnesses/lib/spawned-peers.js +190 -0
  387. package/.versions/1.0.0/.pi/harnesses/package-lock.json +2046 -0
  388. package/.versions/1.0.0/.pi/harnesses/package.json +10 -0
  389. package/.versions/1.0.0/.pi/prompts/af-build.md +24 -0
  390. package/.versions/1.0.0/.pi/prompts/af-code-simplify.md +22 -0
  391. package/.versions/1.0.0/.pi/prompts/af-plan.md +16 -0
  392. package/.versions/1.0.0/.pi/prompts/af-review.md +16 -0
  393. package/.versions/1.0.0/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  394. package/.versions/1.0.0/.pi/prompts/af-ship.md +17 -0
  395. package/.versions/1.0.0/.pi/prompts/af-spec.md +15 -0
  396. package/.versions/1.0.0/.pi/prompts/af-test.md +19 -0
  397. package/.versions/1.0.0/.pi/skills/bowser/SKILL.md +145 -0
  398. package/.versions/1.0.0/.version +1 -0
  399. package/.versions/1.0.0/agents/architect.md +24 -0
  400. package/.versions/1.0.0/agents/bowser.md +27 -0
  401. package/.versions/1.0.0/agents/builder.md +54 -0
  402. package/.versions/1.0.0/agents/code-reviewer.md +208 -0
  403. package/.versions/1.0.0/agents/deep-researcher.md +32 -0
  404. package/.versions/1.0.0/agents/documenter.md +18 -0
  405. package/.versions/1.0.0/agents/orchestrator.md +72 -0
  406. package/.versions/1.0.0/agents/plan-reviewer.md +83 -0
  407. package/.versions/1.0.0/agents/planner.md +70 -0
  408. package/.versions/1.0.0/agents/releaser.md +24 -0
  409. package/.versions/1.0.0/agents/researcher.md +28 -0
  410. package/.versions/1.0.0/agents/security-auditor.md +167 -0
  411. package/.versions/1.0.0/agents/test-engineer.md +153 -0
  412. package/.versions/1.0.0/agents/web-debugger.md +43 -0
  413. package/.versions/1.0.0/agents/web-performance-auditor.md +193 -0
  414. package/.versions/1.0.0/codex/CONDUCTOR.md +148 -0
  415. package/.versions/1.0.0/docs/ARCHITECTURE.md +337 -0
  416. package/.versions/1.0.0/docs/agent-fleet-setup.md +437 -0
  417. package/.versions/1.0.0/docs/claude-code-coms-bridge.md +128 -0
  418. package/.versions/1.0.0/docs/codex-remote-conductor.md +170 -0
  419. package/.versions/1.0.0/docs/coms-hermes-bridge.md +189 -0
  420. package/.versions/1.0.0/docs/getting-started.md +98 -0
  421. package/.versions/1.0.0/docs/npm-install.md +292 -0
  422. package/.versions/1.0.0/docs/pi-extensions.md +412 -0
  423. package/.versions/1.0.0/docs/pi-setup.md +74 -0
  424. package/.versions/1.0.0/docs/skill-anatomy.md +150 -0
  425. package/.versions/1.0.0/hermes/README.md +347 -0
  426. package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  427. package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  428. package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  429. package/.versions/1.0.0/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  430. package/.versions/1.0.0/hermes/gates/gate-o-capability.md +8 -0
  431. package/.versions/1.0.0/hermes/gates/gate-o-validator-fixtures.json +1 -0
  432. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  433. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  434. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  435. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  436. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  437. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  438. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  439. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  440. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  441. package/.versions/1.0.0/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  442. package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  443. package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  444. package/.versions/1.0.0/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  445. package/.versions/1.0.0/hermes/skills/hub-conductor/SKILL.md +84 -0
  446. package/.versions/1.0.0/hermes/skills/hub-liaison/SKILL.md +84 -0
  447. package/.versions/1.0.0/hermes/skills/hub-watchdog/SKILL.md +76 -0
  448. package/.versions/1.0.0/hermes/skills/hub-watchdog/manifest.json +1 -0
  449. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  450. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  451. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  452. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  453. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  454. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  455. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  456. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  457. package/.versions/1.0.0/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  458. package/.versions/1.0.0/hermes/watchdog-tests/__init__.py +0 -0
  459. package/.versions/1.0.0/hooks/coms-stop-hook.mjs +84 -0
  460. package/.versions/1.0.0/install-manifest.json +2745 -0
  461. package/.versions/1.0.0/justfile +272 -0
  462. package/.versions/1.0.0/manifest-meta.json +882 -0
  463. package/.versions/1.0.0/references/accessibility-checklist.md +160 -0
  464. package/.versions/1.0.0/references/definition-of-done.md +67 -0
  465. package/.versions/1.0.0/references/fleet-coordination-patterns.md +151 -0
  466. package/.versions/1.0.0/references/observability-checklist.md +91 -0
  467. package/.versions/1.0.0/references/orchestration-patterns.md +370 -0
  468. package/.versions/1.0.0/references/performance-checklist.md +153 -0
  469. package/.versions/1.0.0/references/prompting-patterns.md +380 -0
  470. package/.versions/1.0.0/references/security-checklist.md +179 -0
  471. package/.versions/1.0.0/references/testing-patterns.md +236 -0
  472. package/.versions/1.0.0/scripts/codex-conductor.ts +41 -0
  473. package/.versions/1.0.0/scripts/codex-remote-control.ts +167 -0
  474. package/.versions/1.0.0/scripts/coms-claude-bridge.ts +411 -0
  475. package/.versions/1.0.0/scripts/coms-cli.ts +484 -0
  476. package/.versions/1.0.0/scripts/coms-hermes-bridge.ts +413 -0
  477. package/.versions/1.0.0/scripts/fleet.ts +185 -0
  478. package/.versions/1.0.0/scripts/hermes-monitor-capability-runner.ts +25 -0
  479. package/.versions/1.0.0/scripts/hermes-monitor-scenario.ts +474 -0
  480. package/.versions/1.0.0/scripts/hermes-watchdog-capability-probe.ts +45 -0
  481. package/.versions/1.0.0/scripts/install-hermes-plugin.sh +180 -0
  482. package/.versions/1.0.0/scripts/lib/claude-bridge-core.ts +210 -0
  483. package/.versions/1.0.0/scripts/lib/codex-conductor.ts +88 -0
  484. package/.versions/1.0.0/scripts/lib/codex-remote-control.ts +480 -0
  485. package/.versions/1.0.0/scripts/lib/coms-envelope.ts +582 -0
  486. package/.versions/1.0.0/scripts/lib/fake-herdr-server.ts +88 -0
  487. package/.versions/1.0.0/scripts/lib/fleet-command.ts +266 -0
  488. package/.versions/1.0.0/scripts/lib/herdr-layout.ts +281 -0
  489. package/.versions/1.0.0/scripts/lib/hermes-bridge-core.ts +241 -0
  490. package/.versions/1.0.0/scripts/lib/hermes-monitor-events.ts +1 -0
  491. package/.versions/1.0.0/scripts/lib/hermes-monitor-herdr.ts +2 -0
  492. package/.versions/1.0.0/scripts/lib/hermes-monitor-model.ts +3 -0
  493. package/.versions/1.0.0/scripts/lib/hermes-monitor-registry.ts +2 -0
  494. package/.versions/1.0.0/scripts/lib/hermes-monitor-socket.ts +2 -0
  495. package/.versions/1.0.0/scripts/lib/hermes-monitor-store.ts +2 -0
  496. package/.versions/1.0.0/scripts/lib/monitor-env.ts +146 -0
  497. package/.versions/1.0.0/scripts/lib/peer-launch.ts +318 -0
  498. package/.versions/1.0.0/scripts/lib/persona-banner.ts +62 -0
  499. package/.versions/1.0.0/scripts/lib/spawn-stagger.ts +101 -0
  500. package/.versions/1.0.0/scripts/lib/team-project.ts +213 -0
  501. package/.versions/1.0.0/scripts/lib/team-snapshot.ts +147 -0
  502. package/.versions/1.0.0/scripts/peer-banner.ts +40 -0
  503. package/.versions/1.0.0/scripts/peer-launch.ts +259 -0
  504. package/.versions/1.0.0/scripts/team-snapshot.ts +237 -0
  505. package/.versions/1.0.0/scripts/team-up.ts +406 -0
  506. package/.versions/1.0.0/skills/_internal/grilling.md +11 -0
  507. package/.versions/1.0.0/skills/browser-testing-with-devtools/SKILL.md +351 -0
  508. package/.versions/1.0.0/skills/code-review-and-quality/SKILL.md +381 -0
  509. package/.versions/1.0.0/skills/compound-learning/SKILL.md +137 -0
  510. package/.versions/1.0.0/skills/context-engineering/SKILL.md +291 -0
  511. package/.versions/1.0.0/skills/deprecation-and-migration/SKILL.md +206 -0
  512. package/.versions/1.0.0/skills/designing-agents/SKILL.md +394 -0
  513. package/.versions/1.0.0/skills/designing-agents/pi-harness-authoring.md +222 -0
  514. package/.versions/1.0.0/skills/frontend-ui-engineering/SKILL.md +328 -0
  515. package/.versions/1.0.0/skills/git-workflow-and-versioning/SKILL.md +316 -0
  516. package/.versions/1.0.0/skills/idea-refine/SKILL.md +182 -0
  517. package/.versions/1.0.0/skills/idea-refine/examples.md +238 -0
  518. package/.versions/1.0.0/skills/idea-refine/frameworks.md +99 -0
  519. package/.versions/1.0.0/skills/idea-refine/refinement-criteria.md +113 -0
  520. package/.versions/1.0.0/skills/idea-refine/scripts/idea-refine.sh +15 -0
  521. package/.versions/1.0.0/skills/incremental-implementation/SKILL.md +287 -0
  522. package/.versions/1.0.0/skills/interview-me/SKILL.md +226 -0
  523. package/.versions/1.0.0/skills/orchestration-verification/SKILL.md +181 -0
  524. package/.versions/1.0.0/skills/peer-coms/SKILL.md +90 -0
  525. package/.versions/1.0.0/skills/performance-optimization/SKILL.md +350 -0
  526. package/.versions/1.0.0/skills/planning-and-task-breakdown/SKILL.md +254 -0
  527. package/.versions/1.0.0/skills/security-and-hardening/SKILL.md +461 -0
  528. package/.versions/1.0.0/skills/spec-driven-development/SKILL.md +257 -0
  529. package/.versions/1.0.0/skills/using-agent-skills/SKILL.md +199 -0
  530. package/.versions/1.0.0/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  531. package/.versions/1.0.0/vendor/agent-skills-upstream/LICENSE +21 -0
  532. package/.versions/1.0.0/vendor/agent-skills-upstream/README.md +11 -0
  533. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  534. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  535. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  536. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  537. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  538. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  539. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  540. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  541. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  542. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  543. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  544. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  545. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  546. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  547. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  548. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  549. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  550. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  551. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  552. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  553. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  554. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  555. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  556. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  557. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  558. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  559. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  560. package/.versions/1.0.0/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  561. package/CHANGELOG.md +149 -0
  562. package/README.md +117 -79
  563. package/agents/orchestrator.md +1 -1
  564. package/{.versions/0.0.8/skills/guided-workspace-setup/companion-manifest.json → bin/catalog/harness-runtime-closure.json} +2 -0
  565. package/bin/cli.js +289 -359
  566. package/bin/force-patch-changesets.js +18 -2
  567. package/bin/lib/apply.js +86 -32
  568. package/bin/lib/desired.js +87 -0
  569. package/bin/lib/detect-agent.js +22 -38
  570. package/bin/lib/doctor.js +283 -33
  571. package/bin/lib/features.js +78 -0
  572. package/bin/lib/manifest.js +127 -48
  573. package/bin/lib/overrides.js +35 -0
  574. package/bin/lib/personas.js +37 -0
  575. package/bin/lib/plan.js +18 -9
  576. package/bin/lib/purge.js +11 -0
  577. package/bin/lib/reconcile.js +68 -0
  578. package/bin/lib/scan.js +24 -0
  579. package/bin/lib/state.js +25 -1
  580. package/bin/lib/stt-wizard.js +33 -0
  581. package/bin/lib/transaction.js +149 -0
  582. package/bin/lib/tui.js +71 -0
  583. package/bin/lib/verify.js +9 -26
  584. package/bin/snapshot-version.js +3 -6
  585. package/docs/ARCHITECTURE.md +55 -21
  586. package/docs/MIGRATION-agent-fleet.md +222 -0
  587. package/docs/agent-fleet-setup.md +124 -64
  588. package/docs/claude-code-coms-bridge.md +21 -2
  589. package/docs/coms-hermes-bridge.md +1 -1
  590. package/docs/getting-started.md +61 -217
  591. package/docs/npm-install.md +207 -429
  592. package/docs/pi-extensions.md +90 -41
  593. package/docs/pi-setup.md +48 -545
  594. package/hermes/README.md +1 -1
  595. package/install-manifest.json +385 -1255
  596. package/justfile +45 -27
  597. package/manifest-meta.json +544 -134
  598. package/node_modules/pi-ask-user/README.md +43 -5
  599. package/node_modules/pi-ask-user/index.ts +630 -75
  600. package/node_modules/pi-ask-user/package.json +1 -1
  601. package/package.json +5 -11
  602. package/scripts/coms-claude-bridge.ts +10 -0
  603. package/scripts/fleet.ts +107 -90
  604. package/scripts/lib/claude-bridge-core.ts +45 -0
  605. package/scripts/lib/fleet-command.ts +170 -15
  606. package/scripts/lib/monitor-env.ts +27 -1
  607. package/scripts/lib/peer-launch.ts +6 -2
  608. package/scripts/lib/team-project.ts +24 -4
  609. package/scripts/team-up.ts +57 -11
  610. package/skills/designing-agents/SKILL.md +1 -1
  611. package/skills/designing-agents/pi-harness-authoring.md +3 -3
  612. package/.claude/commands/build.md +0 -44
  613. package/.claude/commands/design-agent.md +0 -14
  614. package/.claude/commands/doctor-agent-fleet.md +0 -22
  615. package/.claude/commands/orchestrate.md +0 -112
  616. package/.claude/commands/prime.md +0 -22
  617. package/.claude/commands/set-hermes-watchdog.md +0 -6
  618. package/.claude/commands/setup-agent-fleet.md +0 -17
  619. package/.claude/commands/ship.md +0 -72
  620. package/.claude/commands/webperf.md +0 -32
  621. package/.claude/orchestrate-teams.yaml +0 -24
  622. package/.opencode/commands/af-build.md +0 -17
  623. package/.opencode/commands/af-code-simplify.md +0 -16
  624. package/.opencode/commands/af-compound.md +0 -16
  625. package/.opencode/commands/af-design-agent.md +0 -15
  626. package/.opencode/commands/af-doctor-agent-fleet.md +0 -22
  627. package/.opencode/commands/af-orchestrate.md +0 -112
  628. package/.opencode/commands/af-plan.md +0 -16
  629. package/.opencode/commands/af-prime.md +0 -22
  630. package/.opencode/commands/af-review.md +0 -15
  631. package/.opencode/commands/af-set-hermes-watchdog.md +0 -6
  632. package/.opencode/commands/af-setup-agent-fleet.md +0 -17
  633. package/.opencode/commands/af-ship.md +0 -16
  634. package/.opencode/commands/af-spec.md +0 -16
  635. package/.opencode/commands/af-test.md +0 -21
  636. package/.opencode/commands/af-webperf.md +0 -32
  637. package/.opencode/orchestrate-teams.yaml +0 -24
  638. package/.pi/prompts/af-doctor-agent-fleet.md +0 -22
  639. package/.pi/prompts/af-setup-agent-fleet.md +0 -19
  640. package/.versions/0.0.1/.opencode/commands/af-doctor-agent-fleet.md +0 -15
  641. package/.versions/0.0.1/.opencode/commands/af-setup-agent-fleet.md +0 -15
  642. package/.versions/0.0.1/skills/guided-workspace-setup/SKILL.md +0 -506
  643. package/.versions/0.0.10/.opencode/commands/af-doctor-agent-fleet.md +0 -22
  644. package/.versions/0.0.10/.opencode/commands/af-setup-agent-fleet.md +0 -17
  645. package/.versions/0.0.10/.pi/prompts/af-doctor-agent-fleet.md +0 -22
  646. package/.versions/0.0.10/.pi/prompts/af-setup-agent-fleet.md +0 -19
  647. package/.versions/0.0.10/skills/guided-workspace-setup/SKILL.md +0 -226
  648. package/.versions/0.0.4/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  649. package/.versions/0.0.4/.opencode/commands/af-setup-agent-fleet.md +0 -15
  650. package/.versions/0.0.4/skills/guided-workspace-setup/SKILL.md +0 -535
  651. package/.versions/0.0.4/skills/guided-workspace-setup/companion-manifest.json +0 -33
  652. package/.versions/0.0.5/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  653. package/.versions/0.0.5/.opencode/commands/af-setup-agent-fleet.md +0 -15
  654. package/.versions/0.0.5/skills/guided-workspace-setup/SKILL.md +0 -542
  655. package/.versions/0.0.5/skills/guided-workspace-setup/companion-manifest.json +0 -35
  656. package/.versions/0.0.6/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  657. package/.versions/0.0.6/.opencode/commands/af-setup-agent-fleet.md +0 -15
  658. package/.versions/0.0.6/.pi/prompts/af-doctor-agent-fleet.md +0 -15
  659. package/.versions/0.0.6/.pi/prompts/af-setup-agent-fleet.md +0 -27
  660. package/.versions/0.0.6/skills/guided-workspace-setup/SKILL.md +0 -544
  661. package/.versions/0.0.6/skills/guided-workspace-setup/companion-manifest.json +0 -35
  662. package/.versions/0.0.7/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  663. package/.versions/0.0.7/.opencode/commands/af-setup-agent-fleet.md +0 -15
  664. package/.versions/0.0.7/.pi/prompts/af-doctor-agent-fleet.md +0 -15
  665. package/.versions/0.0.7/.pi/prompts/af-setup-agent-fleet.md +0 -27
  666. package/.versions/0.0.7/skills/guided-workspace-setup/SKILL.md +0 -544
  667. package/.versions/0.0.7/skills/guided-workspace-setup/companion-manifest.json +0 -35
  668. package/.versions/0.0.8/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  669. package/.versions/0.0.8/.opencode/commands/af-setup-agent-fleet.md +0 -15
  670. package/.versions/0.0.8/.pi/prompts/af-doctor-agent-fleet.md +0 -15
  671. package/.versions/0.0.8/.pi/prompts/af-setup-agent-fleet.md +0 -27
  672. package/.versions/0.0.8/skills/guided-workspace-setup/SKILL.md +0 -544
  673. package/.versions/0.0.9/.opencode/commands/af-doctor-agent-fleet.md +0 -17
  674. package/.versions/0.0.9/.opencode/commands/af-setup-agent-fleet.md +0 -15
  675. package/.versions/0.0.9/.pi/prompts/af-doctor-agent-fleet.md +0 -15
  676. package/.versions/0.0.9/.pi/prompts/af-setup-agent-fleet.md +0 -27
  677. package/.versions/0.0.9/skills/guided-workspace-setup/SKILL.md +0 -544
  678. package/bin/lib/bootstrap.js +0 -323
  679. package/bin/lib/transform-persona.js +0 -180
  680. package/docs/opencode-setup.md +0 -281
  681. package/hooks/SIMPLIFY-IGNORE.md +0 -90
  682. package/hooks/hooks.json +0 -14
  683. package/hooks/session-start.sh +0 -74
  684. package/hooks/simplify-ignore.sh +0 -302
  685. package/skills/guided-workspace-setup/SKILL.md +0 -226
  686. /package/.versions/0.0.10/{skills/guided-workspace-setup/companion-manifest.json → bin/catalog/harness-runtime-closure.json} +0 -0
  687. /package/{.opencode/commands → .versions/0.0.11/.pi/prompts}/af-set-hermes-telegram.md +0 -0
  688. /package/.versions/{0.0.9/skills/guided-workspace-setup/companion-manifest.json → 0.0.11/bin/catalog/harness-runtime-closure.json} +0 -0
  689. /package/{.claude/commands/set-hermes-telegram.md → .versions/1.0.0/.pi/prompts/af-set-hermes-telegram.md} +0 -0
  690. /package/{skills/guided-workspace-setup/companion-manifest.json → .versions/1.0.0/bin/catalog/harness-runtime-closure.json} +0 -0
@@ -1,506 +0,0 @@
1
- ---
2
- name: guided-workspace-setup
3
- description: Guides installation of agent-fleet artifacts into a target workspace. Use when onboarding a project to agent-fleet, when installing skills, commands, prompts, personas, or pi extensions for a chosen coding agent, or when a workspace needs its setup files configured.
4
- ---
5
-
6
- # Guided Workspace Setup
7
-
8
- ## Overview
9
-
10
- This skill installs and configures agent-fleet artifacts — skills, agent personas, commands or prompts, pi extensions and harnesses, references, and hooks — into a target workspace for a chosen coding agent. It runs interactively, writes project overrides to the target's `.ai/agent-fleet-overrides.md`, records what it installed in `.ai/agent-fleet-setup.md`, and can be re-run on the same workspace to add, update, or remove artifacts.
11
-
12
- ## When to Use
13
-
14
- - Onboarding a new project or workspace to agent-fleet
15
- - Installing or changing which skills, commands, or personas a workspace uses
16
- - Re-running setup to add, update, or remove already-installed artifacts
17
- - Configuring a workspace's `.ai/agent-fleet-overrides.md`
18
-
19
- **NOT for:** authoring new skills or personas (use `designing-sub-agents`); editing artifacts inside the agent-fleet repo itself; general context or rules-file tuning (use `context-engineering`).
20
-
21
- ## The Workflow
22
-
23
- This skill is run from the agent-fleet repo with the target coding agent active, and invoked with a path to the workspace to configure. Steps are gated — nothing is written to the target workspace until the user confirms in Step 9 — with **one explicit exception**: the `pi-ask-user` bootstrap in Step 5b. When the agent is `pi` and that interaction package is missing, the skill (after its own confirmation) installs it *before* the install menu and asks the user to reload and re-run, so the rest of setup can drive a native multi-select widget instead of a text fallback.
24
-
25
- It maintains two files in the target's `.ai/` directory: `agent-fleet-overrides.md` holds the minimal per-reader overrides that skills and the `agent-hub` harness read on every run/session start, and `agent-fleet-setup.md` holds the install record this skill itself reads on re-runs. The overrides file stays small; the install record absorbs the bulk.
26
-
27
- ### 1. Detect interaction capability
28
-
29
- Determine which interaction mode this runtime supports. The mode is chosen by agent:
30
-
31
- - **`claude-code` → `AskUserQuestion` questionnaires (primary).** Drive every Step 6 group through `AskUserQuestion` rather than printing a table and waiting for a free-text reply. Because the tool caps at 4 options per question and supports `multiSelect: true`, use this two-tier strategy:
32
- - **Quick path first.** For each group, ask one `AskUserQuestion` (multiSelect off) offering `Recommended set` / `Everything` / `Customise` / `Skip group`. Only when the user picks `Customise` do you drill in. This avoids questionnaire fatigue on the ~20-item Skills group.
33
- - **Customise drill-in.** Present the group's items as `AskUserQuestion` multiSelect prompts chunked by sub-category (the existing `Group` column), ≤ 4 options per question; a sub-category with > 4 items splits into sequential questions. Pre-selection still follows the Step 6 state rules (installed → pre-checked).
34
-
35
- The selection semantics are **identical** to the tabular menu (unchecked installed item = remove, `recommended` adds `★` on top, etc.) — only the rendering differs.
36
- - **`pi` → native multi-select widget.** Provided by the external `pi-ask-user` package; when it is absent, Step 5b bootstraps it first (install → reload → re-run) so this mode becomes available on the second pass. Because the Step 6 groups are large, prefer bootstrapping `pi-ask-user` over falling straight to the tabular fallback.
37
- - **`opencode` / any other runtime → native multi-select widget if supplied**, else the tabular fallback below.
38
- - **Tabular fallback** (any runtime lacking the above) — print the group table (Step 6 format) and ask the user to reply with the picks. Always accept the shortcuts `all`, `recommended`, `none`, or a comma-separated list of item names/numbers.
39
-
40
- ### 2. Resolve inputs
41
-
42
- Resolve four things. Accept any already supplied in the invocation (the `npx @chankov/agent-fleet init` CLI passes the first three as flags); otherwise ask.
43
-
44
- - **Source root** — the agent-fleet package. **Resolution priority (use the first that works; never fall through silently):**
45
-
46
- 1. **Bootstrap marker** — read `<workspace>/.ai/.agent-fleet-bootstrap.json` if present. Its `sourceRoot` field is authoritative; the CLI wrote it during `init` and it points at the exact package the user's install came from (npm cache, global install, or symlinked clone). Verify the path still exists and contains a `package.json` whose `name` is `@chankov/agent-fleet`; if so, use it and **stop**. If the path no longer exists (e.g. npx cache was cleaned), warn the user and continue to step 2.
47
- 2. **SKILL.md realpath** — only if the marker is missing. If this `SKILL.md` is a symlink, follow it with `readlink`/`realpath` and use the resolved package root. **Do not** use the SKILL.md's *workspace* location (e.g. `.pi/skills/guided-workspace-setup/`) — bootstrap copies the file there, so that path is the workspace, not the source. The realpath only helps in symlink mode.
48
- 3. **Ask the user explicitly.** Print: *"Source root not found. Run `npx @chankov/agent-fleet@latest init` to bootstrap, or paste an absolute path to the package."* Verify the answer is a directory whose `package.json#name` is `@chankov/agent-fleet`. **Do not scan the user's filesystem** for other agent-fleet repos — that is invasive and produces wrong answers (it will pick up dev clones, forks, or stale copies).
49
-
50
- The install record's `## install-status` may *also* mention an older source root from a previous setup pass; ignore it for resolution. The bootstrap marker overrides it because it reflects what the user just ran. Note the divergence in the Step 9 summary so the user sees the change.
51
-
52
- - **Workspace path** — the target project to configure. Confirm the path exists and is a directory; stop and ask again if it does not.
53
- - **Coding agent** — `claude-code`, `opencode`, or `pi`. Detect the running agent from the runtime, show it to the user, and let them choose a different one.
54
- - **Package version** — read `version` from the source root's `package.json`. This is the version that will be stamped into the install record in Step 10, and the right-hand side of every version-aware diff in Step 6.
55
-
56
- ### 3. Read the agent's setup conventions
57
-
58
- For `opencode` and `pi`, read `docs/<agent>-setup.md` in the source root and follow the install locations and format it documents. For `claude-code`, use the built-in target map below. When the `*-setup.md` doc and the built-in map disagree, the doc wins.
59
-
60
- Target map, relative to the workspace root:
61
-
62
- | Artifact | claude-code | opencode | pi |
63
- |---|---|---|---|
64
- | Skills | `.claude/skills/<name>/` | per `docs/opencode-setup.md` | `.pi/skills/<name>/` |
65
- | Personas | `.claude/agents/<name>.md` *(generated)* | `.opencode/agent/<name>.md` *(generated)* | `agents/<name>.md` |
66
- | Commands / prompts | `.claude/commands/<name>.md` | `.opencode/commands/af-<name>.md` | `.pi/prompts/<name>.md` |
67
- | `/orchestrate` team config *(companion of the `orchestrate` command)* | `.claude/orchestrate-teams.yaml` | `.opencode/orchestrate-teams.yaml` | — |
68
- | References | `.claude/references/<name>.md` | per `docs/opencode-setup.md` | per `docs/pi-setup.md` |
69
- | Hooks *(claude-code only)* | `.claude/hooks/<name>`, registered in `.claude/settings.json` | — | — |
70
- | pi extensions | — | — | `.pi/extensions/<name>/` |
71
- | pi harnesses | — | — | `.pi/harnesses/<name>/` |
72
- | pi harness support | — | — | `justfile` (agent-fleet managed region), `scripts/*.ts`, `.pi/agents/*.yaml`, `.pi/damage-control-rules.yaml`, `.pi/harnesses/package.json` |
73
-
74
- **Personas are generated, not copied.** The canonical persona format in `agents/*.md` is pi-flavored (agent-hub frontmatter: `models`, `thinking`, `delegate_depth`, `subagents`, …). For `pi` the file is installed as-is (copy or symlink). For `claude-code` and `opencode` the install runs the deterministic transformer instead — `node <source-root>/bin/cli.js transform-persona --agent <agent> --workspace <workspace> <name…>` — which translates `tools`/`model` to the target's vocabulary, adds `mode: subagent` for opencode, and drops the agent-hub-only keys. Never transform persona frontmatter by hand in this skill; the mapping lives in `bin/lib/transform-persona.js`, under test. Its `--list` flag prints the per-agent availability matrix (pi-only personas — `bowser`, `web-debugger`, `orchestrator` — are excluded for other agents and must not appear in their menu).
75
-
76
- The **pi harness support** row is not a menu group of its own — it is the set of shared files the harnesses need in order to launch (the `justfile` recipes, the `team-up` script, the peer/team YAML, the damage-control rules, and the harness `package.json` of runtime deps). These travel **with** the pi harnesses group (Step 6, group 6): whenever any harness is installed, refreshed, or removed, this support set is refreshed from source in the same pass. The `justfile` specifically is refreshed from the **current** source, so retired-harness recipes are pruned and new-harness recipes added automatically — see Step 6 and Step 10 for the merge and removal rules.
77
-
78
- When neither the built-in map nor the agent's `*-setup.md` defines a path for a selected artifact, ask the user instead of guessing.
79
-
80
- ### 4. Analyse the workspace
81
-
82
- Scan the workspace to ground the recommendations and the overrides offer:
83
-
84
- - Language, framework, and package manager (`package.json`, `go.mod`, `pyproject.toml`, …)
85
- - Test runner and dev-server command, where discoverable
86
- - Git presence and current branch
87
- - Existing agent directories (`.claude/`, `.opencode/`, `.pi/`)
88
- - Existing `.ai/agent-fleet-setup.md` — read its `## install-status` section to learn what is already installed, **and the `version:` line in `## workspace-summary` to learn which package version performed the install**
89
- - An existing `.ai/agent-fleet-setup.md` (or any populated agent directory) means this workspace has prior state — flag it for Step 5
90
-
91
- **Version delta.** Compare the recorded `version:` against the package version from Step 2:
92
-
93
- - Missing `version:` → workspace is **pre-versioning**. Prompt the user: "This workspace was set up before agent-fleet used semver. Stamp it as `v<current>` (assume installed copies match the current source), or wipe and reinstall?" Do not run the three-way diff for pre-versioning workspaces — there is no recorded baseline.
94
- - Recorded `version:` equals current → no version-driven menu changes; Step 6 only surfaces content-level drift.
95
- - Recorded `version:` differs from current → load `CHANGELOG.md` between the two versions, and load the `.versions/<recorded>/` snapshot from the source root. Both feed Step 6.
96
-
97
- Report a short summary of the findings before continuing.
98
-
99
- ### 5. Doctor preflight (existing setup only)
100
-
101
- If Step 4 found prior state — `.ai/agent-fleet-setup.md` exists **or** any of the install-target directories already contains skills/personas/commands — run the Doctor scan now, **before** showing the install menu. A fresh workspace skips this step.
102
-
103
- Walk every install-target directory the chosen agent uses and look for **broken symlinks** — links whose source has been moved, renamed, or deleted. Directories to check, when present:
104
-
105
- - `agents/`, `.claude/agents/`, `.opencode/agent/`, `.opencode/agents/` (legacy), `.pi/agents/`
106
- - `.claude/skills/`, `.opencode/skills/`, `.pi/skills/`, `.agents/skills`
107
- - `.claude/commands/`, `.opencode/commands/`, `.pi/prompts/`
108
- - `.claude/references/`, `.claude/hooks/`
109
-
110
- For each broken link discovered:
111
-
112
- 1. Resolve where the link **was** pointing (`readlink`) and look up the canonical replacement in the source `agents/` or `skills/` tree — many breakages are stale names from the pre-merge layout (e.g. `reviewer` → `code-reviewer`, `red-team` → `security-auditor`).
113
- 2. If a canonical replacement exists, offer to repair it. For persona links under `.claude/agents/` or `.opencode/agent(s)/` the repair **regenerates a transformed copy** (`transform-persona`) — never a raw symlink into the source; everywhere else it repoints the symlink.
114
- 3. If no replacement exists, offer to delete the broken link.
115
- 4. Never overwrite a regular file you find at a target path — only act on symlinks whose target is missing.
116
-
117
- Also flag any YAML configs (`teams.yaml`, `peers.yaml`) that still reference removed persona names, and offer to rename the references to the canonical name.
118
-
119
- Also flag malformed peer entries in `.pi/agents/peers.yaml`: field lines (`persona:`, `model:`, ...) sitting under a team heading before any `- name: ...` list item — the team-up launcher's minimal parser silently drops them, so the peer never spawns. **Advisory only**: report with the missing `- name: <peer>` suggestion, never rewrite the file yourself. (`agent-fleet doctor` runs this same check.)
120
-
121
- Also validate `.ai/agent-fleet-overrides.md` when it exists, against the schema in `docs/agent-fleet-setup.md`: unknown sections, unknown keys in known sections, invalid values for the mechanically parsed `agent-hub` keys (`thinking.*` levels, `delegate-depth.*`, `persona-gate`), `rules:` folders and `docs:` entry points that don't exist, and `## env` `required:` names that are neither set nor declared in the root `.env`. These findings are **advisory only** — report them in the table with fix "edit by hand", never edit the overrides file yourself. (`agent-fleet doctor` runs this same validation.)
122
-
123
- Present findings in a single table (keep it narrow — same widget constraint as Step 6/9: short `Issue`/`Fix` phrases, paths relative to the workspace, no overflowing cells):
124
-
125
- | # | Path | Issue | Fix |
126
- |---|---|---|---|
127
- | 1 | `.claude/agents/reviewer.md` | broken link → missing `reviewer.md` | repoint → `code-reviewer.md` |
128
- | 2 | `.pi/agents/red-team.md` | broken link, no replacement | delete |
129
- | 3 | `.pi/agents/teams.yaml` | refs `red-team` | rename → `security-auditor` |
130
-
131
- Then ask, multi-select: which fixes to apply now. Apply only the picked ones; record skipped items so the install menu can surface them again. Append a `## doctor-runs` line to `.ai/agent-fleet-setup.md` with the date, agent, phase (`preflight`), and `repaired` / `deleted` / `skipped` counts.
132
-
133
- The doctor scan is also exposed standalone as `/doctor-agent-fleet` — running it outside a setup pass is this same scan-and-repair flow without the rest of the install menu.
134
-
135
- ### 5b. Bootstrap `pi-ask-user` first (pi only)
136
-
137
- **Skip this step entirely unless the agent is `pi`.** For `claude-code` and `opencode`, the runtime already supplies a multi-select widget — go straight to Step 6.
138
-
139
- For `pi`, the native multi-select widget comes from the external `pi-ask-user` package. The Step 6 groups are large (the Skills group alone is ~20 rows), so driving them through the tabular fallback is clumsy. The fix is to install the interaction tool *before* the menu, then re-enter setup once it is loaded.
140
-
141
- From the Step 4 analysis, determine whether `pi-ask-user` is already available:
142
-
143
- - **Available** — bundled by `@chankov/agent-fleet`, recorded as a project package in `.pi/settings.json` / `pi list`, or provided globally by user settings. Then this step is a no-op: note "interaction widget present" and proceed to Step 6, which will use the native widget.
144
- - **Not available** — do the bootstrap:
145
- 1. Tell the user what is about to happen and why: *"`pi` renders the setup menu best with the `pi-ask-user` widget. I'll install it project-scoped, then you reload and re-run setup so the rest of the menu uses real checkboxes."*
146
- 2. Ask for confirmation (this is the one pre-Step-9 write, per the gating exception). If declined, fall back to the tabular mode and continue to Step 6 in this same pass — do **not** force the install.
147
- 3. On confirm, run `pi install -l npm:pi-ask-user` (project-scoped). Mention `pi install npm:pi-ask-user` only if the user explicitly wants a global pin.
148
- 4. Record the package under the `external-pi-packages` / `project-packages` line in `.ai/agent-fleet-setup.md` (same convention as Step 6's external-package handling) — do not copy files from `node_modules`.
149
- 5. **Stop the pass here.** Print: *"`pi-ask-user` installed. Reload pi (restart the session or `/reload`), then re-run `/setup-agent-fleet` — the menu will then use native multi-select. Nothing else has been written to your workspace."* Do not continue to Step 6 on this pass: the tool only becomes callable after the reload.
150
-
151
- On the **re-run**, Step 4 finds `pi-ask-user` installed, this step is a no-op, and Step 6 renders every group as a true checkbox widget. In Step 6's External-pi-packages group, the already-installed `pi-ask-user` simply shows `installed · project package` and is pre-checked to keep — the bootstrap is not repeated. Do **not** bootstrap other external pi packages here; optional suggestions such as `pi-codex-image-gen` are offered only in Group 7 and installed only when the user selects them.
152
-
153
- ### 6. Present the install menu
154
-
155
- Offer every installable artifact, split into the groups below. **Each group is its own multi-select prompt** so the user picks one screen at a time. On `claude-code` (per Step 1) each group is rendered as `AskUserQuestion` questionnaire chunks (quick-path, then ≤ 4-option drill-in) rather than one wide table — but the **selection semantics are identical** (unchecked installed item = remove, `recommended` adds `★` on top, etc.). The groups are deliberately broad — 7 total (4 shared + 3 pi-only), so a non-`pi` workspace sees only 4 screens. Several groups bundle more than one artifact type; within such a group, a leading `Group` column labels the sub-category and rows are ordered by it so the table still reads as labeled sections. Render every group's items as a markdown table using this fixed format:
156
-
157
- | Pick | Item | Group | St | Purpose |
158
- |---|---|---|---|---|
159
- | `[x]` / `[ ]` | `<name>` (append ` ★` when recommended) | sub-category (see each group) — omit the column for single-type groups | short status token (see legend) | one-line purpose, ≤ ~6 words |
160
-
161
- **Keep it narrow.** The `pi-ask-user` widget renders the table at fixed column widths, so wide cells force horizontal overflow — the user then has to zoom out, which makes the widget re-render and flicker. Render compact so the whole table fits a standard terminal width:
162
-
163
- - Use the short `St` token, never the long state name. Print the legend once, on a single line above the table: `St: ok=up to date · upd=update available · mod=modified locally · cflt=conflicting upgrade · gone=removed upstream · new=new this version · pkg=project package · — =not installed · brk=broken`.
164
- - Fold the recommendation mark into `Item` (append ` ★`) — do **not** add a separate `Rec` column.
165
- - Keep `Purpose` to a short phrase (truncate with `…` if needed); keep `Group` labels short (`UI`, `focus`, `safety`, `orch`, `msg`, `ext`, `skill`, `ref`, `hook`, `rw`, `ro`).
166
- - Keep the context preamble and the after-table prompt to short single lines — no multi-clause sentences that overflow the terminal.
167
-
168
- **Pre-selection rule.** The `Pick` column is pre-ticked from the workspace's current state — not from preference. Every item is either pre-checked `[x]` (touched if confirmed) or pre-unchecked `[ ]` (left alone if confirmed):
169
-
170
- | Current state | `St` token | Pre-check | What confirming will do |
171
- |---|---|---|---|
172
- | `installed · up to date` | `ok` | `[x]` | no-op (kept as-is) |
173
- | `installed · outdated` (source newer than the installed copy; copy-mode only) | `upd` | `[x]` | refresh to current source |
174
- | `installed · modified` (target diverged from source) | `mod` | `[x]` | refresh from source — **local edits will be overwritten**; untick to preserve them |
175
- | `installed · upgrade available` (recorded version != current; user copy still matches the recorded-version source) | `upd` | `[x]` | clean refresh to the current-version source |
176
- | `installed · conflicting upgrade` (recorded version != current; user modified the copy AND source changed upstream) | `cflt` | `[ ]` | nothing — show the three-way diff (recorded vs installed vs current) inline and ask before any write; tick only after the user accepts the overwrite |
177
- | `installed · removed upstream` (artifact gone in the current version) | `gone` | `[x]` | propose deletion in Step 10 (subject to the removal-scope rule); untick to keep the local copy |
178
- | `not installed` | `—` | `[ ]` | nothing — unless the user ticks it to install |
179
- | `not installed · new in this version` (artifact added between recorded and current) | `new` | `[ ]` | nothing — unless the user ticks it; marked `★` if recommended |
180
- | `broken · skipped in preflight` (carried over from Step 5) | `brk` | `[ ]` | remove the dangling link in Step 10; tick it to attempt repair instead |
181
- | `not installed · ★ recommended` | `—` | `[ ]` | nothing — unless the user ticks it or replies `recommended` |
182
-
183
- **The three-way diff for `conflicting upgrade`.** For each row in that state, compare:
184
-
185
- - *source @ recorded* — read from `<source-root>/.versions/<recorded-version>/<artifact-path>`
186
- - *installed copy* — read from the target path in the workspace
187
- - *source @ current* — read from `<source-root>/<artifact-path>`
188
-
189
- If the recorded snapshot is missing (unpublished local build, or a version older than the snapshot retention), fall back to "treat installed copy as canonical" — do not pretend a diff exists. Mention the missing snapshot in the row's status text so the user can decide.
190
-
191
- After the table, ask: *"Which items in this group? — adjust the picks, or reply `all` / `recommended` / `none` / `keep` (keep the pre-selection as shown)."* `recommended` ticks every `★` item **in addition to** the already-installed pre-selection (so the user never accidentally removes installed items by accepting recommendations). `keep` is the no-change shortcut.
192
-
193
- For an already-configured workspace, an **unchecked installed item means *remove it*** (subject to the removal-scope rule); a **checked one means *keep or update it***. An `St` token appears for every row — even `—` (not installed) — with the legend shown once above the table, so the user always sees an explicit state instead of inferring it from an empty checkbox.
194
-
195
- **Source availability filter — never substitute across agents.** Each row is offered only when the source file the **chosen agent** needs already exists in this repo. The source location is fixed per agent:
196
-
197
- | Artifact | claude-code source | opencode source | pi source |
198
- |---|---|---|---|
199
- | Skills | `skills/<name>/SKILL.md`, else `vendor/agent-skills-upstream/skills/<name>/SKILL.md` | `skills/<name>/SKILL.md`, else `vendor/agent-skills-upstream/skills/<name>/SKILL.md` | `skills/<name>/SKILL.md`, else `vendor/agent-skills-upstream/skills/<name>/SKILL.md` |
200
- | Personas | `agents/<name>.md` | `agents/<name>.md` | `agents/<name>.md` |
201
- | Commands / prompts | `.claude/commands/<name>.md` | `.opencode/commands/af-<name>.md` | `.pi/prompts/<name>.md` |
202
- | `/orchestrate` team config | `.claude/orchestrate-teams.yaml` | `.opencode/orchestrate-teams.yaml` | — |
203
- | pi extensions / harnesses / runtime skills | — | — | `.pi/extensions/<name>/`, `.pi/harnesses/<name>/`, `.pi/skills/<name>/` |
204
- | References | source files in `references/` (all agents) |
205
- | Hooks | source files in `hooks/` | — | — |
206
-
207
- If the per-agent source is missing, the row is **not shown** — never silently fall back to a different agent's tree (for example: do not symlink `.claude/commands/design-agent.md` from `.pi/prompts/design-agent.md` when the agent is `pi`). When the user explicitly asks for an item the source lacks for their agent, say so plainly and stop; the answer is to author the missing source file first, not to cross-link runtimes.
208
-
209
- Groups, in order. Groups 1–4 apply to every agent; groups 5–7 are shown **only when the agent is `pi`**.
210
-
211
- 1. **Skills** *(`Group` column = lifecycle phase)* — one screen for all skills, ordered by phase. The catalogue spans **two skill roots**: fleet-native `skills/` and the vendored upstream import `vendor/agent-skills-upstream/skills/` (see `docs/UPSTREAM-SKILLS.md`). When the same name exists in both, **the native `skills/` copy wins** and the vendored one is never offered as a separate row; names that exist only in the vendor root are offered from there. Record the resolved source root per skill in the install record so `doctor` and `update` know which copy (and which upstream commit) a workspace got:
212
- - *Define / Plan* — `spec-driven-development` ★, `planning-and-task-breakdown` ★, `idea-refine`
213
- - *Build* — `incremental-implementation` ★, `test-driven-development` ★, `context-engineering`, `source-driven-development`, `frontend-ui-engineering`, `api-and-interface-design`
214
- - *Verify* — `browser-testing-with-devtools`, `debugging-and-error-recovery` ★
215
- - *Review* — `code-review-and-quality` ★, `code-simplification`, `security-and-hardening`, `performance-optimization`
216
- - *Ship* — `git-workflow-and-versioning` ★, `ci-cd-and-automation`, `deprecation-and-migration`, `documentation-and-adrs`, `shipping-and-launch`
217
- - *Orchestrate* — `orchestration-verification` ★ *(the Verification Contract enforced by the `orchestrator` persona + agent-hub harness; also read by the `builder`/`test-engineer`/`code-reviewer` personas for their structured returns, so recommend it whenever any of those personas or the `orchestrate` command is selected)*
218
- - *Learn* — `compound-learning` ★ *(the end-of-session compound pass — session lessons landed as deduped, capped diffs on the project's `rules:`/`docs:` targets; read by the `documenter` persona for `/compound` dispatches and by the `compound` command, so recommend it whenever either of those is selected)*
219
- - *Meta* — `using-agent-skills` ★, `designing-agents` *(`guided-workspace-setup` is installer-only — never offered)*
220
-
221
- **Internal skill companions.** `skills/_internal/grilling.md` is not a menu row and has no `SKILL.md`; it is a shared helper for `idea-refine`, `spec-driven-development`, and `planning-and-task-breakdown`. Whenever any of those three skills is installed, kept, refreshed, or removed, apply the helper as a sibling at `<skills-target>/_internal/grilling.md` using the same copy/symlink method, record it as a companion rather than a selected skill, and keep it while any installed parent skill still references it.
222
-
223
- 2. **Agent personas** *(`Group` column = `rw` / `ro` / `pi-only`)* — one screen listing the **full availability matrix** for the chosen agent (never a hardcoded subset; `transform-persona --list --agent <agent>` is the authoritative roster). Read-only personas carry a read-only toolset and an explicit "Do NOT modify files." rule:
224
- - *rw* — `builder` ★, `test-engineer` ★, `documenter`, `planner` *(scoped: writes only the plan document in the plan directory; bash limited to read-only git inspection)*, `architect`, `releaser`
225
- - *ro* — `code-reviewer` ★, `security-auditor`, `plan-reviewer`, `researcher`, `deep-researcher`
226
- - *pi-only* *(shown only when the agent is `pi`)* — `bowser`, `web-debugger`, `orchestrator`
227
-
228
- For `claude-code`/`opencode`, installed rows are **generated artifacts** (see Step 3): record them with `transformed: true` in `## install-status`, and compute their status by comparing the installed file against `transform(current source)` — and for upgrades against `transform(.versions/<recorded>/agents/<name>.md)` — never against the raw canonical source, whose bytes legitimately differ from the generated output.
229
- 3. **Commands / prompts** *(single-type — no `Group` column)* — mapped to the chosen agent; items without a per-agent source are filtered out, no cross-tool substitution. Full candidate list: `spec` ★, `plan` ★, `build` ★, `test` ★, `review` ★, `orchestrate` ★, `compound`, `code-simplify`, `ship`, `design-agent`, `prime`. The actual menu shows only items whose per-agent source file exists — for example, `.pi/prompts/design-agent.md` and `.pi/prompts/prime.md` are absent, so neither is offered when the agent is `pi`; and `orchestrate` has a source for `claude-code` (`.claude/commands/orchestrate.md`) and `opencode` (`.opencode/commands/af-orchestrate.md`) but **not** `pi` (no `.pi/prompts/orchestrate.md`), so the existing source-availability filter surfaces it for claude-code + opencode and hides it for pi automatically. `compound` follows the same pattern (`.claude/commands/compound.md` / `.opencode/commands/af-compound.md`, no pi prompt — the agent-hub harness ships its own `/compound` command); when `compound` is selected, recommend the `compound-learning` skill alongside it. *(`setup` and `doctor` are installer-only — never offered, since they live in the source agent-fleet repo and act on target workspaces from there.)*
230
-
231
- **`orchestrate` carries a team-config companion.** `orchestrate-teams.yaml` (the named-team roster the `/orchestrate` command reads) is not its own menu row — it is a companion of the `orchestrate` command (same idea as the pi harness `justfile` companion). Whenever `orchestrate` is installed/kept/removed, install/remove the agent's team config from source in the same pass — `.claude/orchestrate-teams.yaml` for claude-code, `.opencode/orchestrate-teams.yaml` for opencode. Treat it as a normal versioned artifact for the Step 6 status tokens: a user-edited copy is `mod`/`cflt` and gets the three-way-diff treatment, never a silent clobber of their team definitions. **Removal safety:** when `orchestrate` is removed, the team config is removed **only** if it still matches the shipped source (unedited); a user-edited `orchestrate-teams.yaml` is preserved and listed under "Skipped — user-modified" rather than deleted, so custom team definitions survive an uninstall.
232
- 4. **References & Hooks** *(`Group` column = `reference` / `hook`)* — one screen for the shared non-agent-specific artifacts:
233
- - *reference* — testing, performance, security, accessibility checklists *(offered for every agent)*
234
- - *hook* — `session-start.sh`, `simplify-ignore.sh` (+ `simplify-ignore-test.sh`) *(**claude-code only** — hooks register into `.claude/settings.json`, and neither `docs/opencode-setup.md` nor `docs/pi-setup.md` defines a hook install path)*
235
-
236
- The **hook** sub-category is shown only when the agent is `claude-code`. For `opencode`/`pi` this group degrades to **References only** — no hook rows.
237
- 5. **pi extensions & runtime skills** *(pi only; `Group` column = `extension` / `runtime-skill`)* — always-on once installed:
238
- - *extension* — `mcp-bridge`, `chrome-devtools-mcp`, `compact-and-continue`, `agent-fleet-update-check` ★, `btw`, `pi-voice-stt`
239
- - *runtime-skill* — `bowser`
240
-
241
- **Two complementary browser stacks.** `bowser` (runtime-skill, here) and `chrome-devtools-mcp` (extension, here) cover different browser needs and pair well — `bowser`/`playwright-cli` for headless, parallel, delegatable automation; `chrome-devtools-mcp` (driven by the `web-debugger` persona in group 2) for interactive headful debugging with live DOM/console/network. When the user wants full browser coverage, recommend both; when they only want one, fit it to the use case (automation vs interactive debug). See `docs/pi-extensions.md` ("Two browser stacks — when to use which").
242
-
243
- **`bowser` external CLI dependency.** The `bowser` runtime-skill drives the external **Playwright Agent CLI** (`playwright-cli`), which is **not** an agent-fleet artifact and is not copied from this repo (same idea as the `pi-ask-user` external package). Whenever `bowser` is ticked (installed or kept), check whether `playwright-cli` is on `PATH` (`playwright-cli --help`, or `npx playwright-cli --help`). If it is missing, tell the user and offer the install — `npm install -g @playwright/cli@latest` (global) or note the `npx playwright-cli` ad-hoc fallback — then surface it in the Step 9 plan as an external dependency, not a file write. Record it under the same `external-pi-packages` / `project-packages` convention in `.ai/agent-fleet-setup.md` so re-runs re-verify it. Do not silently install a global package without the user's confirmation, and never block the `bowser` install on it — a missing CLI is a warning, not a hard stop. Install reference: <https://playwright.dev/agent-cli/installation>.
244
-
245
- **`pi-voice-stt` provider configuration.** The `pi-voice-stt` extension (Alt+S voice dictation) is a **gated no-op until a provider is configured** — installing the files alone binds no hotkey. Whenever it is ticked (installed or kept) **and** the workspace has no `.ai/stt.json` yet, offer (don't force) to configure it now; the user may skip and run `/stt doctor` later. The config write is a **companion** of the extension (same idea as the `orchestrate-teams.yaml` companion), applied in Step 10, not a separate menu row. When the user opts in, ask the provider:
246
- - **Azure Speech** (`type: azure`) — collect the resource endpoint and (optionally) candidate `locales` for per-phrase language identification, e.g. `["bg-BG","en-US"]`. Default env var names: `AZURE_SPEECH_KEY`, `AZURE_SPEECH_ENDPOINT`.
247
- - **Azure OpenAI Whisper** (`type: azure-openai`) — Whisper on Azure OpenAI / Azure AI Foundry; best for mixed-language speech. Collect the resource `endpoint` and the Whisper `deployment` name, plus `apiVersion` (default `2024-10-21`). **Use the legacy data-plane host `https://<resource>.openai.azure.com` (or `…cognitiveservices.azure.com`), not the Foundry `…services.ai.azure.com` host** — audio transcription 404s on the Foundry `/openai/v1` endpoint. Default env vars: `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT` — but a multi-service Azure AI Services resource can reuse the Speech key, so offer `apiKeyEnv: AZURE_SPEECH_KEY` when the user says the key is shared.
248
- - **OpenAI-compatible** (`type: openai`) — collect `baseUrl` (default `https://api.openai.com/v1`; a `http://127.0.0.1:*/v1` loopback is allowed for local whisper) and `model` (default `whisper-1`). Default env var: `OPENAI_API_KEY`.
249
-
250
- Then write **two** things in the target repo, following the project-file convention (config references env-var **names**; secrets live in a gitignored `.env`):
251
- 1. `<workspace>/.ai/stt.json` — the non-secret config (`type`, `language`, `model`/`baseUrl`/`endpoint`/`locales`, and `apiKeyEnv`). **Never** write a key value here. The extension reads this project-local file ahead of the global `~/.pi/agent/stt.json`.
252
- 2. `<workspace>/.env` (repo root, auto-loaded by the `justfile`'s `dotenv-load`) — append the referenced secret variables as **empty placeholders** only if absent (`AZURE_SPEECH_KEY=`, `AZURE_SPEECH_ENDPOINT=`, or `OPENAI_API_KEY=`); never overwrite an existing value, and tell the user to fill them in. Ensure `.env` is gitignored — add a `.env` line to the workspace `.gitignore` if no `.env`/`.env*` rule already covers it.
253
-
254
- Record `.ai/stt.json` (and the `.env` keys touched) in `## install-status`. On a later removal of `pi-voice-stt`, delete `.ai/stt.json` **only** if it still matches what setup wrote (unedited; a user-edited config is preserved and listed under "Skipped — user-modified"), and **never** delete `.env`, its values, or the `.gitignore` line. Secrets in `.env` outlive the extension.
255
- 6. **pi harnesses** *(pi only; `Group` column = harness category — install many, load through the explicit recipes; `just hub` stacks `damage-control-continue` + `ask-user-remote` before `agent-hub`)* — one screen for all harnesses:
256
- - *orchestration* — `agent-hub`, `ask-user-remote`
257
- - *safety* — `damage-control`, `damage-control-continue`
258
- - *messaging* — `coms`
259
-
260
- **Mandatory pairing: `agent-hub` ⇒ `damage-control` + `damage-control-continue` + `ask-user-remote`.** When `agent-hub` is ticked (installed or kept), auto-tick **both** damage-control variants and `ask-user-remote` in the same pass and refuse to untick any of them while `agent-hub` stays selected — explain that the hub's `just hub` main session loads `damage-control-continue` and `ask-user-remote` before `agent-hub` (so recipes pointing at missing harnesses would fail to launch or lose the `ask_user` handoff path), and the hub re-loads a guardrail into every spawned subagent as their only protection: `damage-control` (hard-stop) into specialists, `damage-control-continue` into research helpers. Removing either guardrail leaves part of the session unguarded; removing `ask-user-remote` makes agent-hub's `askUserAvailable` probe omit `ask_user` from the dispatcher tools. These harnesses without `agent-hub` remain freely selectable.
261
-
262
- **Harness companions (refreshed with the group, not separate rows).** A harness directory does not run on its own — the launch recipes live in the `justfile`, and several harnesses shell out to support files. So whenever **any** harness in this group is ticked (installed/kept) or unticked (removed), refresh its companions from source in the same pass — they are not shown as their own menu rows:
263
- - `justfile` — the `just hub` / `just team-up` / `just conductor` / `just safe-coms` launch recipes plus private helpers.
264
- - `scripts/team-up.ts` — used by the `team-up` recipe.
265
- - `.pi/agents/peers.yaml`, `.pi/agents/teams.yaml`, and the peer personas they name (e.g. `architect`, `releaser`) — read by `team-up`.
266
- - `.pi/damage-control-rules.yaml` — the rule set the damage-control harness loads.
267
- - `.pi/harnesses/package.json` (+ `npm install --prefix .pi/harnesses`) — the harness runtime deps (`yaml`, `@sinclair/typebox`).
268
-
269
- **The `justfile` is the one that goes stale on upgrade.** Refresh it from the **current** source, never leave the installed copy as-is: the source `justfile` is canonical, so refreshing it prunes recipes for harnesses retired since the recorded version and adds recipes for new ones. A workspace whose harness set changed between versions but whose `justfile` was left untouched is the exact failure this rule prevents — `just --list` keeps recipes pointing at deleted `.pi/harnesses/<name>/` dirs and lacks recipes for the new harnesses. Treat the `justfile` as a normal versioned artifact subject to the Step 6 status rules: it carries its own `St` token in the menu's after-table restate line (`ok`/`upd`/`mod`/`cflt`), and a user-edited `justfile` gets the same three-way diff and pre-unchecked `cflt` treatment as any other modified file — never a silent clobber. The `.versions/<recorded>/justfile` snapshot is the recorded-side of that diff.
270
-
271
- **The `justfile` managed region.** The source `justfile` wraps its recipes between `# >>> agent-fleet:harnesses … >>>` and `# <<< agent-fleet:harnesses <<<` sentinels. Only that region is agent-fleet'. When refreshing into a target that has its own recipes outside the sentinels, replace **only** the managed region (preserving the user's recipes); if the target has no sentinels but every recipe matches the recorded-version `justfile` snapshot (i.e. the user never edited it), it is wholly ours — refresh the whole file, re-introducing the sentinels. If the target has no sentinels **and** has diverged from the snapshot, treat it as `mod`/`cflt` and show the diff before touching it. When merging into a `justfile` that already declares its own `set dotenv-load`, drop that line from the region rather than duplicating the setting (just errors on a repeated setting).
272
-
273
- 7. **External pi packages** *(pi only — companion packages recorded in pi settings, not copied from this repo)* — `pi-ask-user` ★; `pi-codex-image-gen` ★ *(optional suggested image-generation package; install with `pi install -l npm:pi-codex-image-gen` when selected)*. On a `pi` re-run, `pi-ask-user` is normally already `installed · project package` because Step 5b bootstrapped it; that row exists so the user can keep, remove, or re-scope it. `pi-codex-image-gen` is never bootstrapped and is not bundled by this repo; it is offered only as a selected external package.
274
-
275
- Defaults differ by workspace state:
276
-
277
- - **Fresh workspace (no install record).** Pre-selection is empty; replying `recommended` ticks the `★` items across groups 1–4. pi groups (5–7) stay empty unless the agent is `pi`.
278
- - **Existing workspace.** Pre-selection mirrors the install record — every `installed · *` row starts `[x]`. Replying `keep` accepts that pre-selection unchanged; replying `recommended` adds the `★` items on top of what is already installed (it never silently unticks installed items).
279
-
280
- Because groups now span sub-categories, the shortcuts (`all`, `recommended`, `none`, `keep`) and any comma-separated picks apply to the **whole group screen**, across every sub-category in it. After every group, restate the picks in one line so the user can correct them before moving on. The restate line uses the same status vocabulary — for example: *"Skills: keep `code-review-and-quality` (up to date), install `security-and-hardening` (recommended), remove `performance-optimization`."*
281
-
282
- **External pi package status.** For Group 7, treat each row as an external pi package rather than an agent-fleet artifact. In the rendered table the `St` cell is `pkg` for any installed scope (state the scope in the after-table restate line) and `—` when not installed. Apply the same decision logic to every external package row, with package-specific install commands:
283
-
284
- - `installed · bundled by @chankov/agent-fleet` — only for packages actually exposed by this repo's pi manifest (currently `pi-ask-user`). Leave the row unchecked/no-op and do not add a duplicate package entry. Do **not** show `pi-codex-image-gen` as bundled by this repo.
285
- - `installed · project package` — `.pi/settings.json`/`pi list` already records the package spec (for example `npm:pi-ask-user` or `npm:pi-codex-image-gen`); pre-check it to keep.
286
- - `installed · global package` — user settings already provide the package; leave project install unchecked unless the user wants a project-scoped pin.
287
- - `not installed` — show the project-scoped command for the row. Use `pi install -l npm:pi-ask-user` for `pi-ask-user` and `pi install -l npm:pi-codex-image-gen` for `pi-codex-image-gen`. Mention the global form (`pi install npm:<package>`) only when the user chose a global pi setup.
288
-
289
- When an external pi package is selected during clone/symlink or manual pi setup — or when `pi-ask-user` is installed by the Step 5b bootstrap — record that package's npm spec under an `external-pi-packages` / `project-packages` line in `.ai/agent-fleet-setup.md`; do not copy files from `node_modules` or this repo. When deselected later, remove only the package entry this setup owns (for example the project-scoped `.pi/settings.json` entry it recorded). A setup-recorded external package spec such as `npm:pi-codex-image-gen` is governed by this Group 7 ownership rule. Never remove a user-owned global package, an unrecorded project package, or a package entry that predates the install record; surface those as skipped/not owned instead.
290
-
291
- **Removal scope — what "unchecked = remove" actually touches.** A target item is eligible for removal only when **both** are true:
292
-
293
- 1. **It is part of the agent-fleet inventory.** Its name matches an artifact shipped in the source repo's canonical trees (`skills/`, `vendor/agent-skills-upstream/skills/`, `agents/`, `.claude/commands/`, `.pi/prompts/`, `.pi/extensions/`, `.pi/harnesses/`, `.pi/skills/`, `references/`, `hooks/`). External pi packages are governed by the Group 7 ownership rule above. Other out-of-inventory items — user-authored skills, project-specific commands, custom personas, third-party plugins, external pi packages not managed by Group 7 (not setup-owned entries), unrelated dotfiles — are never proposed for removal even if they sit in the same directory.
294
- 2. **It is recorded in this workspace's install record.** The `## install-status` section of `.ai/agent-fleet-setup.md` lists it as previously installed by this skill, *or* it is a symlink whose target resolves into the agent-fleet source root (which is unambiguously ours).
295
-
296
- If a candidate fails either test, list it once under a "Skipped — not owned by agent-fleet" line in the Step 9 plan and leave it alone. Settings files (`.claude/settings.json`, `.opencode/config*`, env vars, MCP config) are touched **only** to remove agent-fleet' own hook registrations — never other keys, never user env vars, never third-party MCP entries.
297
-
298
- ### 7. Offer project overrides
299
-
300
- From the Step 4 analysis, propose draft override sections for `.ai/agent-fleet-overrides.md` — `spec-driven-development`, `planning-and-task-breakdown`, `browser-testing-with-devtools`, `git-workflow-and-versioning`.
301
-
302
- For `pi` workspaces where `agent-hub` is selected, installed, or kept, also offer its user-facing language override:
303
-
304
- - Section: `## agent-hub` (an existing legacy `## agent-team` section is equivalent — preserve its name, don't duplicate it)
305
- - Key: `language: English` as the offered default
306
- - Existing section: preserve the current `language` value in the draft and let the user edit it
307
- - Omitted section: keep `agent-hub`'s default English
308
-
309
- In the same `## agent-hub` draft, offer the project-knowledge keys when the Step 4 analysis finds matching material — propose, never invent:
310
-
311
- - `rules:` — offer when the workspace has a dedicated rule-file tree (common homes: `.ai/rules/`, `docs/rules/`, `.cursor/rules/`); list the folder(s) found. Rule folders with a top-level `README.md`/`index.md` are resolved index-first by the personas, so point the key at the tree root, not at individual bundle files.
312
- - `docs:` — offer when the workspace has canonical WHAT/WHY documentation entry points (an `AGENTS.md`, an architecture overview, a docs index); list the specific entry-point files (or a doc folder with an index), not the whole doc tree.
313
-
314
- Both keys accept comma-separated repo-relative paths; semantics and persona behavior are documented in `docs/agent-fleet-setup.md`. Skip a key when nothing matching exists — an empty guess sends every specialist hunting for files that aren't there.
315
-
316
- Write each section as terse `key: value` lines, never prose: the lifecycle skills and `agent-hub` load this file on every run/session start and parse it by key, so it stays minimal. Show the draft and let the user edit, accept, or skip each section. Reference env-var names for any credentials; keep secrets out of the file. When any drafted section references env-var names (browser-testing roles, STT keys), also offer an `## env` section with `required: <NAME>[, <NAME>]` listing those names — only `agent-fleet doctor` reads it, to warn on unset vars.
317
-
318
- ### 8. Choose the install method
319
-
320
- Ask `copy` or `symlink` for this run.
321
-
322
- - `copy` — copy each artifact into its target path.
323
- - `symlink` — link each target path to the source artifact in the agent-fleet repo.
324
-
325
- **Exception:** personas for `claude-code` and `opencode` are always materialized as generated files via `transform-persona` (Step 3), even in symlink mode — a symlink would expose the untransformed pi-flavored source. Only `pi` persona installs may symlink. State this in the Step 9 summary when the method is `symlink` and personas are selected.
326
-
327
- ### 9. Confirm the plan
328
-
329
- Present the plan compactly — the **"Keep it narrow"** rule from Step 6 applies here too, since this confirmation renders in the same `pi-ask-user` widget. Do **not** render a wide multi-column table: a `Target paths` column plus a `Notes` column plus an `Artifacts` cell that lists every skill name is exactly what overflows the terminal and forces the user to zoom out. Instead, group the plan by action — one short line per action, each artifact list wrapping naturally:
330
-
331
- - `Add (N): a, b, c` — newly ticked items
332
- - `Refresh (N): a, b` — re-installed from source; append `— overwrites local edits` when any row was `mod`
333
- - `Remove (N): a` — unticked installed items (removal-scope rule already applied)
334
- - `Keep (N)` — render as a count, not a full name list (expand only if the user asks)
335
- - `Records: stamp v<current>, update install-status + overrides`
336
- - `Method: copy` (or `symlink`)
337
-
338
- Target paths are deterministic from the per-agent source map, so omit them from the confirmation — show a path only when the user asks. When the version delta from Step 4 is non-empty, lead with a short **"Changes since `v<recorded>` → `v<current>`"** heading followed by one short bullet per change (sourced from `CHANGELOG.md`, only the entries between the two versions) — bullets on their own lines, never crammed into one long line that overflows. Ask the user to confirm, and write nothing until they do.
339
-
340
- **Installer cleanup line.** The summary always ends with one line stating that the installer slash commands (`/setup-agent-fleet`, `/doctor-agent-fleet` — or `/af-*-agent-fleet` for OpenCode — plus the `guided-workspace-setup` skill body) will be removed after apply, so they do not pollute the user's slash-command list. Add the verbatim suffix: *"Reply `keep` to leave them in place; re-run `npx @chankov/agent-fleet init` later if removed."* If the user replies `keep`, record `keep-installer: true` in `## workspace-summary` and skip Step 10b. Otherwise the default is to remove them.
341
-
342
- ### 10. Apply the setup
343
-
344
- Apply the changes: create directories, add or update selected artifacts, and remove deselected ones — **bound by the removal-scope rule from Step 6**. Selected personas for `claude-code`/`opencode` are applied with `node <source-root>/bin/cli.js transform-persona --agent <agent> --workspace <workspace> <name…>` and recorded with `transformed: true`; pi personas follow the normal copy/symlink path. Before deleting any target, verify both conditions: (a) the name is in the agent-fleet inventory and (b) the item is either listed in `## install-status` or is a symlink resolving into the source repo. If either check fails, skip the deletion silently and log the path under a "Skipped — not owned by agent-fleet" line in the final report.
345
-
346
- **Apply without mid-flight questions.** Refresh every ticked item from its per-agent source unconditionally. Do not pause to ask whether to overwrite a modified file — `installed · modified` already appeared in Step 6 with the explicit warning that refreshing overwrites local edits, and the user's tick is the consent. The Step 9 confirmation is the single gate; nothing further is asked during apply. (If the apply hits a genuine error — permission denied, source missing, broken target type — stop, report it, and ask how to proceed; that is not the same as soliciting consent.)
347
-
348
- For settings files (`.claude/settings.json` and equivalents), edit only the agent-fleet hook entries; leave every other key — user permissions, env vars, third-party MCP servers, custom hooks — untouched.
349
-
350
- **pi harness companions.** When this pass installs, refreshes, or removes any pi harness (Step 6 group 6), apply the companion set in the same pass per the Step 6 rules:
351
-
352
- - Refresh `scripts/team-up.ts`, `.pi/agents/peers.yaml`, `.pi/agents/teams.yaml`, the peer personas they name, `.pi/damage-control-rules.yaml`, and `.pi/harnesses/package.json` from source (then `npm install --prefix .pi/harnesses` for the runtime deps).
353
- - Refresh the `justfile` from the **current** source into its managed region (between the `# >>> agent-fleet:harnesses … >>>` / `# <<< agent-fleet:harnesses <<<` sentinels), preserving any user recipes outside it — this is what prunes retired-harness recipes and adds new ones. In symlink mode, link the whole `justfile` to source **only** when the target has no `justfile` or its existing one is wholly agent-fleet'; if the target carries user recipes, fall back to a copy-mode managed-region rewrite so those recipes survive.
354
- - **Removal:** when the **last** pi harness is removed, strip the agent-fleet managed region from the `justfile` (and drop the now-orphaned `scripts/`/`.pi/agents/` companions that no remaining harness needs), bound by the same removal-scope rule — never delete user recipes outside the sentinels, and never delete a companion the user authored.
355
-
356
- **`pi-voice-stt` config companion.** When this pass installs `pi-voice-stt` and the user opted into provider configuration (Step 6 group 5 note), write `.ai/stt.json` (non-secret config) and append the referenced env-var placeholders to the workspace root `.env` (creating it and the `.gitignore` rule if needed) in this same pass — never write key values into `.ai/`. On removal of `pi-voice-stt`, delete `.ai/stt.json` only if unedited, and leave `.env` untouched. Record both under `## install-status`.
357
-
358
- Then write both `.ai/` files: the agreed override sections from Step 7 into `.ai/agent-fleet-overrides.md`, and the install record — artifacts, target paths, method, **package version**, date — into `.ai/agent-fleet-setup.md`. The `version:` line in `## workspace-summary` is set to the package version from Step 2; this is what the next re-run will compare against to compute the version delta.
359
-
360
- ### 10b. Remove the installer artifacts (unless the user said `keep`)
361
-
362
- After Step 10 has written the catalogue + the `.ai/` files, the installer files dropped by `npx @chankov/agent-fleet init` — the `setup-agent-fleet` / `doctor-agent-fleet` slash commands and the `guided-workspace-setup` skill body itself — are no longer needed in the workspace. They were bootstrap plumbing, not part of the user's permanent install. Leaving them in place pollutes the agent's slash-command list and confuses re-runs (which should always go through `init`, not a stale local copy).
363
-
364
- Default behaviour:
365
-
366
- - **`keep-installer: true` in `## workspace-summary`** → skip this step. The files stay.
367
- - **Otherwise** → run the cleanup. Delete every file the bootstrap wrote for the chosen agent:
368
-
369
- | Agent | Files removed |
370
- |---|---|
371
- | `claude-code` | `.claude/commands/setup-agent-fleet.md`, `.claude/commands/doctor-agent-fleet.md`, `.claude/skills/guided-workspace-setup/SKILL.md` |
372
- | `pi` | `.pi/prompts/setup-agent-fleet.md`, `.pi/prompts/doctor-agent-fleet.md`, `.pi/skills/guided-workspace-setup/SKILL.md` |
373
- | `opencode` | `.opencode/commands/af-setup-agent-fleet.md`, `.opencode/commands/af-doctor-agent-fleet.md`, `.opencode/skills/guided-workspace-setup/SKILL.md` |
374
-
375
- After deleting, prune any directories that were created solely for these files (e.g. `.claude/skills/guided-workspace-setup/`) — never prune a directory that contains other files.
376
-
377
- Note: the skill body file you are removing here is the same file the agent is *currently executing*. Filesystem removal does not interrupt the in-memory copy — finish this step, then Step 11, then return as normal.
378
-
379
- If `cleanupInstaller` is available via the CLI (`npx @chankov/agent-fleet cleanup-installer --agent <agent> --workspace <path>`), invoking it is equivalent to the manual deletions above; either path is acceptable. Failures (permission denied, file already gone) are logged but do not abort the apply.
380
-
381
- ### 11. Verify and report
382
-
383
- Re-scan the install-target directories one more time and confirm: every selected artifact exists at its target path, every deselected one is gone, and zero broken symlinks remain. When pi harnesses were touched, also confirm the `justfile` is consistent with the installed harness set: every installed harness has its launch recipe, and **no recipe points at a `.pi/harnesses/<name>/` that is not installed** (a leftover recipe for a retired harness is the regression this check catches). Also re-read `.ai/agent-fleet-setup.md` and verify the `version:` line matches the package version from Step 2 — a mismatch here means the apply pass did not stamp the new version, and must be corrected before the next re-run computes the wrong delta. If the post-apply scan surfaces any new breakage, treat it as a doctor finding and offer the same repair options as Step 5, then append a second `## doctor-runs` line with `phase: postflight`. List what changed, point the user at `.ai/agent-fleet-overrides.md` and `.ai/agent-fleet-setup.md`, and suggest loading `using-agent-skills` first in their next session.
384
-
385
- Close the report with one line explaining the installer-cleanup outcome:
386
-
387
- - If Step 10b ran: *"Installer slash commands removed from your workspace. Re-run `npx @chankov/agent-fleet init` if you need `/setup-agent-fleet` back."*
388
- - If Step 10b was skipped (`keep-installer: true`): *"Installer slash commands kept in place per your choice. `/setup-agent-fleet` and `/doctor-agent-fleet` remain available."*
389
-
390
- ## Common Rationalizations
391
-
392
- | Rationalization | Reality |
393
- |---|---|
394
- | "The user wants everything — I'll install all skills without asking." | Loading every skill wastes context and dilutes discovery. The per-group menu and the `★` recommendations exist so a workspace gets only what it needs. |
395
- | "I'll skip the doctor preflight — the menu will surface broken items anyway." | Broken symlinks distort the install menu's `installed` / `not installed` state. Repair first so the menu reflects reality. |
396
- | "I'll collapse the 7 groups into one big checklist — it's faster." | The 7 groups are how the user reasons about scope (skills vs personas vs commands vs pi-only). A single flat list of ~50 items makes recommendations and sub-category labels meaningless. Keep the 7 screens; within a multi-type group, the `Group` column preserves the sub-sections. |
397
- | "I'll re-split the Skills group back into one screen per phase — six small screens are clearer." | The whole point of the restructure is 7 screens, not 19. The `Group` column already labels the phase within the single Skills screen; splitting it back re-introduces the screen sprawl we removed. |
398
- | "The agent is `pi` and `pi-ask-user` is missing — I'll just run the menu in the tabular fallback and skip the bootstrap." | Step 5b exists precisely to avoid forcing a ~50-row menu through plain text. Offer the install-then-reload bootstrap first; only fall back to tabular if the user *declines*. |
399
- | "I installed `pi-ask-user` in Step 5b, so I'll keep going straight into the install menu in the same pass." | The tool only becomes callable after pi reloads. Stop the pass after install, ask the user to reload and re-run; the native widget is unavailable until then. |
400
- | "I'll copy the files now and confirm afterwards." | Writing before the Step 9 confirmation can clobber config the user wanted to keep. Confirmation is the only gate that protects the target workspace. |
401
- | "There is no `*-setup.md` for this agent, so I'll guess the install paths." | Guessed paths put artifacts where the agent never loads them. Read the agent's setup doc, or use the built-in map — a location is never invented. |
402
- | "The workspace already has a `.claude/` directory, so setup is done." | A directory existing is not install state. The `## install-status` section is the only record of what this skill installed; read it before deciding. |
403
- | "An existing file differs from the source — I'll pause and ask the user mid-apply whether to overwrite." | Step 6 already surfaced `installed · modified` with the warning that refreshing overwrites local edits. The user's tick is the consent. Mid-apply questions break the apply pass; they were replaced by the upfront status. |
404
- | "`.pi/prompts/design-agent.md` doesn't exist, but `.claude/commands/design-agent.md` does — I'll symlink to the Claude file so the user gets the prompt." | That mixes runtimes silently and lets the source repo's claude-code tree drive a pi target. The source availability filter forbids it: items without a per-agent source are not offered at all. |
405
- | "The harness directories installed fine — the `justfile` is just launch shortcuts, I'll leave the existing one." | The `justfile` is how harnesses are launched; if it is not refreshed from the current source, retired-harness recipes linger (pointing at deleted `.pi/harnesses/<name>/` dirs) and newly added harnesses (for example `ask-user-remote` or the Hermes `conductor` recipe) have no recipe at all. It is a companion of the harness group and must be refreshed whenever any harness changes. |
406
- | "I'll just copy the source `justfile` over the target's to refresh it." | A wholesale copy clobbers any recipes the user authored. Refresh only the managed region between the `agent-fleet:harnesses` sentinels; a user-edited `justfile` outside that region is `mod`/`cflt` and gets the three-way diff first — never a silent overwrite. |
407
- | "The persona is just markdown — I'll copy it as-is for claude-code; the extra frontmatter keys are harmless." | The canonical frontmatter carries pi tool names (`find`, `ls`), pi model routes (`openai-codex/…`), and agent-hub keys the target cannot read. The `transform-persona` CLI exists so the installed file is correct and deterministic — raw copies and hand-transforms both drift. |
408
- | "I'll skip the workspace analysis and just ask the user everything." | The analysis is what makes the override offer accurate. Asking blind produces an overrides file the user has to hand-correct afterwards. |
409
- | "I'll record the full install detail in the overrides file too — one place is simpler." | Other skills load the overrides file on every run. Install detail belongs only in `agent-fleet-setup.md`; padding the overrides file taxes every later session. |
410
- | "There's an unfamiliar skill in `.claude/skills/` — the user must have forgotten to uncheck it, I'll remove it." | The removal scope rule exists exactly to prevent this. If the name is not in the agent-fleet inventory or not in `## install-status`, it is user-owned; leave it alone and log it as skipped. |
411
- | "The user wants a clean workspace — I'll prune custom hooks and unrelated MCP entries from `settings.json` too." | Setting-file edits are limited to agent-fleet' own hook registrations. Touching anything else silently deletes work that does not belong to this skill. |
412
- | "`/setup-agent-fleet` and `/doctor-agent-fleet` are useful — I'll re-install them at the end of apply so the user can re-run them locally." | They are installer commands that the CLI bootstraps and the skill itself cleans up in Step 10b by default. Keeping them is opt-in via `keep` in Step 9. Re-installing them silently undoes the cleanup the user implicitly chose. |
413
- | "The bootstrap marker is missing — I'll search the user's `~/repos/`, `~/projects/`, and `/media/` for any clone of `agent-fleet` to use as the source root." | Scanning the user's filesystem picks up dev clones, forks, half-edited working trees, and stale checkouts that are NOT the package the user installed from. The npm-installed copy is the only authoritative source after `init`. Without the marker, ask the user explicitly — never guess. |
414
- | "This `SKILL.md` is two levels below the workspace's `.pi/skills/`, so the workspace root must be the source root." | Bootstrap copies `SKILL.md` into the workspace precisely so the slash command can load it. The workspace is the *target* of the install, not the source. Use the marker file to find the real source; resolving from `SKILL.md`'s workspace location always lies. |
415
- | "The recorded version differs from the current — I'll just refresh everything to the new source without showing the diff." | Conflicting upgrades (user-modified copy + source changed upstream) require the three-way diff to be shown in Step 6, with the row pre-unchecked. Refreshing silently overwrites work the user did between versions. |
416
- | "The `.versions/<recorded>/` snapshot is missing — I'll pretend the installed copy matches the recorded source and refresh anyway." | A missing snapshot means we cannot compute the three-way diff. The skill must fall back to "treat installed copy as canonical" and surface the missing snapshot in the row's status so the user can decide — never pretend a diff exists. |
417
- | "The workspace has no `version:` line — I'll silently stamp the current version and move on." | A pre-versioning workspace must be flagged in Step 4 and the user prompted: stamp the current version (assume copies match) or wipe and reinstall. Silent stamping hides a real decision. |
418
- | "The user didn't say anything about the installer cleanup line — I'll leave the installer files in place to be safe." | The default is to remove. Step 9's confirmation line explicitly states the cleanup will happen unless the user replies `keep`. Silence is consent for the default, not opt-out from it. |
419
- | "I'll add `setup-agent-fleet` and `doctor-agent-fleet` to the install menu so the user can pick whether to keep them." | They are still installer-only and excluded from the menu. The keep-vs-remove choice is the single Step 9 line, not a menu group — adding them to the menu re-opens the pollution we just fixed. |
420
- | "The skill is currently executing; deleting its own file in Step 10b will crash mid-run." | The agent loads the skill into memory at the start of execution. Removing the file on disk does not unload the in-memory copy — Steps 10b and 11 complete normally before control returns. |
421
-
422
- ## Red Flags
423
-
424
- - Files written to the target workspace before the Step 9 confirmation.
425
- - The doctor preflight skipped on a workspace that already has prior install state.
426
- - An install menu rendered as one undifferentiated list instead of the 7 grouped tables (≤ 8), or the Skills group re-split into one screen per phase.
427
- - A multi-type group (Skills, Agent personas, References & Hooks, pi extensions & runtime skills, pi harnesses) rendered without the `Group` sub-category column.
428
- - The agent is `pi`, `pi-ask-user` is missing, and the install menu was rendered in tabular fallback without first offering the Step 5b bootstrap.
429
- - Step 5b installed `pi-ask-user` but the pass continued into the install menu instead of stopping for the user to reload and re-run.
430
- - A menu group rendered without a per-row `St` token (or without the legend that defines them), or with installed items not pre-checked.
431
- - A menu table rendered with the long `installed · …` state names, a separate `Rec` column, or wide cells/preamble that overflow the terminal — render the compact form so the `pi-ask-user` widget fits without zooming.
432
- - The Step 9 confirmation rendered as a wide multi-column table (a `Target paths` or `Notes` column, or an `Artifacts` cell listing every skill name) instead of compact action-grouped lines, or the "Changes since" delta crammed into one long line instead of short per-change bullets.
433
- - A `recommended` reply that silently unticks already-installed items instead of adding `★` items on top.
434
- - `setup`, `doctor`, or `guided-workspace-setup` shown in the install menu — they are installer-only.
435
- - An item offered for one agent whose per-agent source file does not exist (cross-tool substitution).
436
- - Hook rows offered to a non-`claude-code` agent (group 4 should degrade to References-only for `opencode`/`pi`).
437
- - A persona for `claude-code`/`opencode` copied or symlinked raw instead of generated via `transform-persona` — or its frontmatter "transformed" by hand in prose instead of by the CLI.
438
- - A pi-only persona (`bowser`, `web-debugger`, `orchestrator`) offered in a non-`pi` menu, or the personas group showing a hardcoded subset instead of the full `transform-persona --list` roster.
439
- - A transformed persona row diffed against the raw canonical source instead of against the generated output (false `modified` status on every re-run).
440
- - A mid-apply prompt asking whether to overwrite a modified target file — that consent belongs in Step 6 / Step 9, not in Step 10.
441
- - A target file or directory deleted whose name is not in the agent-fleet inventory, or that is not recorded in `## install-status` and is not a symlink into the source repo.
442
- - Edits to `settings.json` / env vars / MCP config beyond removing agent-fleet' own hook registrations.
443
- - An artifact installed to a path backed by neither the built-in map nor the agent's `*-setup.md`.
444
- - pi harnesses installed, refreshed, or retired without the `justfile` being refreshed — its `just --list` still shows recipes for removed harnesses, points at `.pi/harnesses/<name>/` dirs that are not installed, or lacks recipes for newly added harnesses.
445
- - The `justfile` (or `scripts/`/`.pi/agents/` companions) overwritten wholesale, clobbering recipes or files the user authored outside the agent-fleet managed region.
446
- - `.ai/agent-fleet-setup.md` left unchanged after artifacts were added or removed.
447
- - Credentials or secrets written into either `.ai/` file.
448
- - Every skill installed when the workspace needs a handful.
449
- - An existing, differing target file overwritten without asking the user.
450
- - A re-run that ignores the existing `## install-status` and reinstalls everything.
451
- - A `pi` workspace using `agent-hub` reached Step 7 without being offered the `## agent-hub` / `language: <value>` override, or an existing language value was overwritten instead of preserved.
452
- - `agent-hub` installed or kept without `damage-control` **and** `damage-control-continue` — the mandatory pairing was skipped, or an untick of either damage-control variant was accepted while `agent-hub` stayed selected.
453
- - The `bowser` runtime-skill installed without checking for the external `playwright-cli` CLI — or a global `@playwright/cli` install run without the user's confirmation.
454
- - The overrides file padded with install status, summaries, or prose instead of terse `key: value` sections.
455
- - A re-run that detects a non-empty version delta but skips the "Changes since v<recorded> → v<current>" block in Step 9.
456
- - A `conflicting upgrade` row pre-checked, or the three-way diff omitted for it.
457
- - A pre-versioning workspace stamped with the current version without prompting the user first.
458
- - The post-apply `version:` line not matching the package version from Step 2.
459
- - Step 9 summary missing the installer-cleanup line, or the line stated `keep` as the default.
460
- - Source root resolved by scanning the filesystem for `agent-fleet` repos (`find`, `fd`, `grep -r`, …) instead of using `.ai/.agent-fleet-bootstrap.json` or asking the user.
461
- - Source root resolved by treating `SKILL.md`'s workspace location (`.pi/skills/...` or `.claude/skills/...`) as the package root.
462
- - The bootstrap marker file (`.ai/.agent-fleet-bootstrap.json`) ignored when present, or trusted blindly when the path it names no longer exists.
463
- - Installer files (`setup-agent-fleet`, `doctor-agent-fleet`, the `guided-workspace-setup` skill body) left in place without a recorded `keep-installer: true`.
464
- - `setup-agent-fleet` or `doctor-agent-fleet` shown as install-menu rows.
465
- - Step 11 report omitting the one-line installer-cleanup outcome.
466
-
467
- ## Verification
468
-
469
- After completing the workflow, confirm:
470
-
471
- - [ ] The workspace path was validated as an existing directory before any write.
472
- - [ ] The coding agent was confirmed, and `docs/<agent>-setup.md` was read for `opencode`/`pi` (or the built-in map used for `claude-code`).
473
- - [ ] The doctor preflight ran on any workspace with prior install state, and its findings were resolved or explicitly skipped.
474
- - [ ] On `pi`, Step 5b ran before the menu: `pi-ask-user` was either already present (no-op) or its install-then-reload bootstrap was offered; the pass stopped after install when it was bootstrapped, and was not forced when the user declined.
475
- - [ ] The install menu was presented as the 7 grouped tables (groups 5–7 shown only for `pi`), not 19 screens and not one flat list; each was its own multi-select with `★` recommendations marked.
476
- - [ ] Each multi-type group (Skills, Agent personas, References & Hooks, and the pi extension/harness groups) carried a `Group` sub-category column ordering its rows.
477
- - [ ] Every row carried an explicit `St` token (`ok`, `upd`, `mod`, `cflt`, `gone`, `new`, `pkg`, `—`, or `brk`) with the legend shown once above the table — never blank and never the long `installed · …` state names that overflow the widget.
478
- - [ ] Installed items were pre-checked `[x]`; not-installed items were pre-checked `[ ]`; `recommended` added `★` items on top of the pre-selection without unticking installed ones.
479
- - [ ] Items lacking a per-agent source were filtered out of the menu — no cross-tool substitution offered.
480
- - [ ] Hooks were offered only for `claude-code`; References were still offered for all agents.
481
- - [ ] On `claude-code`, groups were driven via `AskUserQuestion` (quick-path + ≤ 4-option chunks), not free-text table replies.
482
- - [ ] The personas group listed the full `transform-persona --list` roster for the chosen agent; pi-only personas appeared only for `pi`; selected personas for `claude-code`/`opencode` were written by the `transform-persona` CLI and recorded with `transformed: true`.
483
- - [ ] Apply ran without any overwrite-this-file prompt; ticked items refreshed unconditionally and unticked modified items were preserved.
484
- - [ ] `setup`, `doctor`, and `guided-workspace-setup` were excluded from the install menu.
485
- - [ ] Every selected artifact exists at its resolved target path; every deselected one was removed **only if** the removal-scope rule allowed it (in inventory + in install record / symlink-into-source).
486
- - [ ] When pi harnesses were installed/refreshed/removed, the `justfile` and harness support files were refreshed from the current source: the `justfile` lists a recipe for every installed harness, none for a removed one, and points at no missing `.pi/harnesses/<name>/`; user recipes outside the managed-region sentinels were preserved.
487
- - [ ] Out-of-inventory and unrecorded items found in the install-target directories were left untouched and logged under "Skipped — not owned by agent-fleet".
488
- - [ ] Settings-file edits were limited to agent-fleet' own hook entries; no user keys, env vars, or third-party MCP entries were modified.
489
- - [ ] `.ai/agent-fleet-overrides.md` holds the agreed override sections as terse `key: value` lines, and nothing else.
490
- - [ ] For `pi` workspaces using `agent-hub`, the `## agent-hub` language override was offered (an existing legacy `## agent-team` section kept its name), existing values were preserved, and omitting the section was treated as default English.
491
- - [ ] If `agent-hub` was installed or kept, `damage-control` was installed/kept alongside it (mandatory pairing) and could not be deselected while `agent-hub` remained.
492
- - [ ] If the `bowser` runtime-skill was installed or kept, the external `playwright-cli` dependency was checked, and a missing CLI was surfaced with the install offer (`npm install -g @playwright/cli@latest`) rather than silently installed or treated as a hard failure.
493
- - [ ] `.ai/agent-fleet-setup.md` holds an up-to-date install record, including at least one `## doctor-runs` entry for this session, and a `version:` line in `## workspace-summary` that matches the package version from Step 2.
494
- - [ ] Step 9 was rendered as compact action-grouped lines (Add / Refresh / Remove / Keep-count / Records / Method), not a wide `Target paths` + `Notes` table that overflows the widget.
495
- - [ ] When the version delta was non-empty, Step 9's summary led with the "Changes since v<recorded> → v<current>" heading followed by short per-change bullets sourced from `CHANGELOG.md` — never one long overflowing line.
496
- - [ ] Every `conflicting upgrade` row was rendered with its three-way diff in Step 6 and was not pre-checked.
497
- - [ ] A pre-versioning workspace was flagged in Step 4 and the user was prompted to stamp or wipe — not silently stamped.
498
- - [ ] Source root was resolved from `.ai/.agent-fleet-bootstrap.json` if present, or from `SKILL.md`'s realpath (symlink mode), or by asking the user — **never** by scanning the filesystem.
499
- - [ ] If the bootstrap marker named a path that no longer exists, the user was warned and asked for a new path — not silently ignored.
500
- - [ ] Step 9 summary ended with the installer-cleanup line: states remove-by-default and offers `keep` as the opt-out.
501
- - [ ] Step 10b ran (or was explicitly skipped because `keep-installer: true`); the installer files are absent from the workspace unless the user opted to keep them.
502
- - [ ] Step 11 report includes the one-line installer-cleanup outcome.
503
- - [ ] No broken symlinks remain in any of the scanned install-target directories.
504
- - [ ] No YAML config references a removed persona name.
505
- - [ ] No secrets were written to either `.ai/` file.
506
- - [ ] The user confirmed the plan in Step 9 before any file was written.
@@ -1,22 +0,0 @@
1
- ---
2
- description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
3
- ---
4
-
5
- Invoke the `guided-workspace-setup` skill via the `skill` tool and run its repair path only — not the rest of the install flow. `/af-setup-agent-fleet` offers the same thing as soon as it finds prior install state.
6
-
7
- Run the CLI — do not walk directories or repair files yourself:
8
-
9
- ```
10
- node <source-root>/bin/cli.js doctor --workspace <workspace> [--agent <agent>] --json
11
- ```
12
-
13
- Resolve `<source-root>` from `<workspace>/.ai/.agent-fleet-bootstrap.json`, or this prompt's realpath if it is a symlink, or by asking. Never scan the filesystem for agent-fleet clones.
14
-
15
- The report has two halves, and they are repaired differently on purpose:
16
-
17
- - `repairs` — recorded items that are missing, dangling, or linked outside the source root. These are rebuilt through the same `apply()` path `install` writes with, so a repaired file is byte-identical to a freshly installed one.
18
- - `findings` — what the install record cannot own: broken symlinks in a pre-engine workspace, stale persona names in `.pi/agents/*.yaml` (`reviewer` → `code-reviewer`, `red-team` → `security-auditor`), plus advisory ones. `overrides` and `yaml-shape` findings are **advisory**: report them with "edit by hand" and never fix them, because the fix is always a hand edit of the flagged file.
19
-
20
- Print the two lists as text, then ask one native single-select (or a plain text question without a widget) — *"Apply the suggested fixes?"* — and on yes re-run with `--fix`. An empty answer or a cancel applies nothing.
21
-
22
- Exit codes: `0` nothing to repair, `2` repairable issues found (or advisories present, or a repair failed), `1` could not run. Report the counts the CLI returns; do not invent your own.