@chankov/agent-fleet 0.0.8 → 0.0.10

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 (682) hide show
  1. package/.claude/commands/doctor-agent-fleet.md +12 -7
  2. package/.claude/commands/setup-agent-fleet.md +7 -15
  3. package/.opencode/commands/af-doctor-agent-fleet.md +12 -7
  4. package/.opencode/commands/af-setup-agent-fleet.md +8 -6
  5. package/.pi/agents/model-profiles.yaml +9 -2
  6. package/.pi/agents/peers.yaml +12 -16
  7. package/.pi/agents/teams.yaml +4 -2
  8. package/.pi/extensions/agent-fleet-update-check/README.md +2 -3
  9. package/.pi/extensions/btw/README.md +2 -2
  10. package/.pi/extensions/chrome-devtools-mcp/README.md +3 -6
  11. package/.pi/extensions/compact-and-continue/README.md +3 -3
  12. package/.pi/extensions/mcp-bridge/README.md +1 -1
  13. package/.pi/harnesses/agent-hub/README.md +159 -15
  14. package/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  15. package/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  16. package/.pi/harnesses/agent-hub/footer.ts +4 -2
  17. package/.pi/harnesses/agent-hub/index.ts +552 -50
  18. package/.pi/harnesses/agent-hub/package.json +1 -1
  19. package/.pi/harnesses/agent-hub/review-findings.js +102 -0
  20. package/.pi/harnesses/agent-hub/run-budget.js +302 -4
  21. package/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  22. package/.pi/harnesses/agent-hub/version.ts +25 -1
  23. package/.pi/harnesses/coms/README.md +8 -1
  24. package/.pi/harnesses/coms/package.json +1 -1
  25. package/.pi/harnesses/coms/version.ts +25 -1
  26. package/.pi/harnesses/damage-control-continue/README.md +8 -1
  27. package/.pi/harnesses/damage-control-continue/package.json +1 -1
  28. package/.pi/harnesses/damage-control-continue/version.ts +25 -1
  29. package/.pi/harnesses/lib/herdr-client.ts +10 -1
  30. package/.pi/harnesses/lib/spawned-peers.js +190 -0
  31. package/.pi/prompts/af-doctor-agent-fleet.md +13 -6
  32. package/.pi/prompts/af-setup-agent-fleet.md +7 -15
  33. package/.versions/0.0.10/.claude/commands/build.md +44 -0
  34. package/.versions/0.0.10/.claude/commands/code-simplify.md +22 -0
  35. package/.versions/0.0.10/.claude/commands/design-agent.md +14 -0
  36. package/.versions/0.0.10/.claude/commands/doctor-agent-fleet.md +22 -0
  37. package/.versions/0.0.10/.claude/commands/orchestrate.md +112 -0
  38. package/.versions/0.0.10/.claude/commands/plan.md +16 -0
  39. package/.versions/0.0.10/.claude/commands/prime.md +22 -0
  40. package/.versions/0.0.10/.claude/commands/review.md +16 -0
  41. package/.versions/0.0.10/.claude/commands/set-hermes-telegram.md +15 -0
  42. package/.versions/0.0.10/.claude/commands/set-hermes-watchdog.md +6 -0
  43. package/.versions/0.0.10/.claude/commands/setup-agent-fleet.md +17 -0
  44. package/.versions/0.0.10/.claude/commands/ship.md +72 -0
  45. package/.versions/0.0.10/.claude/commands/spec.md +15 -0
  46. package/.versions/0.0.10/.claude/commands/test.md +19 -0
  47. package/.versions/0.0.10/.claude/commands/webperf.md +32 -0
  48. package/.versions/0.0.10/.claude/orchestrate-teams.yaml +24 -0
  49. package/.versions/0.0.10/.opencode/commands/af-build.md +17 -0
  50. package/.versions/0.0.10/.opencode/commands/af-code-simplify.md +16 -0
  51. package/.versions/0.0.10/.opencode/commands/af-compound.md +16 -0
  52. package/.versions/0.0.10/.opencode/commands/af-design-agent.md +15 -0
  53. package/.versions/0.0.10/.opencode/commands/af-doctor-agent-fleet.md +22 -0
  54. package/.versions/0.0.10/.opencode/commands/af-orchestrate.md +112 -0
  55. package/.versions/0.0.10/.opencode/commands/af-plan.md +16 -0
  56. package/.versions/0.0.10/.opencode/commands/af-prime.md +22 -0
  57. package/.versions/0.0.10/.opencode/commands/af-review.md +15 -0
  58. package/.versions/0.0.10/.opencode/commands/af-set-hermes-telegram.md +15 -0
  59. package/.versions/0.0.10/.opencode/commands/af-set-hermes-watchdog.md +6 -0
  60. package/.versions/0.0.10/.opencode/commands/af-setup-agent-fleet.md +17 -0
  61. package/.versions/0.0.10/.opencode/commands/af-ship.md +16 -0
  62. package/.versions/0.0.10/.opencode/commands/af-spec.md +16 -0
  63. package/.versions/0.0.10/.opencode/commands/af-test.md +21 -0
  64. package/.versions/0.0.10/.opencode/commands/af-webperf.md +32 -0
  65. package/.versions/0.0.10/.opencode/orchestrate-teams.yaml +24 -0
  66. package/.versions/0.0.10/.pi/agents/dispatch-policy.yaml +32 -0
  67. package/.versions/0.0.10/.pi/agents/model-profiles.yaml +27 -0
  68. package/.versions/0.0.10/.pi/agents/peers.yaml +142 -0
  69. package/.versions/0.0.10/.pi/agents/teams.yaml +41 -0
  70. package/.versions/0.0.10/.pi/damage-control-rules.yaml +297 -0
  71. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/README.md +57 -0
  72. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  73. package/.versions/0.0.10/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  74. package/.versions/0.0.10/.pi/extensions/btw/README.md +118 -0
  75. package/.versions/0.0.10/.pi/extensions/btw/index.ts +917 -0
  76. package/.versions/0.0.10/.pi/extensions/btw/package.json +6 -0
  77. package/.versions/0.0.10/.pi/extensions/btw/state.js +179 -0
  78. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
  79. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  80. package/.versions/0.0.10/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  81. package/.versions/0.0.10/.pi/extensions/compact-and-continue/README.md +42 -0
  82. package/.versions/0.0.10/.pi/extensions/compact-and-continue/index.ts +120 -0
  83. package/.versions/0.0.10/.pi/extensions/compact-and-continue/package.json +6 -0
  84. package/.versions/0.0.10/.pi/extensions/mcp-bridge/README.md +46 -0
  85. package/.versions/0.0.10/.pi/extensions/mcp-bridge/index.ts +206 -0
  86. package/.versions/0.0.10/.pi/extensions/mcp-bridge/package.json +6 -0
  87. package/.versions/0.0.10/.pi/extensions/package-lock.json +1143 -0
  88. package/.versions/0.0.10/.pi/extensions/package.json +9 -0
  89. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/README.md +201 -0
  90. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/config.ts +198 -0
  91. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  92. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/index.ts +248 -0
  93. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/package.json +6 -0
  94. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  95. package/.versions/0.0.10/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  96. package/.versions/0.0.10/.pi/harnesses/agent-hub/README.md +1001 -0
  97. package/.versions/0.0.10/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  98. package/.versions/0.0.10/.pi/harnesses/agent-hub/artifacts.js +146 -0
  99. package/.versions/0.0.10/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  100. package/.versions/0.0.10/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  101. package/.versions/0.0.10/.pi/harnesses/agent-hub/context-window.js +106 -0
  102. package/.versions/0.0.10/.pi/harnesses/agent-hub/delegate.ts +435 -0
  103. package/.versions/0.0.10/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  104. package/.versions/0.0.10/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
  105. package/.versions/0.0.10/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  106. package/.versions/0.0.10/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  107. package/.versions/0.0.10/.pi/harnesses/agent-hub/footer.ts +31 -0
  108. package/.versions/0.0.10/.pi/harnesses/agent-hub/helpers.ts +248 -0
  109. package/.versions/0.0.10/.pi/harnesses/agent-hub/index.ts +9111 -0
  110. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  111. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  112. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  113. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  114. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  115. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  116. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  117. package/.versions/0.0.10/.pi/harnesses/agent-hub/monitor-session-bridge.ts +257 -0
  118. package/.versions/0.0.10/.pi/harnesses/agent-hub/package.json +7 -0
  119. package/.versions/0.0.10/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  120. package/.versions/0.0.10/.pi/harnesses/agent-hub/research-retention.js +34 -0
  121. package/.versions/0.0.10/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  122. package/.versions/0.0.10/.pi/harnesses/agent-hub/return-contract.js +293 -0
  123. package/.versions/0.0.10/.pi/harnesses/agent-hub/return-extract.js +75 -0
  124. package/.versions/0.0.10/.pi/harnesses/agent-hub/review-findings.js +102 -0
  125. package/.versions/0.0.10/.pi/harnesses/agent-hub/run-budget.js +479 -0
  126. package/.versions/0.0.10/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  127. package/.versions/0.0.10/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  128. package/.versions/0.0.10/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  129. package/.versions/0.0.10/.pi/harnesses/agent-hub/session-health.js +110 -0
  130. package/.versions/0.0.10/.pi/harnesses/agent-hub/spawn.ts +354 -0
  131. package/.versions/0.0.10/.pi/harnesses/agent-hub/version.ts +42 -0
  132. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/README.md +19 -0
  133. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/index.ts +321 -0
  134. package/.versions/0.0.10/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  135. package/.versions/0.0.10/.pi/harnesses/coms/README.md +100 -0
  136. package/.versions/0.0.10/.pi/harnesses/coms/index.ts +1767 -0
  137. package/.versions/0.0.10/.pi/harnesses/coms/package.json +7 -0
  138. package/.versions/0.0.10/.pi/harnesses/coms/version.ts +42 -0
  139. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/README.md +124 -0
  140. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/index.ts +536 -0
  141. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/package.json +7 -0
  142. package/.versions/0.0.10/.pi/harnesses/damage-control-continue/version.ts +42 -0
  143. package/.versions/0.0.10/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  144. package/.versions/0.0.10/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  145. package/.versions/0.0.10/.pi/harnesses/lib/herdr-client.ts +472 -0
  146. package/.versions/0.0.10/.pi/harnesses/lib/herdr-presence.ts +399 -0
  147. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  148. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  149. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  150. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  151. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  152. package/.versions/0.0.10/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  153. package/.versions/0.0.10/.pi/harnesses/lib/spawned-peers.js +190 -0
  154. package/.versions/0.0.10/.pi/harnesses/package-lock.json +35 -0
  155. package/.versions/0.0.10/.pi/harnesses/package.json +9 -0
  156. package/.versions/0.0.10/.pi/prompts/af-build.md +24 -0
  157. package/.versions/0.0.10/.pi/prompts/af-code-simplify.md +22 -0
  158. package/.versions/0.0.10/.pi/prompts/af-doctor-agent-fleet.md +22 -0
  159. package/.versions/0.0.10/.pi/prompts/af-plan.md +16 -0
  160. package/.versions/0.0.10/.pi/prompts/af-review.md +16 -0
  161. package/.versions/0.0.10/.pi/prompts/af-set-hermes-telegram.md +15 -0
  162. package/.versions/0.0.10/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  163. package/.versions/0.0.10/.pi/prompts/af-setup-agent-fleet.md +19 -0
  164. package/.versions/0.0.10/.pi/prompts/af-ship.md +17 -0
  165. package/.versions/0.0.10/.pi/prompts/af-spec.md +15 -0
  166. package/.versions/0.0.10/.pi/prompts/af-test.md +19 -0
  167. package/.versions/0.0.10/.pi/skills/bowser/SKILL.md +145 -0
  168. package/.versions/0.0.10/.version +1 -0
  169. package/.versions/0.0.10/agents/architect.md +24 -0
  170. package/.versions/0.0.10/agents/bowser.md +27 -0
  171. package/.versions/0.0.10/agents/builder.md +54 -0
  172. package/.versions/0.0.10/agents/code-reviewer.md +208 -0
  173. package/.versions/0.0.10/agents/deep-researcher.md +32 -0
  174. package/.versions/0.0.10/agents/documenter.md +18 -0
  175. package/.versions/0.0.10/agents/orchestrator.md +72 -0
  176. package/.versions/0.0.10/agents/plan-reviewer.md +83 -0
  177. package/.versions/0.0.10/agents/planner.md +70 -0
  178. package/.versions/0.0.10/agents/releaser.md +24 -0
  179. package/.versions/0.0.10/agents/researcher.md +28 -0
  180. package/.versions/0.0.10/agents/security-auditor.md +167 -0
  181. package/.versions/0.0.10/agents/test-engineer.md +153 -0
  182. package/.versions/0.0.10/agents/web-debugger.md +43 -0
  183. package/.versions/0.0.10/agents/web-performance-auditor.md +193 -0
  184. package/.versions/0.0.10/codex/CONDUCTOR.md +148 -0
  185. package/.versions/0.0.10/docs/ARCHITECTURE.md +303 -0
  186. package/.versions/0.0.10/docs/agent-fleet-setup.md +377 -0
  187. package/.versions/0.0.10/docs/claude-code-coms-bridge.md +109 -0
  188. package/.versions/0.0.10/docs/codex-remote-conductor.md +170 -0
  189. package/.versions/0.0.10/docs/coms-hermes-bridge.md +189 -0
  190. package/.versions/0.0.10/docs/getting-started.md +254 -0
  191. package/.versions/0.0.10/docs/npm-install.md +514 -0
  192. package/.versions/0.0.10/docs/opencode-setup.md +281 -0
  193. package/.versions/0.0.10/docs/pi-extensions.md +363 -0
  194. package/.versions/0.0.10/docs/pi-setup.md +571 -0
  195. package/.versions/0.0.10/docs/skill-anatomy.md +150 -0
  196. package/.versions/0.0.10/hermes/README.md +347 -0
  197. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  198. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  199. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  200. package/.versions/0.0.10/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  201. package/.versions/0.0.10/hermes/gates/gate-o-capability.md +8 -0
  202. package/.versions/0.0.10/hermes/gates/gate-o-validator-fixtures.json +1 -0
  203. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  204. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  205. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  206. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  207. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  208. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  209. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  210. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  211. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  212. package/.versions/0.0.10/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  213. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  214. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  215. package/.versions/0.0.10/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  216. package/.versions/0.0.10/hermes/skills/hub-conductor/SKILL.md +84 -0
  217. package/.versions/0.0.10/hermes/skills/hub-liaison/SKILL.md +84 -0
  218. package/.versions/0.0.10/hermes/skills/hub-watchdog/SKILL.md +76 -0
  219. package/.versions/0.0.10/hermes/skills/hub-watchdog/manifest.json +1 -0
  220. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  221. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  222. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  223. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  224. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  225. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  226. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  227. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  228. package/.versions/0.0.10/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  229. package/.versions/0.0.10/hermes/watchdog-tests/__init__.py +0 -0
  230. package/.versions/0.0.10/hooks/SIMPLIFY-IGNORE.md +90 -0
  231. package/.versions/0.0.10/hooks/coms-stop-hook.mjs +84 -0
  232. package/.versions/0.0.10/hooks/hooks.json +14 -0
  233. package/.versions/0.0.10/hooks/session-start.sh +74 -0
  234. package/.versions/0.0.10/hooks/simplify-ignore.sh +302 -0
  235. package/.versions/0.0.10/install-manifest.json +3615 -0
  236. package/.versions/0.0.10/justfile +254 -0
  237. package/.versions/0.0.10/manifest-meta.json +472 -0
  238. package/.versions/0.0.10/references/accessibility-checklist.md +160 -0
  239. package/.versions/0.0.10/references/definition-of-done.md +67 -0
  240. package/.versions/0.0.10/references/fleet-coordination-patterns.md +151 -0
  241. package/.versions/0.0.10/references/observability-checklist.md +91 -0
  242. package/.versions/0.0.10/references/orchestration-patterns.md +370 -0
  243. package/.versions/0.0.10/references/performance-checklist.md +153 -0
  244. package/.versions/0.0.10/references/prompting-patterns.md +380 -0
  245. package/.versions/0.0.10/references/security-checklist.md +179 -0
  246. package/.versions/0.0.10/references/testing-patterns.md +236 -0
  247. package/.versions/0.0.10/scripts/codex-conductor.ts +41 -0
  248. package/.versions/0.0.10/scripts/codex-remote-control.ts +167 -0
  249. package/.versions/0.0.10/scripts/coms-claude-bridge.ts +401 -0
  250. package/.versions/0.0.10/scripts/coms-cli.ts +484 -0
  251. package/.versions/0.0.10/scripts/coms-hermes-bridge.ts +413 -0
  252. package/.versions/0.0.10/scripts/fleet.ts +168 -0
  253. package/.versions/0.0.10/scripts/hermes-monitor-capability-runner.ts +25 -0
  254. package/.versions/0.0.10/scripts/hermes-monitor-scenario.ts +474 -0
  255. package/.versions/0.0.10/scripts/hermes-watchdog-capability-probe.ts +45 -0
  256. package/.versions/0.0.10/scripts/install-hermes-plugin.sh +180 -0
  257. package/.versions/0.0.10/scripts/lib/claude-bridge-core.ts +165 -0
  258. package/.versions/0.0.10/scripts/lib/codex-conductor.ts +88 -0
  259. package/.versions/0.0.10/scripts/lib/codex-remote-control.ts +480 -0
  260. package/.versions/0.0.10/scripts/lib/coms-envelope.ts +582 -0
  261. package/.versions/0.0.10/scripts/lib/fake-herdr-server.ts +88 -0
  262. package/.versions/0.0.10/scripts/lib/fleet-command.ts +111 -0
  263. package/.versions/0.0.10/scripts/lib/herdr-layout.ts +281 -0
  264. package/.versions/0.0.10/scripts/lib/hermes-bridge-core.ts +241 -0
  265. package/.versions/0.0.10/scripts/lib/hermes-monitor-events.ts +1 -0
  266. package/.versions/0.0.10/scripts/lib/hermes-monitor-herdr.ts +2 -0
  267. package/.versions/0.0.10/scripts/lib/hermes-monitor-model.ts +3 -0
  268. package/.versions/0.0.10/scripts/lib/hermes-monitor-registry.ts +2 -0
  269. package/.versions/0.0.10/scripts/lib/hermes-monitor-socket.ts +2 -0
  270. package/.versions/0.0.10/scripts/lib/hermes-monitor-store.ts +2 -0
  271. package/.versions/0.0.10/scripts/lib/monitor-env.ts +120 -0
  272. package/.versions/0.0.10/scripts/lib/peer-launch.ts +314 -0
  273. package/.versions/0.0.10/scripts/lib/persona-banner.ts +62 -0
  274. package/.versions/0.0.10/scripts/lib/spawn-stagger.ts +101 -0
  275. package/.versions/0.0.10/scripts/lib/team-project.ts +193 -0
  276. package/.versions/0.0.10/scripts/lib/team-snapshot.ts +147 -0
  277. package/.versions/0.0.10/scripts/peer-banner.ts +40 -0
  278. package/.versions/0.0.10/scripts/peer-launch.ts +259 -0
  279. package/.versions/0.0.10/scripts/team-snapshot.ts +237 -0
  280. package/.versions/0.0.10/scripts/team-up.ts +360 -0
  281. package/.versions/0.0.10/skills/_internal/grilling.md +11 -0
  282. package/.versions/0.0.10/skills/browser-testing-with-devtools/SKILL.md +351 -0
  283. package/.versions/0.0.10/skills/code-review-and-quality/SKILL.md +381 -0
  284. package/.versions/0.0.10/skills/compound-learning/SKILL.md +137 -0
  285. package/.versions/0.0.10/skills/context-engineering/SKILL.md +291 -0
  286. package/.versions/0.0.10/skills/deprecation-and-migration/SKILL.md +206 -0
  287. package/.versions/0.0.10/skills/designing-agents/SKILL.md +394 -0
  288. package/.versions/0.0.10/skills/designing-agents/pi-harness-authoring.md +222 -0
  289. package/.versions/0.0.10/skills/frontend-ui-engineering/SKILL.md +328 -0
  290. package/.versions/0.0.10/skills/git-workflow-and-versioning/SKILL.md +316 -0
  291. package/.versions/0.0.10/skills/guided-workspace-setup/SKILL.md +226 -0
  292. package/.versions/0.0.10/skills/guided-workspace-setup/companion-manifest.json +38 -0
  293. package/.versions/0.0.10/skills/idea-refine/SKILL.md +182 -0
  294. package/.versions/0.0.10/skills/idea-refine/examples.md +238 -0
  295. package/.versions/0.0.10/skills/idea-refine/frameworks.md +99 -0
  296. package/.versions/0.0.10/skills/idea-refine/refinement-criteria.md +113 -0
  297. package/.versions/0.0.10/skills/idea-refine/scripts/idea-refine.sh +15 -0
  298. package/.versions/0.0.10/skills/incremental-implementation/SKILL.md +287 -0
  299. package/.versions/0.0.10/skills/interview-me/SKILL.md +226 -0
  300. package/.versions/0.0.10/skills/orchestration-verification/SKILL.md +181 -0
  301. package/.versions/0.0.10/skills/peer-coms/SKILL.md +90 -0
  302. package/.versions/0.0.10/skills/performance-optimization/SKILL.md +350 -0
  303. package/.versions/0.0.10/skills/planning-and-task-breakdown/SKILL.md +254 -0
  304. package/.versions/0.0.10/skills/security-and-hardening/SKILL.md +461 -0
  305. package/.versions/0.0.10/skills/spec-driven-development/SKILL.md +257 -0
  306. package/.versions/0.0.10/skills/using-agent-skills/SKILL.md +199 -0
  307. package/.versions/0.0.10/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  308. package/.versions/0.0.10/vendor/agent-skills-upstream/LICENSE +21 -0
  309. package/.versions/0.0.10/vendor/agent-skills-upstream/README.md +11 -0
  310. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  311. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  312. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  313. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  314. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  315. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  316. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  317. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  318. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  319. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  320. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  321. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  322. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  323. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  324. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  325. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  326. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  327. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  328. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  329. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  330. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  331. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  332. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  333. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  334. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  335. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  336. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  337. package/.versions/0.0.10/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  338. package/.versions/0.0.9/.claude/commands/build.md +44 -0
  339. package/.versions/0.0.9/.claude/commands/code-simplify.md +22 -0
  340. package/.versions/0.0.9/.claude/commands/design-agent.md +14 -0
  341. package/.versions/0.0.9/.claude/commands/doctor-agent-fleet.md +17 -0
  342. package/.versions/0.0.9/.claude/commands/orchestrate.md +112 -0
  343. package/.versions/0.0.9/.claude/commands/plan.md +16 -0
  344. package/.versions/0.0.9/.claude/commands/prime.md +22 -0
  345. package/.versions/0.0.9/.claude/commands/review.md +16 -0
  346. package/.versions/0.0.9/.claude/commands/set-hermes-telegram.md +15 -0
  347. package/.versions/0.0.9/.claude/commands/set-hermes-watchdog.md +6 -0
  348. package/.versions/0.0.9/.claude/commands/setup-agent-fleet.md +25 -0
  349. package/.versions/0.0.9/.claude/commands/ship.md +72 -0
  350. package/.versions/0.0.9/.claude/commands/spec.md +15 -0
  351. package/.versions/0.0.9/.claude/commands/test.md +19 -0
  352. package/.versions/0.0.9/.claude/commands/webperf.md +32 -0
  353. package/.versions/0.0.9/.claude/orchestrate-teams.yaml +24 -0
  354. package/.versions/0.0.9/.opencode/commands/af-build.md +17 -0
  355. package/.versions/0.0.9/.opencode/commands/af-code-simplify.md +16 -0
  356. package/.versions/0.0.9/.opencode/commands/af-compound.md +16 -0
  357. package/.versions/0.0.9/.opencode/commands/af-design-agent.md +15 -0
  358. package/.versions/0.0.9/.opencode/commands/af-doctor-agent-fleet.md +17 -0
  359. package/.versions/0.0.9/.opencode/commands/af-orchestrate.md +112 -0
  360. package/.versions/0.0.9/.opencode/commands/af-plan.md +16 -0
  361. package/.versions/0.0.9/.opencode/commands/af-prime.md +22 -0
  362. package/.versions/0.0.9/.opencode/commands/af-review.md +15 -0
  363. package/.versions/0.0.9/.opencode/commands/af-set-hermes-telegram.md +15 -0
  364. package/.versions/0.0.9/.opencode/commands/af-set-hermes-watchdog.md +6 -0
  365. package/.versions/0.0.9/.opencode/commands/af-setup-agent-fleet.md +15 -0
  366. package/.versions/0.0.9/.opencode/commands/af-ship.md +16 -0
  367. package/.versions/0.0.9/.opencode/commands/af-spec.md +16 -0
  368. package/.versions/0.0.9/.opencode/commands/af-test.md +21 -0
  369. package/.versions/0.0.9/.opencode/commands/af-webperf.md +32 -0
  370. package/.versions/0.0.9/.opencode/orchestrate-teams.yaml +24 -0
  371. package/.versions/0.0.9/.pi/agents/dispatch-policy.yaml +32 -0
  372. package/.versions/0.0.9/.pi/agents/model-profiles.yaml +27 -0
  373. package/.versions/0.0.9/.pi/agents/peers.yaml +142 -0
  374. package/.versions/0.0.9/.pi/agents/teams.yaml +41 -0
  375. package/.versions/0.0.9/.pi/damage-control-rules.yaml +297 -0
  376. package/.versions/0.0.9/.pi/extensions/agent-fleet-update-check/README.md +58 -0
  377. package/.versions/0.0.9/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  378. package/.versions/0.0.9/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  379. package/.versions/0.0.9/.pi/extensions/btw/README.md +118 -0
  380. package/.versions/0.0.9/.pi/extensions/btw/index.ts +917 -0
  381. package/.versions/0.0.9/.pi/extensions/btw/package.json +6 -0
  382. package/.versions/0.0.9/.pi/extensions/btw/state.js +179 -0
  383. package/.versions/0.0.9/.pi/extensions/chrome-devtools-mcp/README.md +58 -0
  384. package/.versions/0.0.9/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  385. package/.versions/0.0.9/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  386. package/.versions/0.0.9/.pi/extensions/compact-and-continue/README.md +42 -0
  387. package/.versions/0.0.9/.pi/extensions/compact-and-continue/index.ts +120 -0
  388. package/.versions/0.0.9/.pi/extensions/compact-and-continue/package.json +6 -0
  389. package/.versions/0.0.9/.pi/extensions/mcp-bridge/README.md +46 -0
  390. package/.versions/0.0.9/.pi/extensions/mcp-bridge/index.ts +206 -0
  391. package/.versions/0.0.9/.pi/extensions/mcp-bridge/package.json +6 -0
  392. package/.versions/0.0.9/.pi/extensions/package-lock.json +1143 -0
  393. package/.versions/0.0.9/.pi/extensions/package.json +9 -0
  394. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/README.md +201 -0
  395. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/config.ts +198 -0
  396. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  397. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/index.ts +248 -0
  398. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/package.json +6 -0
  399. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  400. package/.versions/0.0.9/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  401. package/.versions/0.0.9/.pi/harnesses/agent-hub/README.md +872 -0
  402. package/.versions/0.0.9/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  403. package/.versions/0.0.9/.pi/harnesses/agent-hub/artifacts.js +146 -0
  404. package/.versions/0.0.9/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  405. package/.versions/0.0.9/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  406. package/.versions/0.0.9/.pi/harnesses/agent-hub/context-window.js +106 -0
  407. package/.versions/0.0.9/.pi/harnesses/agent-hub/delegate.ts +435 -0
  408. package/.versions/0.0.9/.pi/harnesses/agent-hub/drift-watchdog.js +211 -0
  409. package/.versions/0.0.9/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  410. package/.versions/0.0.9/.pi/harnesses/agent-hub/footer.ts +31 -0
  411. package/.versions/0.0.9/.pi/harnesses/agent-hub/helpers.ts +248 -0
  412. package/.versions/0.0.9/.pi/harnesses/agent-hub/index.ts +8702 -0
  413. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  414. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  415. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  416. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  417. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  418. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  419. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  420. package/.versions/0.0.9/.pi/harnesses/agent-hub/monitor-session-bridge.ts +257 -0
  421. package/.versions/0.0.9/.pi/harnesses/agent-hub/package.json +7 -0
  422. package/.versions/0.0.9/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  423. package/.versions/0.0.9/.pi/harnesses/agent-hub/research-retention.js +34 -0
  424. package/.versions/0.0.9/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  425. package/.versions/0.0.9/.pi/harnesses/agent-hub/return-contract.js +293 -0
  426. package/.versions/0.0.9/.pi/harnesses/agent-hub/return-extract.js +75 -0
  427. package/.versions/0.0.9/.pi/harnesses/agent-hub/run-budget.js +181 -0
  428. package/.versions/0.0.9/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  429. package/.versions/0.0.9/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  430. package/.versions/0.0.9/.pi/harnesses/agent-hub/session-health.js +110 -0
  431. package/.versions/0.0.9/.pi/harnesses/agent-hub/spawn.ts +354 -0
  432. package/.versions/0.0.9/.pi/harnesses/agent-hub/version.ts +42 -0
  433. package/.versions/0.0.9/.pi/harnesses/ask-user-remote/README.md +19 -0
  434. package/.versions/0.0.9/.pi/harnesses/ask-user-remote/index.ts +321 -0
  435. package/.versions/0.0.9/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  436. package/.versions/0.0.9/.pi/harnesses/coms/README.md +100 -0
  437. package/.versions/0.0.9/.pi/harnesses/coms/index.ts +1767 -0
  438. package/.versions/0.0.9/.pi/harnesses/coms/package.json +7 -0
  439. package/.versions/0.0.9/.pi/harnesses/coms/version.ts +42 -0
  440. package/.versions/0.0.9/.pi/harnesses/damage-control-continue/README.md +124 -0
  441. package/.versions/0.0.9/.pi/harnesses/damage-control-continue/index.ts +536 -0
  442. package/.versions/0.0.9/.pi/harnesses/damage-control-continue/package.json +7 -0
  443. package/.versions/0.0.9/.pi/harnesses/damage-control-continue/version.ts +42 -0
  444. package/.versions/0.0.9/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  445. package/.versions/0.0.9/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  446. package/.versions/0.0.9/.pi/harnesses/lib/herdr-client.ts +472 -0
  447. package/.versions/0.0.9/.pi/harnesses/lib/herdr-presence.ts +399 -0
  448. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  449. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  450. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  451. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  452. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  453. package/.versions/0.0.9/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  454. package/.versions/0.0.9/.pi/harnesses/lib/spawned-peers.js +190 -0
  455. package/.versions/0.0.9/.pi/harnesses/package-lock.json +35 -0
  456. package/.versions/0.0.9/.pi/harnesses/package.json +9 -0
  457. package/.versions/0.0.9/.pi/prompts/af-build.md +24 -0
  458. package/.versions/0.0.9/.pi/prompts/af-code-simplify.md +22 -0
  459. package/.versions/0.0.9/.pi/prompts/af-doctor-agent-fleet.md +15 -0
  460. package/.versions/0.0.9/.pi/prompts/af-plan.md +16 -0
  461. package/.versions/0.0.9/.pi/prompts/af-review.md +16 -0
  462. package/.versions/0.0.9/.pi/prompts/af-set-hermes-telegram.md +15 -0
  463. package/.versions/0.0.9/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  464. package/.versions/0.0.9/.pi/prompts/af-setup-agent-fleet.md +27 -0
  465. package/.versions/0.0.9/.pi/prompts/af-ship.md +17 -0
  466. package/.versions/0.0.9/.pi/prompts/af-spec.md +15 -0
  467. package/.versions/0.0.9/.pi/prompts/af-test.md +19 -0
  468. package/.versions/0.0.9/.pi/skills/bowser/SKILL.md +145 -0
  469. package/.versions/0.0.9/.version +1 -0
  470. package/.versions/0.0.9/agents/architect.md +24 -0
  471. package/.versions/0.0.9/agents/bowser.md +27 -0
  472. package/.versions/0.0.9/agents/builder.md +54 -0
  473. package/.versions/0.0.9/agents/code-reviewer.md +204 -0
  474. package/.versions/0.0.9/agents/deep-researcher.md +32 -0
  475. package/.versions/0.0.9/agents/documenter.md +18 -0
  476. package/.versions/0.0.9/agents/orchestrator.md +66 -0
  477. package/.versions/0.0.9/agents/plan-reviewer.md +62 -0
  478. package/.versions/0.0.9/agents/planner.md +70 -0
  479. package/.versions/0.0.9/agents/releaser.md +24 -0
  480. package/.versions/0.0.9/agents/researcher.md +28 -0
  481. package/.versions/0.0.9/agents/security-auditor.md +167 -0
  482. package/.versions/0.0.9/agents/test-engineer.md +153 -0
  483. package/.versions/0.0.9/agents/web-debugger.md +43 -0
  484. package/.versions/0.0.9/agents/web-performance-auditor.md +193 -0
  485. package/.versions/0.0.9/codex/CONDUCTOR.md +148 -0
  486. package/.versions/0.0.9/docs/ARCHITECTURE.md +262 -0
  487. package/.versions/0.0.9/docs/agent-fleet-setup.md +366 -0
  488. package/.versions/0.0.9/docs/claude-code-coms-bridge.md +109 -0
  489. package/.versions/0.0.9/docs/codex-remote-conductor.md +170 -0
  490. package/.versions/0.0.9/docs/coms-hermes-bridge.md +189 -0
  491. package/.versions/0.0.9/docs/getting-started.md +231 -0
  492. package/.versions/0.0.9/docs/npm-install.md +337 -0
  493. package/.versions/0.0.9/docs/opencode-setup.md +249 -0
  494. package/.versions/0.0.9/docs/pi-extensions.md +356 -0
  495. package/.versions/0.0.9/docs/pi-setup.md +476 -0
  496. package/.versions/0.0.9/docs/skill-anatomy.md +150 -0
  497. package/.versions/0.0.9/hermes/README.md +347 -0
  498. package/.versions/0.0.9/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  499. package/.versions/0.0.9/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  500. package/.versions/0.0.9/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  501. package/.versions/0.0.9/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  502. package/.versions/0.0.9/hermes/gates/gate-o-capability.md +8 -0
  503. package/.versions/0.0.9/hermes/gates/gate-o-validator-fixtures.json +1 -0
  504. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  505. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  506. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  507. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  508. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  509. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  510. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  511. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  512. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  513. package/.versions/0.0.9/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  514. package/.versions/0.0.9/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  515. package/.versions/0.0.9/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  516. package/.versions/0.0.9/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  517. package/.versions/0.0.9/hermes/skills/hub-conductor/SKILL.md +84 -0
  518. package/.versions/0.0.9/hermes/skills/hub-liaison/SKILL.md +84 -0
  519. package/.versions/0.0.9/hermes/skills/hub-watchdog/SKILL.md +76 -0
  520. package/.versions/0.0.9/hermes/skills/hub-watchdog/manifest.json +1 -0
  521. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  522. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  523. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  524. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  525. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  526. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  527. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  528. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  529. package/.versions/0.0.9/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  530. package/.versions/0.0.9/hermes/watchdog-tests/__init__.py +0 -0
  531. package/.versions/0.0.9/hooks/SIMPLIFY-IGNORE.md +90 -0
  532. package/.versions/0.0.9/hooks/coms-stop-hook.mjs +84 -0
  533. package/.versions/0.0.9/hooks/hooks.json +14 -0
  534. package/.versions/0.0.9/hooks/session-start.sh +74 -0
  535. package/.versions/0.0.9/hooks/simplify-ignore.sh +302 -0
  536. package/.versions/0.0.9/justfile +254 -0
  537. package/.versions/0.0.9/references/accessibility-checklist.md +160 -0
  538. package/.versions/0.0.9/references/definition-of-done.md +67 -0
  539. package/.versions/0.0.9/references/fleet-coordination-patterns.md +151 -0
  540. package/.versions/0.0.9/references/observability-checklist.md +91 -0
  541. package/.versions/0.0.9/references/orchestration-patterns.md +370 -0
  542. package/.versions/0.0.9/references/performance-checklist.md +153 -0
  543. package/.versions/0.0.9/references/prompting-patterns.md +380 -0
  544. package/.versions/0.0.9/references/security-checklist.md +179 -0
  545. package/.versions/0.0.9/references/testing-patterns.md +236 -0
  546. package/.versions/0.0.9/scripts/codex-conductor.ts +41 -0
  547. package/.versions/0.0.9/scripts/codex-remote-control.ts +167 -0
  548. package/.versions/0.0.9/scripts/coms-claude-bridge.ts +401 -0
  549. package/.versions/0.0.9/scripts/coms-cli.ts +484 -0
  550. package/.versions/0.0.9/scripts/coms-hermes-bridge.ts +413 -0
  551. package/.versions/0.0.9/scripts/fleet.ts +168 -0
  552. package/.versions/0.0.9/scripts/hermes-monitor-capability-runner.ts +25 -0
  553. package/.versions/0.0.9/scripts/hermes-monitor-scenario.ts +474 -0
  554. package/.versions/0.0.9/scripts/hermes-watchdog-capability-probe.ts +45 -0
  555. package/.versions/0.0.9/scripts/install-hermes-plugin.sh +180 -0
  556. package/.versions/0.0.9/scripts/lib/claude-bridge-core.ts +165 -0
  557. package/.versions/0.0.9/scripts/lib/codex-conductor.ts +88 -0
  558. package/.versions/0.0.9/scripts/lib/codex-remote-control.ts +480 -0
  559. package/.versions/0.0.9/scripts/lib/coms-envelope.ts +582 -0
  560. package/.versions/0.0.9/scripts/lib/fake-herdr-server.ts +88 -0
  561. package/.versions/0.0.9/scripts/lib/fleet-command.ts +111 -0
  562. package/.versions/0.0.9/scripts/lib/herdr-layout.ts +281 -0
  563. package/.versions/0.0.9/scripts/lib/hermes-bridge-core.ts +241 -0
  564. package/.versions/0.0.9/scripts/lib/hermes-monitor-events.ts +1 -0
  565. package/.versions/0.0.9/scripts/lib/hermes-monitor-herdr.ts +2 -0
  566. package/.versions/0.0.9/scripts/lib/hermes-monitor-model.ts +3 -0
  567. package/.versions/0.0.9/scripts/lib/hermes-monitor-registry.ts +2 -0
  568. package/.versions/0.0.9/scripts/lib/hermes-monitor-socket.ts +2 -0
  569. package/.versions/0.0.9/scripts/lib/hermes-monitor-store.ts +2 -0
  570. package/.versions/0.0.9/scripts/lib/monitor-env.ts +120 -0
  571. package/.versions/0.0.9/scripts/lib/peer-launch.ts +314 -0
  572. package/.versions/0.0.9/scripts/lib/persona-banner.ts +62 -0
  573. package/.versions/0.0.9/scripts/lib/spawn-stagger.ts +101 -0
  574. package/.versions/0.0.9/scripts/lib/team-project.ts +193 -0
  575. package/.versions/0.0.9/scripts/lib/team-snapshot.ts +147 -0
  576. package/.versions/0.0.9/scripts/peer-banner.ts +40 -0
  577. package/.versions/0.0.9/scripts/peer-launch.ts +259 -0
  578. package/.versions/0.0.9/scripts/team-snapshot.ts +237 -0
  579. package/.versions/0.0.9/scripts/team-up.ts +360 -0
  580. package/.versions/0.0.9/skills/_internal/grilling.md +11 -0
  581. package/.versions/0.0.9/skills/browser-testing-with-devtools/SKILL.md +352 -0
  582. package/.versions/0.0.9/skills/code-review-and-quality/SKILL.md +381 -0
  583. package/.versions/0.0.9/skills/compound-learning/SKILL.md +137 -0
  584. package/.versions/0.0.9/skills/context-engineering/SKILL.md +291 -0
  585. package/.versions/0.0.9/skills/deprecation-and-migration/SKILL.md +206 -0
  586. package/.versions/0.0.9/skills/designing-agents/SKILL.md +394 -0
  587. package/.versions/0.0.9/skills/designing-agents/pi-harness-authoring.md +222 -0
  588. package/.versions/0.0.9/skills/frontend-ui-engineering/SKILL.md +328 -0
  589. package/.versions/0.0.9/skills/git-workflow-and-versioning/SKILL.md +316 -0
  590. package/.versions/0.0.9/skills/guided-workspace-setup/SKILL.md +544 -0
  591. package/.versions/0.0.9/skills/guided-workspace-setup/companion-manifest.json +38 -0
  592. package/.versions/0.0.9/skills/idea-refine/SKILL.md +182 -0
  593. package/.versions/0.0.9/skills/idea-refine/examples.md +238 -0
  594. package/.versions/0.0.9/skills/idea-refine/frameworks.md +99 -0
  595. package/.versions/0.0.9/skills/idea-refine/refinement-criteria.md +113 -0
  596. package/.versions/0.0.9/skills/idea-refine/scripts/idea-refine.sh +15 -0
  597. package/.versions/0.0.9/skills/incremental-implementation/SKILL.md +287 -0
  598. package/.versions/0.0.9/skills/interview-me/SKILL.md +226 -0
  599. package/.versions/0.0.9/skills/orchestration-verification/SKILL.md +181 -0
  600. package/.versions/0.0.9/skills/peer-coms/SKILL.md +90 -0
  601. package/.versions/0.0.9/skills/performance-optimization/SKILL.md +350 -0
  602. package/.versions/0.0.9/skills/planning-and-task-breakdown/SKILL.md +236 -0
  603. package/.versions/0.0.9/skills/security-and-hardening/SKILL.md +461 -0
  604. package/.versions/0.0.9/skills/spec-driven-development/SKILL.md +245 -0
  605. package/.versions/0.0.9/skills/using-agent-skills/SKILL.md +199 -0
  606. package/.versions/0.0.9/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  607. package/.versions/0.0.9/vendor/agent-skills-upstream/LICENSE +21 -0
  608. package/.versions/0.0.9/vendor/agent-skills-upstream/README.md +11 -0
  609. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  610. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  611. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  612. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  613. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  614. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  615. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  616. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  617. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  618. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  619. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  620. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  621. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  622. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  623. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  624. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  625. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  626. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  627. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  628. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  629. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  630. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  631. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  632. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  633. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  634. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  635. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  636. package/.versions/0.0.9/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  637. package/CHANGELOG.md +141 -0
  638. package/README.md +22 -5
  639. package/agents/architect.md +1 -0
  640. package/agents/bowser.md +1 -0
  641. package/agents/builder.md +1 -0
  642. package/agents/code-reviewer.md +8 -5
  643. package/agents/deep-researcher.md +2 -1
  644. package/agents/orchestrator.md +8 -1
  645. package/agents/plan-reviewer.md +25 -2
  646. package/agents/planner.md +3 -2
  647. package/agents/security-auditor.md +1 -0
  648. package/agents/test-engineer.md +3 -1
  649. package/agents/web-debugger.md +1 -0
  650. package/agents/web-performance-auditor.md +1 -0
  651. package/bin/build-manifest.js +68 -0
  652. package/bin/cli.js +679 -49
  653. package/bin/lib/apply.js +641 -0
  654. package/bin/lib/manifest.js +731 -0
  655. package/bin/lib/merge-forms.js +106 -0
  656. package/bin/lib/plan.js +569 -0
  657. package/bin/lib/state.js +213 -0
  658. package/bin/lib/verify.js +576 -0
  659. package/bin/snapshot-version.js +5 -0
  660. package/docs/ARCHITECTURE.md +53 -12
  661. package/docs/agent-fleet-setup.md +59 -48
  662. package/docs/getting-started.md +29 -6
  663. package/docs/npm-install.md +208 -31
  664. package/docs/opencode-setup.md +32 -0
  665. package/docs/pi-extensions.md +83 -13
  666. package/docs/pi-setup.md +164 -69
  667. package/install-manifest.json +3615 -0
  668. package/justfile +10 -1
  669. package/manifest-meta.json +472 -0
  670. package/package.json +8 -3
  671. package/scripts/fleet.ts +22 -3
  672. package/scripts/lib/fleet-command.ts +5 -3
  673. package/scripts/lib/herdr-layout.ts +18 -0
  674. package/scripts/lib/peer-launch.ts +314 -0
  675. package/scripts/lib/team-project.ts +3 -1
  676. package/scripts/peer-launch.ts +259 -0
  677. package/skills/browser-testing-with-devtools/SKILL.md +3 -4
  678. package/skills/guided-workspace-setup/SKILL.md +172 -490
  679. package/skills/guided-workspace-setup/companion-manifest.json +2 -0
  680. package/skills/planning-and-task-breakdown/SKILL.md +18 -0
  681. package/skills/spec-driven-development/SKILL.md +12 -0
  682. package/.pi/harnesses/agent-hub/spawned-peers.js +0 -74
@@ -1,6 +1,30 @@
1
1
  import { readFileSync } from "node:fs";
2
2
 
3
3
  export const VERSION_STATUS_KEY = "00-agent-fleet-version";
4
+ export const VERSION_LABEL = "agent fleet";
5
+ export const VERSION_LABEL_URL = "https://github.com/chankov/agent-fleet";
6
+
7
+ /**
8
+ * Wrap `text` in an OSC 8 hyperlink. Terminals that support it make the label
9
+ * clickable and hand the URL to the OS opener; terminals that don't ignore the
10
+ * sequence and render `text` unchanged. pi's TUI strips OSC sequences before
11
+ * measuring (`visibleWidth`) and truncating, so a linked label costs no footer
12
+ * columns. Multiplexers that mangle unknown OSC (GNU screen, tmux before 3.4)
13
+ * are the reason for the AGENT_FLEET_NO_LINKS opt-out below.
14
+ */
15
+ export function linkify(text: string, url: string): string {
16
+ return `\x1b]8;;${url}\x07${text}\x1b]8;;\x07`;
17
+ }
18
+
19
+ function linksEnabled(): boolean {
20
+ const optOut = process.env.AGENT_FLEET_NO_LINKS;
21
+ return !optOut || optOut === "0" || optOut === "false";
22
+ }
23
+
24
+ export function formatVersionLabel(version: string): string {
25
+ const label = linksEnabled() ? linkify(VERSION_LABEL, VERSION_LABEL_URL) : VERSION_LABEL;
26
+ return `${label} v${version}`;
27
+ }
4
28
 
5
29
  function readAdjacentVersion(): string | null {
6
30
  try {
@@ -14,5 +38,5 @@ function readAdjacentVersion(): string | null {
14
38
  export const HARNESS_VERSION = readAdjacentVersion();
15
39
 
16
40
  export function registerVersionStatus(ctx: { ui?: { setStatus?: (key: string, text: string) => void } }): void {
17
- if (HARNESS_VERSION) ctx.ui?.setStatus?.(VERSION_STATUS_KEY, `v${HARNESS_VERSION}`);
41
+ if (HARNESS_VERSION) ctx.ui?.setStatus?.(VERSION_STATUS_KEY, formatVersionLabel(HARNESS_VERSION));
18
42
  }
@@ -351,6 +351,16 @@ export const herdr = {
351
351
 
352
352
  // NOTE: the target field is `target_pane_id` — `pane_id` would be silently
353
353
  // ignored and the FOCUSED pane split instead (spike finding).
354
+ //
355
+ // There is NO `command` param: a split always opens a plain interactive
356
+ // shell in `cwd`. Verified against herdr 0.7.5 — `PaneSplitParams` is
357
+ // {target_pane_id, direction, ratio, cwd, env, focus} and `herdr pane split
358
+ // --help` exposes no command flag. Only `layout.apply` pane nodes carry
359
+ // `command: [argv…]`. This type used to advertise `command?: string[]`;
360
+ // because unknown params are silently ignored, callers got a bare shell
361
+ // pane and a success response. To launch something in a split pane, send
362
+ // the command line as input once the pane is at its shell prompt
363
+ // (paneSendText) — see the herdr_spawn_peer tool in agent-hub.
354
364
  paneSplit: (
355
365
  params: {
356
366
  target_pane_id: string;
@@ -359,7 +369,6 @@ export const herdr = {
359
369
  cwd?: string;
360
370
  env?: Record<string, string>;
361
371
  focus?: boolean;
362
- command?: string[];
363
372
  },
364
373
  opts?: HerdrClientOptions,
365
374
  ) => request<{ pane: PaneInfo }>("pane.split", params, opts),
@@ -0,0 +1,190 @@
1
+ // Spawned coms peers: pane launch, readiness policy and the never-addressed sweep.
2
+ //
3
+ // Lives in the SHARED harness lib, not under agent-hub: `just fleet peer`
4
+ // (scripts/peer-launch.ts) launches a single peer with the same pane plumbing
5
+ // and the same readiness timings, and the fleet scripts are installed into
6
+ // target projects that may not have selected the agent-hub harness at all.
7
+ //
8
+ // Root cause this encodes: `herdr_spawn_peer` launches a REUSABLE coms peer —
9
+ // it boots idle and waits for a `coms_send`. Spawning it delivers no work. One
10
+ // session spawned `repair-builder` and `final-test-worker`, sent all twelve of
11
+ // its messages to a third peer, and left two empty panes named like workers.
12
+ // The spawns were a sound reaction to a broken session; nothing told the
13
+ // dispatcher when the peers became addressable, and nothing noticed they never
14
+ // were addressed.
15
+ //
16
+ // Two answers: the spawn returns a readiness verdict instead of a bare pane id,
17
+ // and an unaddressed hub-spawned peer is named at the end of the session.
18
+
19
+ // Second root cause this encodes: herdr's `pane.split` takes NO command — a
20
+ // split always opens a plain interactive shell in `cwd`. The hub used to pass
21
+ // `command: argv` to it; herdr silently ignores unknown params, so every
22
+ // "spawned peer" was an empty shell pane with the right label, the tool
23
+ // reported success, and the peer never existed. `just fleet team` was
24
+ // unaffected because it launches through `layout.apply`, whose pane nodes DO
25
+ // carry an argv. A hub spawn is therefore three steps: split, wait for the
26
+ // pane's shell prompt, then type the command line.
27
+
28
+ /** Longest we wait for a spawned peer to register in the coms pool. */
29
+ export const PEER_READY_TIMEOUT_MS = 45_000;
30
+
31
+ /** Longest we wait for a freshly split pane to reach its shell prompt. */
32
+ export const PANE_PROMPT_TIMEOUT_MS = 10_000;
33
+
34
+ /** Poll interval while watching a new pane for its shell prompt, in ms. */
35
+ export const PANE_PROMPT_POLL_MS = 250;
36
+
37
+ /** Shell metacharacter-free values pass through unquoted; everything else is quoted. */
38
+ const BARE_ARG = /^[A-Za-z0-9._/,:=@%+-]+$/;
39
+
40
+ function shellQuote(arg) {
41
+ const s = String(arg ?? "");
42
+ if (s === "") return "''"; // positional placeholders must survive as empty args
43
+ if (BARE_ARG.test(s)) return s;
44
+ return `'${s.replace(/'/g, `'\\''`)}'`;
45
+ }
46
+
47
+ /**
48
+ * An argv (as built by peerCommand) turned into one line of shell input,
49
+ * newline included. Quoting matters for the empty positional placeholders the
50
+ * `just` recipes use to keep later positionals aligned — unquoted they would
51
+ * vanish and shift `--project` into the model slot.
52
+ */
53
+ export function paneLaunchLine(argv) {
54
+ if (!Array.isArray(argv) || argv.length === 0) {
55
+ throw new Error("paneLaunchLine: empty argv");
56
+ }
57
+ return `${argv.map(shellQuote).join(" ")}\n`;
58
+ }
59
+
60
+ /**
61
+ * Does this pane read end at an interactive shell prompt? Typing before the
62
+ * shell is up can drop the line, and herdr's own `agent.start` refuses a pane
63
+ * that is not at a prompt, so the spawn waits for one. Best-effort by design:
64
+ * the caller sends anyway once PANE_PROMPT_TIMEOUT_MS is spent.
65
+ */
66
+ export function looksLikeShellPrompt(text) {
67
+ if (typeof text !== "string") return false;
68
+ const lines = text.replace(/\r/g, "").split("\n");
69
+ while (lines.length > 0 && lines[lines.length - 1].trim() === "") lines.pop();
70
+ if (lines.length === 0) return false;
71
+ return /[$#%>❯➜›]\s*$/.test(lines[lines.length - 1]);
72
+ }
73
+
74
+ /**
75
+ * Launch an argv in a freshly split pane by typing it at the pane's shell.
76
+ * `client` is the herdr client (paneRead/paneSendText/paneSendKeys).
77
+ *
78
+ * Text and Enter go as separate calls on purpose: bash enables bracketed
79
+ * paste, where a newline inside sent text is inserted into the line editor
80
+ * instead of executing it. A pane that never shows a prompt still gets the
81
+ * command — the shell's input queue survives a slow banner — but the caller
82
+ * is told, because that is also what a pane whose shell died looks like.
83
+ */
84
+ export async function launchPeerInPane(client, paneId, argv, opts = {}) {
85
+ const {
86
+ timeoutMs = PANE_PROMPT_TIMEOUT_MS,
87
+ pollMs = PANE_PROMPT_POLL_MS,
88
+ now = Date.now,
89
+ sleep = (ms) => new Promise((resolve) => setTimeout(resolve, ms)),
90
+ } = opts;
91
+ const line = paneLaunchLine(argv).replace(/\n$/, "");
92
+ const started = now();
93
+ let promptSeen = false;
94
+ for (;;) {
95
+ try {
96
+ const { read } = await client.paneRead({ pane_id: paneId, lines: 5 });
97
+ if (looksLikeShellPrompt(read?.text ?? "")) {
98
+ promptSeen = true;
99
+ break;
100
+ }
101
+ } catch {
102
+ // Pane not readable yet; the timeout below bounds the wait.
103
+ }
104
+ if (now() - started >= timeoutMs) break;
105
+ await sleep(pollMs);
106
+ }
107
+ await client.paneSendText(paneId, line);
108
+ await client.paneSendKeys(paneId, ["enter"]);
109
+ return { promptSeen, waitedMs: now() - started };
110
+ }
111
+
112
+ /**
113
+ * Seconds a hub-spawned pi peer should sleep before launching (the justfile
114
+ * recipes honor it as AGENT_FLEET_SPAWN_DELAY). Same stale-OAuth lock race
115
+ * that staggers team spawns: the first peer refreshes the token, so only a
116
+ * sibling spawned inside the warm-up window has to wait. `needed` is
117
+ * oauthNeedsWarmup() re-read at each spawn — once the warmer lands a fresh
118
+ * token it goes false and nobody waits.
119
+ */
120
+ export function spawnStaggerSeconds({ needed, lastSpawnAt, now, warmupSeconds }) {
121
+ if (!needed || !Number.isFinite(warmupSeconds) || warmupSeconds <= 0) return 0;
122
+ if (typeof lastSpawnAt !== "number" || !Number.isFinite(lastSpawnAt)) return 0;
123
+ if (now - lastSpawnAt >= warmupSeconds * 1000) return 0;
124
+ return warmupSeconds;
125
+ }
126
+
127
+ /** Poll backoff while waiting for registration, in ms; the last step repeats. */
128
+ export const PEER_READY_BACKOFF_MS = [250, 500, 1_000, 2_000, 3_000];
129
+
130
+ /** Backoff delay for the nth readiness poll (0-based); the last step repeats. */
131
+ export function peerReadyDelayMs(attempt) {
132
+ const i = Math.max(0, Math.min(Math.floor(attempt) || 0, PEER_READY_BACKOFF_MS.length - 1));
133
+ return PEER_READY_BACKOFF_MS[i];
134
+ }
135
+
136
+ /**
137
+ * The verdict a spawn reports back. `ready` means the peer is in the pool and
138
+ * `coms_send` will reach it; otherwise it is still booting and the caller is
139
+ * told how long we waited rather than being left to guess.
140
+ */
141
+ export function peerReadyVerdict({ name, paneId, found, waitedMs, timeoutMs = PEER_READY_TIMEOUT_MS, paneTail }) {
142
+ if (found) {
143
+ return {
144
+ peer_ready: true,
145
+ peer_name: name,
146
+ pane_id: paneId,
147
+ waited_ms: waitedMs,
148
+ message:
149
+ `Peer "${name}" is ready in pane ${paneId} after ${Math.round(waitedMs / 1000)}s — ` +
150
+ `address it with coms_send(target: "${name}", ...). It boots idle and does no work until you send.`,
151
+ };
152
+ }
153
+ // A peer that missed the window is usually dead, not slow, so the verdict
154
+ // carries the pane's own last words instead of sending the caller off to
155
+ // run herdr_read_pane to find out.
156
+ const tail = typeof paneTail === "string" ? paneTail.trim() : "";
157
+ return {
158
+ peer_ready: false,
159
+ peer_name: name,
160
+ pane_id: paneId,
161
+ waited_ms: waitedMs,
162
+ pane_tail: tail || null,
163
+ message:
164
+ `Peer "${name}" did not register in the coms pool within ${Math.round(timeoutMs / 1000)}s — ` +
165
+ `assume it failed to start rather than that it is slow. Do not coms_send to it. ` +
166
+ `Check coms_list; if it never appears, close the pane with herdr_close_pane.` +
167
+ (tail ? `\n\nLast output of pane ${paneId}:\n${tail}` : ""),
168
+ };
169
+ }
170
+
171
+ /**
172
+ * Sweep report for peers this hub spawned. `entries` carry
173
+ * { name, paneId, addressed } — `addressed` is true once any coms_send targeted
174
+ * that peer. Returns null when every spawned peer got work (the common case).
175
+ */
176
+ export function unaddressedPeerSweep(entries) {
177
+ const idle = (Array.isArray(entries) ? entries : []).filter((e) => e && !e.addressed);
178
+ if (idle.length === 0) return null;
179
+ const rows = idle.map((e) => ` ${e.name} (pane ${e.paneId ?? "?"}) — spawned, never sent to`);
180
+ return {
181
+ count: idle.length,
182
+ peers: idle.map((e) => ({ name: e.name, pane_id: e.paneId ?? null })),
183
+ message: [
184
+ `⚠ ${idle.length} hub-spawned peer(s) never received a message:`,
185
+ ...rows,
186
+ "A spawned peer boots idle and waits — it is holding a pane and a model session for nothing.",
187
+ `Close them with herdr_close_pane (asks for your confirmation) or send them work.`,
188
+ ].join("\n"),
189
+ };
190
+ }
@@ -2,14 +2,21 @@
2
2
  description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
3
3
  ---
4
4
 
5
- Load and follow Step 5 (Doctor preflight) of the `guided-workspace-setup` skill — without running the rest of the install flow. Use this when the user wants the repair pass on its own; the full `/af-setup-agent-fleet` flow runs the same scan automatically as soon as it detects prior install state.
5
+ Load and follow the `guided-workspace-setup` skill's repair path — without running the rest of the install flow. Use this when the user wants the repair pass on its own; `/af-setup-agent-fleet` offers the same thing as soon as it finds prior install state.
6
6
 
7
- Walk every install-target directory the chosen coding agent uses (`agents/`, `.claude/agents/`, `.opencode/agent/` (+ legacy `.opencode/agents/`), `.pi/agents/`, `.claude/skills/`, `.opencode/skills/`, `.pi/skills/`, `.agents/skills`, `.claude/commands/`, `.opencode/commands/`, `.pi/prompts/`, `.claude/references/`, `.claude/hooks/`). For each broken symlink, resolve where it pointed, look for a canonical replacement in the source `agents/` and `skills/` trees, and offer to repair or delete (persona links under `.claude/agents/` and `.opencode/agent(s)/` are repaired by regenerating a transformed copy via `transform-persona`, not by re-symlinking the raw source). Common stale names from the pre-merge persona layout: `reviewer` → `code-reviewer`, `red-team` → `security-auditor`.
7
+ Run the CLI — do not walk directories or repair files yourself:
8
8
 
9
- Also flag and offer to rewrite any remaining YAML configs (`teams.yaml`, `peers.yaml`, etc.) that still reference removed persona names.
9
+ ```
10
+ node <source-root>/bin/cli.js doctor --workspace <workspace> [--agent <agent>] --json
11
+ ```
10
12
 
11
- 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, missing `rules:` folders, and `## env` `required:` names that are neither set nor declared in the root `.env`. These findings are advisory only — report them with fix "edit by hand", never edit the overrides file.
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.
12
14
 
13
- Present the findings per the skill's Step 1 interaction contract: print a short text summary (counts per kind, advisory findings as report-only text), then ask one `ask_user` multi-select — *"Which fixes should I apply now?"* — each option titled `<path> — <issue>` with the proposed fix as its description, chunked at ≤ 9 options; empty selection or cancel applies nothing. Without the widget, print a `# | Path | Issue | Suggested fix` table instead and take the picks as text.
15
+ The report has two halves, and they are repaired differently on purpose:
14
16
 
15
- Never overwrite a regular file — only act on symlinks whose target is missing. Report `repaired`, `deleted`, and `skipped` counts, and append a `## doctor-runs` line to `.ai/agent-fleet-setup.md` with the date, agent, phase (`standalone`), and counts.
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 `ask_user` single-select (or a plain text question without the 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.
@@ -4,24 +4,16 @@ description: Guided setup — install agent-fleet artifacts into a workspace for
4
4
 
5
5
  Load and follow the `guided-workspace-setup` skill before proceeding.
6
6
 
7
- Run the guided install for a target workspace. If the user passed a workspace path, use it; otherwise ask for it. Detect the running coding agent and confirm it with the user.
7
+ Run the guided install for a target workspace. If the user passed a workspace path, use it; otherwise ask. Confirm the coding agent (`pi` here unless the user says otherwise).
8
8
 
9
- Analyse the workspace. If prior install state is found (`.ai/agent-fleet-setup.md` or a populated agent directory), run the **Doctor preflight** first (Step 5) — scan for broken symlinks and stale persona references, present findings as a table, and apply the fixes the user picks before continuing.
9
+ The skill is a front-end over the `agent-fleet` CLI's installer engine: `verify --json` supplies the menu (groups, profiles, per-item state), and `install` / `upgrade` / `uninstall` / `doctor --fix` do every write. **Do not copy, symlink, or delete an install target yourself** — the CLI records ownership in `.ai/agent-fleet-state.json`, and anything written by hand is invisible to every later run. The harness/extension closures (Fleet Core, the `justfile` managed region, the `.pi/agents` configs, the runtime script closure) are manifest data, so the CLI already pulls them in; you do not restate or reassemble them. Artifacts install as copies; never ask copy-vs-symlink and never pass `--method`.
10
10
 
11
- **Bootstrap `pi-ask-user` first (Step 5b).** Before the install menu, check whether the `pi-ask-user` interaction package is available (bundled by `@chankov/agent-fleet`, recorded as a project package, or global). If it is missing, offer to install it project-scoped (`pi install -l npm:pi-ask-user`), record it as an external/project pi package, then **stop the pass** and ask the user to reload pi and re-run `/af-setup-agent-fleet`. The tool only becomes callable after reload, and on the re-run the menu uses its native multi-select widget. Only fall back to a text menu in this pass if the user *declines* the bootstrap.
11
+ Two things are yours rather than the CLI's: drafting `.ai/agent-fleet-overrides.md` from a scan of the project, and the `pi-voice-stt` provider Q&A (`.ai/stt.json` names env vars; the key goes in a gitignored `.env`).
12
12
 
13
- The Skills group draws from **two roots**: fleet-native `skills/` and the vendored upstream import `vendor/agent-skills-upstream/skills/` (see `docs/UPSTREAM-SKILLS.md`). On a name collision the native copy wins — never offer the vendored duplicate as a separate row.
13
+ **Bootstrap `pi-ask-user` first.** Before the menu, check whether the interaction package is available (bundled by `@chankov/agent-fleet`, recorded as a project package, or global). If it is missing, offer `pi install -l npm:pi-ask-user`, then **stop the pass** and ask the user to reload pi and re-run `/af-setup-agent-fleet` — the widget is not callable until then. Fall back to a text menu in this pass only if the user declines.
14
14
 
15
- Then present the install menu per the skill's Step 1 interaction contract — drive every decision through the `ask_user` widget, never a printed table awaiting a free-text reply (the table format is reserved for the no-widget fallback when the user declined the bootstrap). Open with the **Express question** (fresh workspace: `Recommended ★` / `Everything` / `Custom — group by group` / `Nothing`; existing: `Keep as-is` / `Apply updates` / `Keep + add recommended ★` / `Custom`) — any answer but `Custom` skips all group screens. On `Custom`, run the **7 groups** (4 shared: Skills, Agent personas, Commands/prompts, References & Hooks; 3 pi-only: pi extensions & runtime skills, pi harnesses, External pi packages): each opens as a single-select quick screen (`Recommended ★ (n)` / `Everything (m)` / `Customise` / `Skip group`, or the installed-state variants with `Remove some…`), and multi-select drill-ins appear only behind `Customise`, chunked by sub-category (lifecycle phase for Skills, `rw`/`ro`/`pi-only` for personas, harness category, …) at ≤ 9 options per call, ≤ 8 `context` lines. Option titles carry `name ★ [st]` (`ok`/`upd`/`mod`/`cflt`/`gone`/`new`/`pkg`/`—`/`brk`); descriptions carry the purpose plus the state in plain words (`mod` → warn that refreshing overwrites local edits). There is **no pre-checking** (`ask_user` has no preselect) — installed state shows as counts on quick screens and words in descriptions; leaving an installed item unselected in a drill-in keeps it as-is. Freeform stays on so `all` / `recommended` (adds `★` on top — never removes) / `none` / `keep` still work; cancel = keep-as-is/skip. `cflt` rows are resolved only by printing the three-way diff and asking per row with `displayMode: "inline"` — never by Express or `Apply updates`. The External pi packages group lists `pi-ask-user` and the optional suggested `pi-codex-image-gen`. After Step 5b, `pi-ask-user` normally counts toward `Keep as-is` (`pkg`, scope `project` / `bundled by @chankov/agent-fleet` / `global` — state it in the restate line, no duplicate entries). `pi-codex-image-gen` is not bundled or bootstrapped; offer `pi install -l npm:pi-codex-image-gen` only when the user selects it. Never offer `setup`, `doctor`, or `guided-workspace-setup` — those are installer-only and live in the source agent-fleet repo.
15
+ Drive every decision through the `ask_user` widget: ≤ 9 options and ≤ 8 `context` lines per call, options carrying the data (never a table in `context`). Open with the Express question backed by the manifest's profiles; group screens run only on `Custom`; drill-ins appear only behind `Customise`. Option titles carry `<name> ★ [state]`, descriptions say what picking it does in plain words. Leaving an installed item unpicked keeps it — removal is its own explicit screen and runs `uninstall`. Cancel is a no-op everywhere except the final confirmation.
16
16
 
17
- Removal happens **only** on an explicit `Remove some…` multi-select (empty selection = remove nothing), and it is scoped: the screen lists only items whose name is in the agent-fleet inventory **and** that are recorded in `## install-status` (or are symlinks resolving into the source repo). User-authored skills, custom commands, third-party plugins, external pi packages not recorded by this setup, and unrelated settings/env keys are left untouched and logged as "Skipped — not owned by agent-fleet".
17
+ If `verify` reports findings or broken items, offer `doctor --fix` before the menu — a broken workspace makes the menu lie about what is installed.
18
18
 
19
- **No cross-tool substitution.** Each row is offered only when the source file the chosen agent needs already exists — for `pi`, that means `.pi/prompts/<name>.md`, `.pi/extensions/<name>/`, etc. Never fall back to `.claude/commands/` (or another agent's tree) to satisfy a pi prompt request; items missing their per-agent source are filtered out of the menu entirely.
20
-
21
- **Personas are generated for non-pi targets.** The personas group lists the full availability roster from `node <source-root>/bin/cli.js transform-persona --list --agent <agent>`. For `pi` the canonical `agents/<name>.md` installs as-is (copy or symlink). For `claude-code`/`opencode` the apply step runs `transform-persona --agent <agent> --workspace <workspace> <name…>` instead — always a generated copy, even in symlink mode — and records the rows with `transformed: true`; status checks diff against the generated output, not the raw source.
22
-
23
- **pi harness companions.** Installing, refreshing, or removing any pi harness also refreshes its companions in the same pass — the `justfile` launch recipes, `scripts/team-up.ts`, the peer/team YAML and personas, `.pi/damage-control-rules.yaml`, and `.pi/harnesses/package.json`. When `agent-hub` is installed or kept, keep its required launch companions together: `damage-control-continue` and `ask-user-remote`; the managed `just hub` / `hub-solo` recipes load both before `agent-hub`, and every native child inherits continue. Treat the retired `damage-control` hard-stop directory as `gone`: remove it only when recorded and unchanged against the recorded snapshot, or when it is a symlink into the source root (including a broken retirement link); preserve every user-modified or unowned copy. Refresh the `justfile` from the **current** source so retired-harness recipes are pruned and new ones added, rewriting only the managed region between the `agent-fleet:harnesses` sentinels so any user recipes survive.
24
-
25
- **No mid-apply overwrite prompts.** The `mod` description already warns that refreshing overwrites local edits. The user's selection is the consent; the Step 9 confirmation is the single gate. During apply, refresh selected items unconditionally — never pause to ask "should I overwrite this file?". Genuine errors (permission denied, missing source) still stop and report.
26
-
27
- Offer override sections for the workspace's `.ai/agent-fleet-overrides.md` based on the analysis (print each draft, then `Accept` / `Edit` / `Skip` per section via `ask_user`), and record what was installed in `.ai/agent-fleet-setup.md`. Print the plan as compact action-grouped lines (Add / Refresh / Remove / Keep-count / Records / Method), then confirm with one `ask_user` single-select asked with `displayMode: "inline"` — `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel` — and write nothing until an Apply is chosen. Then perform the setup, re-scan for any new breakage, and report what changed.
19
+ Print the plan as compact action-grouped lines before confirming, then confirm with one `displayMode: "inline"` single-select: `Apply — and remove the installer commands` (default) / `Apply — keep the installer commands` / `Adjust picks` / `Cancel`. Ask before passing `--allow-exec` (the `npm ci` steps). Exit `3` means conflicts: show the `.new` files the CLI wrote and let the user decide — never pick a side for them. Relay `operator` and `external` steps verbatim; the CLI performs neither, and neither do you.
@@ -0,0 +1,44 @@
1
+ ---
2
+ description: Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
3
+ ---
4
+
5
+ Invoke the agent-fleet:incremental-implementation skill alongside agent-fleet:test-driven-development.
6
+
7
+ ## Modes
8
+
9
+ - **`/build`** — implement the *next* pending task, then stop (careful, one slice at a time).
10
+ - **`/build auto`** — generate the plan if needed, get a single approval, then implement *every* task without stopping between them.
11
+
12
+ `$ARGUMENTS` selects the mode. Treat `auto` (canonical) or `all` as autonomous mode; anything else (or empty) is the default single-task mode. Note: autonomous mode is not faster *per task* — it runs the same test-driven loop — it only removes the human stepping *between* tasks.
13
+
14
+ ## Default: one task
15
+
16
+ Pick the next pending task from the plan. Then:
17
+
18
+ 1. Read the task's acceptance criteria
19
+ 2. Load relevant context (existing code, patterns, types)
20
+ 3. Write a failing test for the expected behavior (RED)
21
+ 4. Implement the minimum code to pass the test (GREEN)
22
+ 5. Run the full test suite to check for regressions
23
+ 6. Run the build to verify compilation
24
+ 7. Commit with a descriptive message
25
+ 8. Mark the task complete and stop
26
+
27
+ ## Autonomous: the whole plan (`/build auto`)
28
+
29
+ Use this once a spec exists and you want to collapse plan + build into one run. It removes the manual stepping between tasks — **not** the verification. Every task still earns a passing test and its own commit.
30
+
31
+ 1. **Require a spec.** Look only for a spec at a known path: `SPEC.md` at the repo root, `docs/SPEC.md`, or a file under `spec/`. A README or arbitrary doc does **not** count. If none exists, stop and tell the user to run `/spec` first — do not invent requirements.
32
+ 2. **Establish a clean baseline.** Run `git status --porcelain`. If there are uncommitted changes outside the expected planning artifacts (`SPEC.md`, `docs/SPEC.md`, `spec/*`, `tasks/plan.md`, `tasks/todo.md`), stop and ask the user to commit, stash, or confirm how to handle them. Autonomous per-task commits must not absorb unrelated local work, or the clean-rollback guarantee breaks.
33
+ 3. **Plan if needed.** If there is no `tasks/plan.md`, invoke agent-fleet:planning-and-task-breakdown to generate one.
34
+ 4. **Single checkpoint.** Present the full plan and wait for an unambiguous affirmative (e.g. "approve", "go", "yes"). Treat hedged responses ("looks reasonable", "I guess") as **not** approved. This is the only human gate — after approval, run autonomously. If you generated `tasks/plan.md`, commit it as a single preparatory commit now so it doesn't bleed into the first task's commit.
35
+ 5. **Execute every task in dependency order.** Use each task's declared dependencies; if they aren't explicit, execute in the order the plan lists them. For each task, run the full default loop above (RED → GREEN → regression → build → commit → mark complete). Stage only the files that task touched plus its task-status update — never `git add -A` blindly — and make one commit per task so any point is a clean rollback.
36
+ 6. **Stop and ask the user** (do not push through) when:
37
+ - a test can't be made to pass or the build breaks without an obvious fix → follow agent-fleet:debugging-and-error-recovery
38
+ - the spec is ambiguous, or a task needs a decision the spec doesn't cover
39
+ - a task is high-risk or irreversible — auth/permission changes, destructive data migrations, payments, deletions, deploys, anything touching secrets, **or anything you can't undo with `git revert`** → follow agent-fleet:doubt-driven-development and get explicit sign-off before continuing
40
+
41
+ After the user resolves a blocker, they re-invoke `/build auto` — it resumes from the next pending task.
42
+ 7. **Summarize at the end:** tasks completed, tests added, commits made, and anything skipped, flagged, or left for the user.
43
+
44
+ If any step fails, follow the agent-fleet:debugging-and-error-recovery skill.
@@ -0,0 +1,22 @@
1
+ ---
2
+ description: Simplify code for clarity and maintainability — reduce complexity without changing behavior
3
+ ---
4
+
5
+ Invoke the agent-fleet:code-simplification skill.
6
+
7
+ Simplify recently changed code (or the specified scope) while preserving exact behavior:
8
+
9
+ 1. Read CLAUDE.md and study project conventions
10
+ 2. Identify the target code — recent changes unless a broader scope is specified
11
+ 3. Understand the code's purpose, callers, edge cases, and test coverage before touching it
12
+ 4. Scan for simplification opportunities:
13
+ - Deep nesting → guard clauses or extracted helpers
14
+ - Long functions → split by responsibility
15
+ - Nested ternaries → if/else or switch
16
+ - Generic names → descriptive names
17
+ - Duplicated logic → shared functions
18
+ - Dead code → remove after confirming
19
+ 5. Apply each simplification incrementally — run tests after each change
20
+ 6. Verify all tests pass, the build succeeds, and the diff is clean
21
+
22
+ If tests fail after a simplification, revert that change and reconsider. Use `code-review-and-quality` to review the result.
@@ -0,0 +1,14 @@
1
+ ---
2
+ description: Design and write a new agent persona (agents/), workflow skill (skills/), or pi harness (.pi/harnesses/)
3
+ ---
4
+
5
+ Invoke the agent-fleet:designing-agents skill.
6
+
7
+ Begin by understanding what the user wants to author:
8
+ 1. Is this a **persona** (a role/lens the agent adopts, e.g. a reviewer or auditor), a **skill** (a repeatable workflow with gated steps and verification), or a **pi harness** (a TypeScript pi extension that reshapes the session — footer, tool-call gate, new command, or orchestrator)?
9
+ 2. The one-sentence purpose and when it should be invoked
10
+ 3. The framework or steps — dimensions evaluated (persona), ordered workflow (skill), or session surface and events hooked (harness)
11
+ 4. Explicit non-goals and scope limits
12
+ 5. Output shape — what a typical invocation should produce
13
+
14
+ Then scan the target location (`agents/`, `skills/`, or `.pi/harnesses/`) for overlap, draft the artifact using the matching template — four-block persona structure, the section order from `docs/skill-anatomy.md`, or the harness pattern in `skills/designing-agents/pi-harness-authoring.md` — verify the draft against `references/prompting-patterns.md`, and confirm with the user before writing the file(s).
@@ -0,0 +1,22 @@
1
+ ---
2
+ description: Scan agent-fleet install targets for broken symlinks, stale persona references, and overrides-file problems, then offer repairs
3
+ ---
4
+
5
+ Run the repair pass on its own. `/setup-agent-fleet` offers the same thing as soon as it finds prior install state; this command is when the user wants only that.
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 command'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 `AskUserQuestion` — *"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.
@@ -0,0 +1,112 @@
1
+ ---
2
+ description: Orchestrate a config-defined team of subagents — route planner/builder (and more) as a runtime roster, handling NEEDS_RESEARCH and PLAN_FILE handoffs
3
+ ---
4
+
5
+ You are the **orchestrator**. The primary agent drives a team of installed Claude Code
6
+ subagents to deliver the task in `$ARGUMENTS`. Subagents cannot nest — **all dispatching is
7
+ yours**.
8
+
9
+ ## Roles
10
+
11
+ | Role | What it does |
12
+ |---|---|
13
+ | `researcher` | Always-available read-only recon. Cites `file:line`. Never edits. |
14
+ | `planner` | Writes a plan doc only; ends with `PLAN_FILE: <path>` or pauses on `NEEDS_RESEARCH:`. |
15
+ | `builder` | Implements in small increments; may pause on `NEEDS_RESEARCH:`. |
16
+ | `plan-reviewer` / `code-reviewer` | Read-only; their whole result is findings (no handoff marker). |
17
+
18
+ ## Step 0 — Resolve the team
19
+
20
+ 1. Read `.claude/orchestrate-teams.yaml` (a map of team-name → ordered persona list).
21
+ 2. Resolve team + task from `$ARGUMENTS`:
22
+ - Treat the **first token** as a team name **only** when it is a bare single word that
23
+ exactly matches a config key **and** is followed by the rest of the task. To force a
24
+ team explicitly, the user writes `/orchestrate team=<name> <task>`. Otherwise the
25
+ team is the first key (`default`) and all of `$ARGUMENTS` is the task.
26
+ - **Fallbacks:** if the config is **absent / empty / fails to parse**, fall back to the
27
+ built-in `planner` + `builder` default and **say which fallback fired** (don't proceed
28
+ silently). If a named team is requested but not found, list the available team keys and
29
+ ask rather than guessing.
30
+ 3. **Validate personas:** each persona in the resolved team must exist in `.claude/agents/`.
31
+ Skip-with-warning any that don't. If every persona is missing, fall back to the built-in
32
+ default.
33
+ 4. List the resolved team back to the user before dispatching.
34
+
35
+ `researcher` / `deep-researcher` are **always available** even when not listed in the team.
36
+
37
+ ## Step 1 — The team is a roster, not a fixed pipeline
38
+
39
+ The persona list is the set of specialists you may route to; **you decide the order at
40
+ runtime from the task state** (the listed order is only a sensible starting default). So:
41
+
42
+ - **Skip `planner`** when a usable plan already exists (the user passed a `PLAN_FILE` or
43
+ pointed at one) — go straight to `builder`.
44
+ - **Re-dispatch `researcher` at any point** — after `planner`, mid-build — whenever a
45
+ specialist needs a fact checked, not only as a first step.
46
+ - **Loop back to `planner`** if `builder` surfaces that the plan is wrong.
47
+
48
+ Do **not** enforce a hard `researcher → planner → builder` sequence.
49
+
50
+ ## The Verification Contract (applies across every step)
51
+
52
+ Read `skills/orchestration-verification/SKILL.md` before non-trivial work and hold its
53
+ contract for the whole run. Subagents here cannot persist a shared ledger, so **you** keep
54
+ the acceptance assertions in your own working notes and refuse "done" until each is proven.
55
+
56
+ - **Build the assertions first.** Before dispatching `builder` for any non-trivial task,
57
+ convert the request into numbered, tagged assertions (`test` | `runtime-ui` | `code-grep`
58
+ | `manual`, one checkable pass condition each). Pass the relevant assertions **verbatim**
59
+ into each dispatch and advance only on assertions that come back *proven with named
60
+ evidence* — propagation in prose is not verification.
61
+ - **Inventory parity for "behave like X" requests.** When the request is "make X behave like
62
+ existing Y", dispatch `researcher` / `deep-researcher` **first** to enumerate every site
63
+ where the exemplar is special-cased (flags, branches, display, validation, translations,
64
+ fixtures, tests), and turn each site into an assertion covering the *whole* set — otherwise
65
+ the exemplar ships and its siblings are missed.
66
+ - **Require runtime proof for UI assertions.** A `runtime-ui` assertion (visibility,
67
+ placement, "appears in the table") is closed only by an actual runtime observation via
68
+ `browser-testing-with-devtools`, never a static review.
69
+ - **Accept assertion status, not verdicts.** Treat specialist returns as `assertions_proven`
70
+ / `assertions_unproven` / `assertions_failed`; demote any "approved" claim with no named
71
+ evidence to unproven and re-dispatch it.
72
+ - **Reset on "wrong again".** When the user reports a delivered requirement is wrong again,
73
+ treat prior summaries as suspect, rebuild the affected assertions from the **latest**
74
+ correction (re-running the parity inventory for "behave like" cases), then re-dispatch.
75
+
76
+ ## Step 2 — Route to specialists, honouring handoff markers
77
+
78
+ State the chosen next step (and why) before each dispatch, so routing is visible.
79
+
80
+ - `planner` → read its `PLAN_FILE: <path>` and load the plan.
81
+ - `builder` → loop over the plan's `## Task List`, **one task per dispatch**, checking each
82
+ task's acceptance criteria **and the relevant acceptance assertions** before moving on.
83
+ - **Marker-less personas** (`plan-reviewer` / `code-reviewer`) emit no handoff marker —
84
+ their returned report **is** the result; "done" = the report came back, nothing to wait
85
+ for. Fold findings forward; if a `code-reviewer` raised must-fix issues, loop back to
86
+ `builder`.
87
+
88
+ ## Step 3 — NEEDS_RESEARCH dispatch (core)
89
+
90
+ Whenever any persona's result contains one or more `NEEDS_RESEARCH: <question>` lines:
91
+
92
+ 1. Pause that track.
93
+ 2. Dispatch `researcher` (read-only) once per question — in parallel when independent.
94
+ 3. Collect the findings.
95
+ 4. Resume the paused persona by re-dispatching it with the **original task plus the
96
+ findings inlined**.
97
+
98
+ **Never** answer a `NEEDS_RESEARCH` by guessing.
99
+
100
+ ## Step 4 — Reviewer only if present
101
+
102
+ The `default` roster has **no reviewer**. After the final builder task's acceptance criteria
103
+ pass, report completion and **state explicitly that review/verification was not run** and
104
+ which acceptance assertions therefore remain unproven (the user can pick the `full` team or
105
+ run `/review`). When the active team *does* include a reviewer, run it as a normal step and
106
+ require it to report parity across sibling cases, not just the exemplar.
107
+
108
+ ## Step 5 — Report
109
+
110
+ Report crisply: **active team**, what changed, which acceptance assertions are **proven (with
111
+ evidence)**, which remain **unproven or failed**, and what's next. Never report "done" while a
112
+ relevant assertion is unproven.
@@ -0,0 +1,16 @@
1
+ ---
2
+ description: Break work into small verifiable tasks with acceptance criteria and dependency ordering
3
+ ---
4
+
5
+ Invoke the agent-fleet:planning-and-task-breakdown skill.
6
+
7
+ Read the existing spec (SPEC.md or equivalent) and the relevant codebase sections. Then:
8
+
9
+ 1. Enter plan mode — read only, no code changes
10
+ 2. Identify the dependency graph between components
11
+ 3. Slice work vertically (one complete path per task, not horizontal layers)
12
+ 4. Write tasks with acceptance criteria and verification steps
13
+ 5. Add checkpoints between phases
14
+ 6. Present the plan for human review
15
+
16
+ Save the plan to the location the `planning-and-task-breakdown` skill defines (default `docs/plans/{area}/PLAN-{prd-name}-{phase}.md`, with the task list embedded — no separate todo file; overridable per project via `.ai/agent-fleet-overrides.md`). Match the project's existing `docs`/`Docs` capitalization.
@@ -0,0 +1,22 @@
1
+ ---
2
+ description: Load foundational context for the agent-fleet repository
3
+ ---
4
+
5
+ # Purpose
6
+
7
+ Orient yourself in **agent-fleet** — a collection of production-grade engineering skills
8
+ for AI coding agents, plus pi extensions, specialist agent personas, and lifecycle
9
+ commands that map to the software development lifecycle.
10
+
11
+ ## Workflow
12
+
13
+ 1. Run `git ls-files` to see the full project file tree
14
+ 2. Read `README.md` and `CLAUDE.md` for the project overview and conventions
15
+ 3. Read `docs/skill-anatomy.md` to learn the required skill format
16
+ 4. Skim `skills/*/SKILL.md` — the core skills, grouped by lifecycle phase
17
+ (Define → Plan → Build → Verify → Review → Ship)
18
+ 5. Read `agents/*.md` — the specialist review personas
19
+ 6. Read `docs/pi-extensions.md`, `.pi/extensions/*/README.md` (always-on utilities), and `.pi/harnesses/*/README.md` (selectable session harnesses)
20
+ 7. Summarize your understanding: purpose, structure, key files, and entry points
21
+
22
+ Do this directly — read the files yourself rather than delegating to subagents.
@@ -0,0 +1,16 @@
1
+ ---
2
+ description: Conduct a five-axis code review — correctness, readability, architecture, security, performance
3
+ ---
4
+
5
+ Invoke the agent-fleet:code-review-and-quality skill.
6
+
7
+ Review the current changes (staged or recent commits) across all five axes:
8
+
9
+ 1. **Correctness** — Does it match the spec? Edge cases handled? Tests adequate?
10
+ 2. **Readability** — Clear names? Straightforward logic? Well-organized?
11
+ 3. **Architecture** — Follows existing patterns? Clean boundaries? Right abstraction level?
12
+ 4. **Security** — Input validated? Secrets safe? Auth checked? (Use security-and-hardening skill)
13
+ 5. **Performance** — No N+1 queries? No unbounded ops? (Use performance-optimization skill)
14
+
15
+ Categorize findings as Critical, Important, or Suggestion.
16
+ Output a structured review with specific file:line references and fix recommendations.