@chankov/agent-fleet 0.0.3 → 0.0.5

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 (608) hide show
  1. package/.claude/commands/set-hermes-telegram.md +15 -0
  2. package/.claude/commands/setup-agent-fleet.md +1 -1
  3. package/.opencode/commands/af-set-hermes-telegram.md +15 -0
  4. package/.opencode/commands/af-setup-agent-fleet.md +1 -1
  5. package/.pi/agents/dispatch-policy.yaml +1 -1
  6. package/.pi/agents/peers.yaml +4 -4
  7. package/.pi/extensions/chrome-devtools-mcp/README.md +1 -1
  8. package/.pi/extensions/mcp-bridge/README.md +1 -1
  9. package/.pi/harnesses/agent-hub/README.md +223 -40
  10. package/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  11. package/.pi/harnesses/agent-hub/delegate.ts +32 -9
  12. package/.pi/harnesses/agent-hub/drift-watchdog.js +165 -0
  13. package/.pi/harnesses/agent-hub/footer.ts +29 -0
  14. package/.pi/harnesses/agent-hub/helpers.ts +49 -0
  15. package/.pi/harnesses/agent-hub/index.ts +1037 -246
  16. package/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  17. package/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  18. package/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  19. package/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  20. package/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  21. package/.pi/harnesses/agent-hub/monitor-session-bridge.ts +11 -0
  22. package/.pi/harnesses/agent-hub/package.json +5 -4
  23. package/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  24. package/.pi/harnesses/agent-hub/run-budget.js +155 -0
  25. package/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  26. package/.pi/harnesses/agent-hub/spawn.ts +161 -94
  27. package/.pi/harnesses/agent-hub/version.ts +18 -0
  28. package/.pi/harnesses/ask-user-remote/README.md +1 -0
  29. package/.pi/harnesses/ask-user-remote/index.ts +36 -8
  30. package/.pi/harnesses/coms/README.md +15 -5
  31. package/.pi/harnesses/coms/index.ts +2 -0
  32. package/.pi/harnesses/coms/package.json +5 -4
  33. package/.pi/harnesses/coms/version.ts +18 -0
  34. package/.pi/harnesses/damage-control-continue/README.md +36 -35
  35. package/.pi/harnesses/damage-control-continue/index.ts +23 -9
  36. package/.pi/harnesses/damage-control-continue/package.json +5 -4
  37. package/.pi/harnesses/damage-control-continue/version.ts +18 -0
  38. package/.pi/harnesses/{damage-control/shared.ts → lib/damage-control-shared.ts} +20 -6
  39. package/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  40. package/.pi/harnesses/lib/hermes-monitor-model.ts +9 -0
  41. package/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  42. package/.pi/harnesses/lib/hermes-monitor-socket.ts +118 -0
  43. package/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  44. package/.pi/prompts/set-hermes-telegram.md +15 -0
  45. package/.pi/prompts/setup-agent-fleet.md +1 -1
  46. package/.versions/0.0.4/.claude/commands/build.md +44 -0
  47. package/.versions/0.0.4/.claude/commands/code-simplify.md +22 -0
  48. package/.versions/0.0.4/.claude/commands/design-agent.md +14 -0
  49. package/.versions/0.0.4/.claude/commands/doctor-agent-fleet.md +17 -0
  50. package/.versions/0.0.4/.claude/commands/orchestrate.md +112 -0
  51. package/.versions/0.0.4/.claude/commands/plan.md +16 -0
  52. package/.versions/0.0.4/.claude/commands/prime.md +22 -0
  53. package/.versions/0.0.4/.claude/commands/review.md +16 -0
  54. package/.versions/0.0.4/.claude/commands/setup-agent-fleet.md +25 -0
  55. package/.versions/0.0.4/.claude/commands/ship.md +72 -0
  56. package/.versions/0.0.4/.claude/commands/spec.md +15 -0
  57. package/.versions/0.0.4/.claude/commands/test.md +19 -0
  58. package/.versions/0.0.4/.claude/commands/webperf.md +32 -0
  59. package/.versions/0.0.4/.claude/orchestrate-teams.yaml +24 -0
  60. package/.versions/0.0.4/.opencode/commands/af-build.md +17 -0
  61. package/.versions/0.0.4/.opencode/commands/af-code-simplify.md +16 -0
  62. package/.versions/0.0.4/.opencode/commands/af-compound.md +16 -0
  63. package/.versions/0.0.4/.opencode/commands/af-design-agent.md +15 -0
  64. package/.versions/0.0.4/.opencode/commands/af-doctor-agent-fleet.md +17 -0
  65. package/.versions/0.0.4/.opencode/commands/af-orchestrate.md +112 -0
  66. package/.versions/0.0.4/.opencode/commands/af-plan.md +16 -0
  67. package/.versions/0.0.4/.opencode/commands/af-prime.md +22 -0
  68. package/.versions/0.0.4/.opencode/commands/af-review.md +15 -0
  69. package/.versions/0.0.4/.opencode/commands/af-setup-agent-fleet.md +15 -0
  70. package/.versions/0.0.4/.opencode/commands/af-ship.md +16 -0
  71. package/.versions/0.0.4/.opencode/commands/af-spec.md +16 -0
  72. package/.versions/0.0.4/.opencode/commands/af-test.md +21 -0
  73. package/.versions/0.0.4/.opencode/commands/af-webperf.md +32 -0
  74. package/.versions/0.0.4/.opencode/orchestrate-teams.yaml +24 -0
  75. package/.versions/0.0.4/.pi/agents/dispatch-policy.yaml +32 -0
  76. package/.versions/0.0.4/.pi/agents/model-profiles.yaml +20 -0
  77. package/.versions/0.0.4/.pi/agents/peers.yaml +146 -0
  78. package/.versions/0.0.4/.pi/agents/teams.yaml +39 -0
  79. package/.versions/0.0.4/.pi/damage-control-rules.yaml +297 -0
  80. package/.versions/0.0.4/.pi/extensions/agent-fleet-update-check/README.md +58 -0
  81. package/.versions/0.0.4/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  82. package/{.pi/harnesses/damage-control → .versions/0.0.4/.pi/extensions/agent-fleet-update-check}/package.json +1 -1
  83. package/.versions/0.0.4/.pi/extensions/btw/README.md +118 -0
  84. package/.versions/0.0.4/.pi/extensions/btw/index.ts +917 -0
  85. package/.versions/0.0.4/.pi/extensions/btw/package.json +6 -0
  86. package/.versions/0.0.4/.pi/extensions/btw/state.js +179 -0
  87. package/.versions/0.0.4/.pi/extensions/chrome-devtools-mcp/README.md +58 -0
  88. package/.versions/0.0.4/.pi/extensions/chrome-devtools-mcp/index.ts +92 -0
  89. package/.versions/0.0.4/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  90. package/.versions/0.0.4/.pi/extensions/compact-and-continue/README.md +42 -0
  91. package/.versions/0.0.4/.pi/extensions/compact-and-continue/index.ts +120 -0
  92. package/.versions/0.0.4/.pi/extensions/compact-and-continue/package.json +6 -0
  93. package/.versions/0.0.4/.pi/extensions/mcp-bridge/README.md +46 -0
  94. package/.versions/0.0.4/.pi/extensions/mcp-bridge/index.ts +206 -0
  95. package/.versions/0.0.4/.pi/extensions/mcp-bridge/package.json +6 -0
  96. package/.versions/0.0.4/.pi/extensions/package-lock.json +1143 -0
  97. package/.versions/0.0.4/.pi/extensions/package.json +9 -0
  98. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/README.md +201 -0
  99. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/config.ts +198 -0
  100. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  101. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/index.ts +248 -0
  102. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/package.json +6 -0
  103. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  104. package/.versions/0.0.4/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  105. package/.versions/0.0.4/.pi/harnesses/agent-hub/README.md +798 -0
  106. package/.versions/0.0.4/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  107. package/.versions/0.0.4/.pi/harnesses/agent-hub/artifacts.js +92 -0
  108. package/.versions/0.0.4/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  109. package/.versions/0.0.4/.pi/harnesses/agent-hub/delegate.ts +386 -0
  110. package/.versions/0.0.4/.pi/harnesses/agent-hub/drift-watchdog.js +165 -0
  111. package/.versions/0.0.4/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  112. package/.versions/0.0.4/.pi/harnesses/agent-hub/footer.ts +29 -0
  113. package/.versions/0.0.4/.pi/harnesses/agent-hub/helpers.ts +214 -0
  114. package/.versions/0.0.4/.pi/harnesses/agent-hub/index.ts +8045 -0
  115. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  116. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  117. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  118. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  119. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  120. package/.versions/0.0.4/.pi/harnesses/agent-hub/monitor-session-bridge.ts +11 -0
  121. package/.versions/0.0.4/.pi/harnesses/agent-hub/package.json +7 -0
  122. package/.versions/0.0.4/.pi/harnesses/agent-hub/research-retention.js +34 -0
  123. package/.versions/0.0.4/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  124. package/.versions/0.0.4/.pi/harnesses/agent-hub/return-contract.js +215 -0
  125. package/.versions/0.0.4/.pi/harnesses/agent-hub/run-budget.js +155 -0
  126. package/.versions/0.0.4/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  127. package/.versions/0.0.4/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  128. package/.versions/0.0.4/.pi/harnesses/agent-hub/spawn.ts +246 -0
  129. package/.versions/0.0.4/.pi/harnesses/agent-hub/version.ts +18 -0
  130. package/.versions/0.0.4/.pi/harnesses/ask-user-remote/README.md +18 -0
  131. package/.versions/0.0.4/.pi/harnesses/ask-user-remote/index.ts +293 -0
  132. package/.versions/0.0.4/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  133. package/.versions/0.0.4/.pi/harnesses/coms/README.md +92 -0
  134. package/.versions/0.0.4/.pi/harnesses/coms/index.ts +1745 -0
  135. package/.versions/0.0.4/.pi/harnesses/coms/package.json +7 -0
  136. package/.versions/0.0.4/.pi/harnesses/coms/version.ts +18 -0
  137. package/.versions/0.0.4/.pi/harnesses/damage-control-continue/README.md +117 -0
  138. package/.versions/0.0.4/.pi/harnesses/damage-control-continue/index.ts +536 -0
  139. package/.versions/0.0.4/.pi/harnesses/damage-control-continue/package.json +7 -0
  140. package/.versions/0.0.4/.pi/harnesses/damage-control-continue/version.ts +18 -0
  141. package/.versions/0.0.4/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  142. package/.versions/0.0.4/.pi/harnesses/lib/herdr-client.ts +458 -0
  143. package/.versions/0.0.4/.pi/harnesses/lib/herdr-presence.ts +288 -0
  144. package/.versions/0.0.4/.pi/harnesses/package-lock.json +35 -0
  145. package/.versions/0.0.4/.pi/harnesses/package.json +9 -0
  146. package/.versions/0.0.4/.pi/prompts/build.md +24 -0
  147. package/.versions/0.0.4/.pi/prompts/code-simplify.md +22 -0
  148. package/.versions/0.0.4/.pi/prompts/doctor-agent-fleet.md +15 -0
  149. package/.versions/0.0.4/.pi/prompts/plan.md +16 -0
  150. package/.versions/0.0.4/.pi/prompts/review.md +16 -0
  151. package/.versions/0.0.4/.pi/prompts/setup-agent-fleet.md +27 -0
  152. package/.versions/0.0.4/.pi/prompts/ship.md +17 -0
  153. package/.versions/0.0.4/.pi/prompts/spec.md +15 -0
  154. package/.versions/0.0.4/.pi/prompts/test.md +19 -0
  155. package/.versions/0.0.4/.pi/skills/bowser/SKILL.md +145 -0
  156. package/.versions/0.0.4/.version +1 -0
  157. package/.versions/0.0.4/agents/architect.md +23 -0
  158. package/.versions/0.0.4/agents/bowser.md +26 -0
  159. package/.versions/0.0.4/agents/builder.md +53 -0
  160. package/.versions/0.0.4/agents/code-reviewer.md +205 -0
  161. package/.versions/0.0.4/agents/deep-researcher.md +31 -0
  162. package/.versions/0.0.4/agents/documenter.md +18 -0
  163. package/.versions/0.0.4/agents/orchestrator.md +54 -0
  164. package/.versions/0.0.4/agents/plan-reviewer.md +60 -0
  165. package/.versions/0.0.4/agents/planner.md +69 -0
  166. package/.versions/0.0.4/agents/releaser.md +24 -0
  167. package/.versions/0.0.4/agents/researcher.md +28 -0
  168. package/.versions/0.0.4/agents/security-auditor.md +166 -0
  169. package/.versions/0.0.4/agents/test-engineer.md +151 -0
  170. package/.versions/0.0.4/agents/web-debugger.md +42 -0
  171. package/.versions/0.0.4/agents/web-performance-auditor.md +192 -0
  172. package/.versions/0.0.4/codex/CONDUCTOR.md +148 -0
  173. package/.versions/0.0.4/docs/ARCHITECTURE.md +210 -0
  174. package/.versions/0.0.4/docs/agent-fleet-setup.md +366 -0
  175. package/.versions/0.0.4/docs/claude-code-coms-bridge.md +103 -0
  176. package/.versions/0.0.4/docs/codex-remote-conductor.md +170 -0
  177. package/.versions/0.0.4/docs/coms-hermes-bridge.md +121 -0
  178. package/.versions/0.0.4/docs/getting-started.md +183 -0
  179. package/.versions/0.0.4/docs/npm-install.md +337 -0
  180. package/.versions/0.0.4/docs/opencode-setup.md +248 -0
  181. package/.versions/0.0.4/docs/pi-extensions.md +288 -0
  182. package/.versions/0.0.4/docs/pi-setup.md +463 -0
  183. package/.versions/0.0.4/docs/skill-anatomy.md +150 -0
  184. package/.versions/0.0.4/hermes/README.md +228 -0
  185. package/.versions/0.0.4/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  186. package/.versions/0.0.4/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  187. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-cap.test.py +15 -0
  188. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-discovery.test.py +19 -0
  189. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-envelope.test.py +13 -0
  190. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-forged-owner.test.py +11 -0
  191. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-lease-list.test.py +9 -0
  192. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-multihub.test.py +17 -0
  193. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter-output.test.py +34 -0
  194. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +151 -0
  195. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter.test.py +39 -0
  196. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  197. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/plugin-api-validation.test.py +12 -0
  198. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  199. package/.versions/0.0.4/hermes/plugins/agent-fleet-monitor/dashboard/review-live-wiring.red.test.py +22 -0
  200. package/.versions/0.0.4/hermes/skills/hub-conductor/SKILL.md +84 -0
  201. package/.versions/0.0.4/hermes/skills/hub-liaison/SKILL.md +84 -0
  202. package/.versions/0.0.4/hooks/SIMPLIFY-IGNORE.md +90 -0
  203. package/.versions/0.0.4/hooks/coms-stop-hook.mjs +73 -0
  204. package/.versions/0.0.4/hooks/hooks.json +14 -0
  205. package/.versions/0.0.4/hooks/session-start.sh +74 -0
  206. package/.versions/0.0.4/hooks/simplify-ignore.sh +302 -0
  207. package/.versions/0.0.4/justfile +256 -0
  208. package/.versions/0.0.4/references/accessibility-checklist.md +160 -0
  209. package/.versions/0.0.4/references/definition-of-done.md +67 -0
  210. package/.versions/0.0.4/references/fleet-coordination-patterns.md +151 -0
  211. package/.versions/0.0.4/references/observability-checklist.md +91 -0
  212. package/.versions/0.0.4/references/orchestration-patterns.md +370 -0
  213. package/.versions/0.0.4/references/performance-checklist.md +153 -0
  214. package/.versions/0.0.4/references/prompting-patterns.md +380 -0
  215. package/.versions/0.0.4/references/security-checklist.md +179 -0
  216. package/.versions/0.0.4/references/testing-patterns.md +236 -0
  217. package/.versions/0.0.4/scripts/codex-conductor.ts +41 -0
  218. package/.versions/0.0.4/scripts/codex-remote-control.ts +167 -0
  219. package/.versions/0.0.4/scripts/coms-claude-bridge.ts +286 -0
  220. package/.versions/0.0.4/scripts/coms-cli.ts +484 -0
  221. package/.versions/0.0.4/scripts/coms-hermes-bridge.ts +403 -0
  222. package/.versions/0.0.4/scripts/hermes-monitor-capability-runner.ts +25 -0
  223. package/.versions/0.0.4/scripts/hermes-monitor-scenario.ts +7 -0
  224. package/.versions/0.0.4/scripts/lib/claude-bridge-core.ts +100 -0
  225. package/.versions/0.0.4/scripts/lib/codex-conductor.ts +88 -0
  226. package/.versions/0.0.4/scripts/lib/codex-remote-control.ts +480 -0
  227. package/.versions/0.0.4/scripts/lib/coms-envelope.ts +539 -0
  228. package/.versions/0.0.4/scripts/lib/fake-herdr-server.ts +88 -0
  229. package/.versions/0.0.4/scripts/lib/herdr-layout.ts +263 -0
  230. package/.versions/0.0.4/scripts/lib/hermes-bridge-core.ts +238 -0
  231. package/.versions/0.0.4/scripts/lib/hermes-monitor-herdr.ts +28 -0
  232. package/.versions/0.0.4/scripts/lib/hermes-monitor-model.ts +9 -0
  233. package/.versions/0.0.4/scripts/lib/hermes-monitor-registry.ts +6 -0
  234. package/.versions/0.0.4/scripts/lib/hermes-monitor-socket.ts +118 -0
  235. package/.versions/0.0.4/scripts/lib/hermes-monitor-store.ts +31 -0
  236. package/.versions/0.0.4/scripts/lib/persona-banner.ts +62 -0
  237. package/.versions/0.0.4/scripts/lib/spawn-stagger.ts +101 -0
  238. package/.versions/0.0.4/scripts/lib/team-project.ts +184 -0
  239. package/.versions/0.0.4/scripts/lib/team-snapshot.ts +147 -0
  240. package/.versions/0.0.4/scripts/peer-banner.ts +40 -0
  241. package/.versions/0.0.4/scripts/team-snapshot.ts +238 -0
  242. package/.versions/0.0.4/scripts/team-up.ts +333 -0
  243. package/.versions/0.0.4/skills/_internal/grilling.md +11 -0
  244. package/.versions/0.0.4/skills/browser-testing-with-devtools/SKILL.md +352 -0
  245. package/.versions/0.0.4/skills/code-review-and-quality/SKILL.md +381 -0
  246. package/.versions/0.0.4/skills/compound-learning/SKILL.md +137 -0
  247. package/.versions/0.0.4/skills/context-engineering/SKILL.md +291 -0
  248. package/.versions/0.0.4/skills/deprecation-and-migration/SKILL.md +206 -0
  249. package/.versions/0.0.4/skills/designing-agents/SKILL.md +394 -0
  250. package/.versions/0.0.4/skills/designing-agents/pi-harness-authoring.md +222 -0
  251. package/.versions/0.0.4/skills/frontend-ui-engineering/SKILL.md +328 -0
  252. package/.versions/0.0.4/skills/git-workflow-and-versioning/SKILL.md +316 -0
  253. package/.versions/0.0.4/skills/guided-workspace-setup/SKILL.md +535 -0
  254. package/.versions/0.0.4/skills/guided-workspace-setup/companion-manifest.json +33 -0
  255. package/.versions/0.0.4/skills/idea-refine/SKILL.md +182 -0
  256. package/.versions/0.0.4/skills/idea-refine/examples.md +238 -0
  257. package/.versions/0.0.4/skills/idea-refine/frameworks.md +99 -0
  258. package/.versions/0.0.4/skills/idea-refine/refinement-criteria.md +113 -0
  259. package/.versions/0.0.4/skills/idea-refine/scripts/idea-refine.sh +15 -0
  260. package/.versions/0.0.4/skills/incremental-implementation/SKILL.md +287 -0
  261. package/.versions/0.0.4/skills/interview-me/SKILL.md +226 -0
  262. package/.versions/0.0.4/skills/orchestration-verification/SKILL.md +181 -0
  263. package/.versions/0.0.4/skills/peer-coms/SKILL.md +90 -0
  264. package/.versions/0.0.4/skills/performance-optimization/SKILL.md +350 -0
  265. package/.versions/0.0.4/skills/planning-and-task-breakdown/SKILL.md +236 -0
  266. package/.versions/0.0.4/skills/security-and-hardening/SKILL.md +461 -0
  267. package/.versions/0.0.4/skills/spec-driven-development/SKILL.md +245 -0
  268. package/.versions/0.0.4/skills/using-agent-skills/SKILL.md +199 -0
  269. package/.versions/0.0.4/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  270. package/.versions/0.0.4/vendor/agent-skills-upstream/LICENSE +21 -0
  271. package/.versions/0.0.4/vendor/agent-skills-upstream/README.md +11 -0
  272. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  273. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  274. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  275. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  276. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  277. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  278. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  279. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  280. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  281. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  282. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  283. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  284. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  285. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  286. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  287. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  288. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  289. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  290. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  291. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  292. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  293. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  294. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  295. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  296. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  297. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  298. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  299. package/.versions/0.0.4/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  300. package/.versions/0.0.5/.claude/commands/build.md +44 -0
  301. package/.versions/0.0.5/.claude/commands/code-simplify.md +22 -0
  302. package/.versions/0.0.5/.claude/commands/design-agent.md +14 -0
  303. package/.versions/0.0.5/.claude/commands/doctor-agent-fleet.md +17 -0
  304. package/.versions/0.0.5/.claude/commands/orchestrate.md +112 -0
  305. package/.versions/0.0.5/.claude/commands/plan.md +16 -0
  306. package/.versions/0.0.5/.claude/commands/prime.md +22 -0
  307. package/.versions/0.0.5/.claude/commands/review.md +16 -0
  308. package/.versions/0.0.5/.claude/commands/set-hermes-telegram.md +15 -0
  309. package/.versions/0.0.5/.claude/commands/setup-agent-fleet.md +25 -0
  310. package/.versions/0.0.5/.claude/commands/ship.md +72 -0
  311. package/.versions/0.0.5/.claude/commands/spec.md +15 -0
  312. package/.versions/0.0.5/.claude/commands/test.md +19 -0
  313. package/.versions/0.0.5/.claude/commands/webperf.md +32 -0
  314. package/.versions/0.0.5/.claude/orchestrate-teams.yaml +24 -0
  315. package/.versions/0.0.5/.opencode/commands/af-build.md +17 -0
  316. package/.versions/0.0.5/.opencode/commands/af-code-simplify.md +16 -0
  317. package/.versions/0.0.5/.opencode/commands/af-compound.md +16 -0
  318. package/.versions/0.0.5/.opencode/commands/af-design-agent.md +15 -0
  319. package/.versions/0.0.5/.opencode/commands/af-doctor-agent-fleet.md +17 -0
  320. package/.versions/0.0.5/.opencode/commands/af-orchestrate.md +112 -0
  321. package/.versions/0.0.5/.opencode/commands/af-plan.md +16 -0
  322. package/.versions/0.0.5/.opencode/commands/af-prime.md +22 -0
  323. package/.versions/0.0.5/.opencode/commands/af-review.md +15 -0
  324. package/.versions/0.0.5/.opencode/commands/af-set-hermes-telegram.md +15 -0
  325. package/.versions/0.0.5/.opencode/commands/af-setup-agent-fleet.md +15 -0
  326. package/.versions/0.0.5/.opencode/commands/af-ship.md +16 -0
  327. package/.versions/0.0.5/.opencode/commands/af-spec.md +16 -0
  328. package/.versions/0.0.5/.opencode/commands/af-test.md +21 -0
  329. package/.versions/0.0.5/.opencode/commands/af-webperf.md +32 -0
  330. package/.versions/0.0.5/.opencode/orchestrate-teams.yaml +24 -0
  331. package/.versions/0.0.5/.pi/agents/dispatch-policy.yaml +32 -0
  332. package/.versions/0.0.5/.pi/agents/model-profiles.yaml +20 -0
  333. package/.versions/0.0.5/.pi/agents/peers.yaml +146 -0
  334. package/.versions/0.0.5/.pi/agents/teams.yaml +39 -0
  335. package/.versions/0.0.5/.pi/damage-control-rules.yaml +297 -0
  336. package/.versions/0.0.5/.pi/extensions/agent-fleet-update-check/README.md +58 -0
  337. package/.versions/0.0.5/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  338. package/.versions/0.0.5/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  339. package/.versions/0.0.5/.pi/extensions/btw/README.md +118 -0
  340. package/.versions/0.0.5/.pi/extensions/btw/index.ts +917 -0
  341. package/.versions/0.0.5/.pi/extensions/btw/package.json +6 -0
  342. package/.versions/0.0.5/.pi/extensions/btw/state.js +179 -0
  343. package/.versions/0.0.5/.pi/extensions/chrome-devtools-mcp/README.md +58 -0
  344. package/.versions/0.0.5/.pi/extensions/chrome-devtools-mcp/index.ts +92 -0
  345. package/.versions/0.0.5/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  346. package/.versions/0.0.5/.pi/extensions/compact-and-continue/README.md +42 -0
  347. package/.versions/0.0.5/.pi/extensions/compact-and-continue/index.ts +120 -0
  348. package/.versions/0.0.5/.pi/extensions/compact-and-continue/package.json +6 -0
  349. package/.versions/0.0.5/.pi/extensions/mcp-bridge/README.md +46 -0
  350. package/.versions/0.0.5/.pi/extensions/mcp-bridge/index.ts +206 -0
  351. package/.versions/0.0.5/.pi/extensions/mcp-bridge/package.json +6 -0
  352. package/.versions/0.0.5/.pi/extensions/package-lock.json +1143 -0
  353. package/.versions/0.0.5/.pi/extensions/package.json +9 -0
  354. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/README.md +201 -0
  355. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/config.ts +198 -0
  356. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  357. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/index.ts +248 -0
  358. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/package.json +6 -0
  359. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  360. package/.versions/0.0.5/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  361. package/.versions/0.0.5/.pi/harnesses/agent-hub/README.md +798 -0
  362. package/.versions/0.0.5/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  363. package/.versions/0.0.5/.pi/harnesses/agent-hub/artifacts.js +92 -0
  364. package/.versions/0.0.5/.pi/harnesses/agent-hub/backend-policy.js +153 -0
  365. package/.versions/0.0.5/.pi/harnesses/agent-hub/delegate.ts +386 -0
  366. package/.versions/0.0.5/.pi/harnesses/agent-hub/drift-watchdog.js +165 -0
  367. package/.versions/0.0.5/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  368. package/.versions/0.0.5/.pi/harnesses/agent-hub/footer.ts +29 -0
  369. package/.versions/0.0.5/.pi/harnesses/agent-hub/helpers.ts +214 -0
  370. package/.versions/0.0.5/.pi/harnesses/agent-hub/index.ts +8045 -0
  371. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  372. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  373. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  374. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  375. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  376. package/.versions/0.0.5/.pi/harnesses/agent-hub/monitor-session-bridge.ts +11 -0
  377. package/.versions/0.0.5/.pi/harnesses/agent-hub/package.json +7 -0
  378. package/.versions/0.0.5/.pi/harnesses/agent-hub/research-retention.js +34 -0
  379. package/.versions/0.0.5/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  380. package/.versions/0.0.5/.pi/harnesses/agent-hub/return-contract.js +215 -0
  381. package/.versions/0.0.5/.pi/harnesses/agent-hub/run-budget.js +155 -0
  382. package/.versions/0.0.5/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  383. package/.versions/0.0.5/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  384. package/.versions/0.0.5/.pi/harnesses/agent-hub/spawn.ts +246 -0
  385. package/.versions/0.0.5/.pi/harnesses/agent-hub/version.ts +18 -0
  386. package/.versions/0.0.5/.pi/harnesses/ask-user-remote/README.md +19 -0
  387. package/.versions/0.0.5/.pi/harnesses/ask-user-remote/index.ts +321 -0
  388. package/.versions/0.0.5/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  389. package/.versions/0.0.5/.pi/harnesses/coms/README.md +92 -0
  390. package/.versions/0.0.5/.pi/harnesses/coms/index.ts +1745 -0
  391. package/.versions/0.0.5/.pi/harnesses/coms/package.json +7 -0
  392. package/.versions/0.0.5/.pi/harnesses/coms/version.ts +18 -0
  393. package/.versions/0.0.5/.pi/harnesses/damage-control-continue/README.md +117 -0
  394. package/.versions/0.0.5/.pi/harnesses/damage-control-continue/index.ts +536 -0
  395. package/.versions/0.0.5/.pi/harnesses/damage-control-continue/package.json +7 -0
  396. package/.versions/0.0.5/.pi/harnesses/damage-control-continue/version.ts +18 -0
  397. package/.versions/0.0.5/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  398. package/.versions/0.0.5/.pi/harnesses/lib/herdr-client.ts +458 -0
  399. package/.versions/0.0.5/.pi/harnesses/lib/herdr-presence.ts +288 -0
  400. package/.versions/0.0.5/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  401. package/.versions/0.0.5/.pi/harnesses/lib/hermes-monitor-model.ts +9 -0
  402. package/.versions/0.0.5/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  403. package/.versions/0.0.5/.pi/harnesses/lib/hermes-monitor-socket.ts +118 -0
  404. package/.versions/0.0.5/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  405. package/.versions/0.0.5/.pi/harnesses/package-lock.json +35 -0
  406. package/.versions/0.0.5/.pi/harnesses/package.json +9 -0
  407. package/.versions/0.0.5/.pi/prompts/build.md +24 -0
  408. package/.versions/0.0.5/.pi/prompts/code-simplify.md +22 -0
  409. package/.versions/0.0.5/.pi/prompts/doctor-agent-fleet.md +15 -0
  410. package/.versions/0.0.5/.pi/prompts/plan.md +16 -0
  411. package/.versions/0.0.5/.pi/prompts/review.md +16 -0
  412. package/.versions/0.0.5/.pi/prompts/set-hermes-telegram.md +15 -0
  413. package/.versions/0.0.5/.pi/prompts/setup-agent-fleet.md +27 -0
  414. package/.versions/0.0.5/.pi/prompts/ship.md +17 -0
  415. package/.versions/0.0.5/.pi/prompts/spec.md +15 -0
  416. package/.versions/0.0.5/.pi/prompts/test.md +19 -0
  417. package/.versions/0.0.5/.pi/skills/bowser/SKILL.md +145 -0
  418. package/.versions/0.0.5/.version +1 -0
  419. package/.versions/0.0.5/agents/architect.md +23 -0
  420. package/.versions/0.0.5/agents/bowser.md +26 -0
  421. package/.versions/0.0.5/agents/builder.md +53 -0
  422. package/.versions/0.0.5/agents/code-reviewer.md +205 -0
  423. package/.versions/0.0.5/agents/deep-researcher.md +31 -0
  424. package/.versions/0.0.5/agents/documenter.md +18 -0
  425. package/.versions/0.0.5/agents/orchestrator.md +54 -0
  426. package/.versions/0.0.5/agents/plan-reviewer.md +60 -0
  427. package/.versions/0.0.5/agents/planner.md +69 -0
  428. package/.versions/0.0.5/agents/releaser.md +24 -0
  429. package/.versions/0.0.5/agents/researcher.md +28 -0
  430. package/.versions/0.0.5/agents/security-auditor.md +166 -0
  431. package/.versions/0.0.5/agents/test-engineer.md +151 -0
  432. package/.versions/0.0.5/agents/web-debugger.md +42 -0
  433. package/.versions/0.0.5/agents/web-performance-auditor.md +192 -0
  434. package/.versions/0.0.5/codex/CONDUCTOR.md +148 -0
  435. package/.versions/0.0.5/docs/ARCHITECTURE.md +210 -0
  436. package/.versions/0.0.5/docs/agent-fleet-setup.md +366 -0
  437. package/.versions/0.0.5/docs/claude-code-coms-bridge.md +103 -0
  438. package/.versions/0.0.5/docs/codex-remote-conductor.md +170 -0
  439. package/.versions/0.0.5/docs/coms-hermes-bridge.md +179 -0
  440. package/.versions/0.0.5/docs/getting-started.md +183 -0
  441. package/.versions/0.0.5/docs/npm-install.md +337 -0
  442. package/.versions/0.0.5/docs/opencode-setup.md +249 -0
  443. package/.versions/0.0.5/docs/pi-extensions.md +293 -0
  444. package/.versions/0.0.5/docs/pi-setup.md +472 -0
  445. package/.versions/0.0.5/docs/skill-anatomy.md +150 -0
  446. package/.versions/0.0.5/hermes/README.md +231 -0
  447. package/.versions/0.0.5/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  448. package/.versions/0.0.5/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  449. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-cap.test.py +15 -0
  450. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-discovery.test.py +19 -0
  451. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-envelope.test.py +13 -0
  452. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-forged-owner.test.py +11 -0
  453. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-lease-list.test.py +9 -0
  454. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-multihub.test.py +17 -0
  455. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter-output.test.py +34 -0
  456. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +151 -0
  457. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/adapter.test.py +39 -0
  458. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  459. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/plugin-api-validation.test.py +12 -0
  460. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  461. package/.versions/0.0.5/hermes/plugins/agent-fleet-monitor/dashboard/review-live-wiring.red.test.py +22 -0
  462. package/.versions/0.0.5/hermes/skills/hub-conductor/SKILL.md +84 -0
  463. package/.versions/0.0.5/hermes/skills/hub-liaison/SKILL.md +84 -0
  464. package/.versions/0.0.5/hooks/SIMPLIFY-IGNORE.md +90 -0
  465. package/.versions/0.0.5/hooks/coms-stop-hook.mjs +73 -0
  466. package/.versions/0.0.5/hooks/hooks.json +14 -0
  467. package/.versions/0.0.5/hooks/session-start.sh +74 -0
  468. package/.versions/0.0.5/hooks/simplify-ignore.sh +302 -0
  469. package/.versions/0.0.5/justfile +245 -0
  470. package/.versions/0.0.5/references/accessibility-checklist.md +160 -0
  471. package/.versions/0.0.5/references/definition-of-done.md +67 -0
  472. package/.versions/0.0.5/references/fleet-coordination-patterns.md +151 -0
  473. package/.versions/0.0.5/references/observability-checklist.md +91 -0
  474. package/.versions/0.0.5/references/orchestration-patterns.md +370 -0
  475. package/.versions/0.0.5/references/performance-checklist.md +153 -0
  476. package/.versions/0.0.5/references/prompting-patterns.md +380 -0
  477. package/.versions/0.0.5/references/security-checklist.md +179 -0
  478. package/.versions/0.0.5/references/testing-patterns.md +236 -0
  479. package/.versions/0.0.5/scripts/codex-conductor.ts +41 -0
  480. package/.versions/0.0.5/scripts/codex-remote-control.ts +167 -0
  481. package/.versions/0.0.5/scripts/coms-claude-bridge.ts +286 -0
  482. package/.versions/0.0.5/scripts/coms-cli.ts +484 -0
  483. package/.versions/0.0.5/scripts/coms-hermes-bridge.ts +413 -0
  484. package/.versions/0.0.5/scripts/fleet.ts +141 -0
  485. package/.versions/0.0.5/scripts/hermes-monitor-capability-runner.ts +25 -0
  486. package/.versions/0.0.5/scripts/hermes-monitor-scenario.ts +7 -0
  487. package/.versions/0.0.5/scripts/lib/claude-bridge-core.ts +100 -0
  488. package/.versions/0.0.5/scripts/lib/codex-conductor.ts +88 -0
  489. package/.versions/0.0.5/scripts/lib/codex-remote-control.ts +480 -0
  490. package/.versions/0.0.5/scripts/lib/coms-envelope.ts +539 -0
  491. package/.versions/0.0.5/scripts/lib/fake-herdr-server.ts +88 -0
  492. package/.versions/0.0.5/scripts/lib/fleet-command.ts +109 -0
  493. package/.versions/0.0.5/scripts/lib/herdr-layout.ts +263 -0
  494. package/.versions/0.0.5/scripts/lib/hermes-bridge-core.ts +241 -0
  495. package/.versions/0.0.5/scripts/lib/hermes-monitor-herdr.ts +2 -0
  496. package/.versions/0.0.5/scripts/lib/hermes-monitor-model.ts +3 -0
  497. package/.versions/0.0.5/scripts/lib/hermes-monitor-registry.ts +2 -0
  498. package/.versions/0.0.5/scripts/lib/hermes-monitor-socket.ts +2 -0
  499. package/.versions/0.0.5/scripts/lib/hermes-monitor-store.ts +2 -0
  500. package/.versions/0.0.5/scripts/lib/persona-banner.ts +62 -0
  501. package/.versions/0.0.5/scripts/lib/spawn-stagger.ts +101 -0
  502. package/.versions/0.0.5/scripts/lib/team-project.ts +191 -0
  503. package/.versions/0.0.5/scripts/lib/team-snapshot.ts +147 -0
  504. package/.versions/0.0.5/scripts/peer-banner.ts +40 -0
  505. package/.versions/0.0.5/scripts/team-snapshot.ts +237 -0
  506. package/.versions/0.0.5/scripts/team-up.ts +351 -0
  507. package/.versions/0.0.5/skills/_internal/grilling.md +11 -0
  508. package/.versions/0.0.5/skills/browser-testing-with-devtools/SKILL.md +352 -0
  509. package/.versions/0.0.5/skills/code-review-and-quality/SKILL.md +381 -0
  510. package/.versions/0.0.5/skills/compound-learning/SKILL.md +137 -0
  511. package/.versions/0.0.5/skills/context-engineering/SKILL.md +291 -0
  512. package/.versions/0.0.5/skills/deprecation-and-migration/SKILL.md +206 -0
  513. package/.versions/0.0.5/skills/designing-agents/SKILL.md +394 -0
  514. package/.versions/0.0.5/skills/designing-agents/pi-harness-authoring.md +222 -0
  515. package/.versions/0.0.5/skills/frontend-ui-engineering/SKILL.md +328 -0
  516. package/.versions/0.0.5/skills/git-workflow-and-versioning/SKILL.md +316 -0
  517. package/.versions/0.0.5/skills/guided-workspace-setup/SKILL.md +542 -0
  518. package/.versions/0.0.5/skills/guided-workspace-setup/companion-manifest.json +35 -0
  519. package/.versions/0.0.5/skills/idea-refine/SKILL.md +182 -0
  520. package/.versions/0.0.5/skills/idea-refine/examples.md +238 -0
  521. package/.versions/0.0.5/skills/idea-refine/frameworks.md +99 -0
  522. package/.versions/0.0.5/skills/idea-refine/refinement-criteria.md +113 -0
  523. package/.versions/0.0.5/skills/idea-refine/scripts/idea-refine.sh +15 -0
  524. package/.versions/0.0.5/skills/incremental-implementation/SKILL.md +287 -0
  525. package/.versions/0.0.5/skills/interview-me/SKILL.md +226 -0
  526. package/.versions/0.0.5/skills/orchestration-verification/SKILL.md +181 -0
  527. package/.versions/0.0.5/skills/peer-coms/SKILL.md +90 -0
  528. package/.versions/0.0.5/skills/performance-optimization/SKILL.md +350 -0
  529. package/.versions/0.0.5/skills/planning-and-task-breakdown/SKILL.md +236 -0
  530. package/.versions/0.0.5/skills/security-and-hardening/SKILL.md +461 -0
  531. package/.versions/0.0.5/skills/spec-driven-development/SKILL.md +245 -0
  532. package/.versions/0.0.5/skills/using-agent-skills/SKILL.md +199 -0
  533. package/.versions/0.0.5/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  534. package/.versions/0.0.5/vendor/agent-skills-upstream/LICENSE +21 -0
  535. package/.versions/0.0.5/vendor/agent-skills-upstream/README.md +11 -0
  536. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  537. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  538. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  539. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  540. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  541. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  542. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  543. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  544. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  545. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  546. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  547. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  548. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  549. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  550. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  551. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  552. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  553. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  554. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  555. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  556. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  557. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  558. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  559. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  560. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  561. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  562. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  563. package/.versions/0.0.5/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  564. package/CHANGELOG.md +62 -0
  565. package/README.md +17 -16
  566. package/agents/builder.md +1 -1
  567. package/agents/code-reviewer.md +1 -1
  568. package/agents/deep-researcher.md +3 -3
  569. package/agents/orchestrator.md +20 -11
  570. package/agents/plan-reviewer.md +3 -3
  571. package/agents/test-engineer.md +11 -4
  572. package/bin/cli.js +83 -1
  573. package/bin/lib/set-hermes-telegram.js +323 -0
  574. package/bin/lib/validate-overrides.js +19 -0
  575. package/bin/sync-harness-versions.js +94 -0
  576. package/docs/ARCHITECTURE.md +49 -4
  577. package/docs/agent-fleet-setup.md +11 -1
  578. package/docs/claude-code-coms-bridge.md +4 -4
  579. package/docs/codex-remote-conductor.md +12 -12
  580. package/docs/coms-hermes-bridge.md +62 -4
  581. package/docs/getting-started.md +4 -4
  582. package/docs/opencode-setup.md +1 -0
  583. package/docs/pi-extensions.md +73 -33
  584. package/docs/pi-setup.md +23 -8
  585. package/hermes/README.md +191 -8
  586. package/justfile +143 -158
  587. package/package.json +13 -5
  588. package/references/fleet-coordination-patterns.md +1 -1
  589. package/scripts/coms-hermes-bridge.ts +18 -8
  590. package/scripts/fleet.ts +141 -0
  591. package/scripts/lib/fake-herdr-server.ts +88 -0
  592. package/scripts/lib/fleet-command.ts +109 -0
  593. package/scripts/lib/hermes-bridge-core.ts +5 -2
  594. package/scripts/lib/hermes-monitor-herdr.ts +2 -0
  595. package/scripts/lib/hermes-monitor-model.ts +3 -0
  596. package/scripts/lib/hermes-monitor-registry.ts +2 -0
  597. package/scripts/lib/hermes-monitor-socket.ts +2 -0
  598. package/scripts/lib/hermes-monitor-store.ts +2 -0
  599. package/scripts/lib/team-project.ts +10 -3
  600. package/scripts/team-snapshot.ts +4 -5
  601. package/scripts/team-up.ts +24 -6
  602. package/skills/designing-agents/SKILL.md +2 -2
  603. package/skills/designing-agents/pi-harness-authoring.md +26 -13
  604. package/skills/guided-workspace-setup/SKILL.md +22 -12
  605. package/skills/guided-workspace-setup/companion-manifest.json +3 -1
  606. package/skills/peer-coms/SKILL.md +1 -1
  607. package/.pi/harnesses/damage-control/README.md +0 -65
  608. package/.pi/harnesses/damage-control/index.ts +0 -250
@@ -0,0 +1,192 @@
1
+ ---
2
+ name: web-performance-auditor
3
+ description: Web performance engineer focused on Core Web Vitals, loading, rendering, and network optimization. Use for performance-focused audits, CWV analysis, and identifying structural performance anti-patterns in web applications.
4
+ tools: read,bash,grep,find,ls
5
+ model: openai-codex/gpt-5.6-terra
6
+ models:
7
+ - openai-codex/gpt-5.6-sol
8
+ - openai-codex/gpt-5.6-luna
9
+ - ollama/nemotron-3-ultra:cloud
10
+ - ollama/glm-5.2:cloud
11
+ thinking: high
12
+ ---
13
+
14
+ # Web Performance Auditor
15
+
16
+ You are an experienced Web Performance Engineer conducting a performance audit. Your role is to identify bottlenecks, assess their real-world user impact, and recommend concrete fixes. You prioritize findings by actual or likely effect on Core Web Vitals and user experience.
17
+
18
+ ## Operating Modes
19
+
20
+ ### Quick mode (default — no tool artifacts provided)
21
+
22
+ Scan source code directly for structural anti-patterns. Every finding is tagged **potential impact**, never as a measurement. The scorecard is marked `not measured` and left empty.
23
+
24
+ ### Deep mode (activated when tool artifacts or live measurement are available)
25
+
26
+ Interpret performance data from one or more of:
27
+
28
+ - **Lighthouse JSON report**: parse directly. Sources include `npx lighthouse <url> --output json`, `npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json` (Chrome DevTools MCP CLI, no install required), or the `lighthouseResult` object from a PageSpeed Insights API response (paste the full JSON).
29
+ - **PageSpeed Insights JSON**: the full JSON response from the PageSpeed Insights API (`pagespeedonline.googleapis.com/pagespeedonline/v5/runPagespeed`). Contains `lighthouseResult` (lab) and `loadingExperience` (CrUX field data). Parse both.
30
+ - **CrUX API response**: field data (p75 over the last 28 days). Parse directly. Requires `CRUX_API_KEY`.
31
+ - **DevTools performance trace** (Perfetto JSON): complex format. Defer interpretation to Chrome DevTools MCP (`performance_analyze_insight`); without MCP, summarize what you can extract and flag the rest as unparsed.
32
+ - **Live capture via Chrome DevTools MCP server**: when the MCP server is configured in the harness, capture metrics directly using `lighthouse_audit`, `performance_start_trace` / `performance_stop_trace`, and `performance_analyze_insight` instead of asking the user to paste artifacts.
33
+ - **Chrome DevTools MCP CLI** (`chrome-devtools` command): when there's no MCP server in the harness, ask the user to invoke the CLI directly. It can be run on demand with `npx -p chrome-devtools-mcp chrome-devtools <tool>` (no install) or after `npm i -g chrome-devtools-mcp`. Example: `chrome-devtools lighthouse_audit --output-format=json > report.json`.
34
+
35
+ Populate the scorecard only with values backed by these sources. Mark unmeasured fields as `not measured`.
36
+
37
+ ## Tooling
38
+
39
+ | Capability | Tool / Source | Requires |
40
+ |---|---|---|
41
+ | Lab metrics, opportunities, diagnostics | Lighthouse JSON | None (parse a provided file) |
42
+ | Field metrics (real users, p75) | CrUX API | `CRUX_API_KEY` or `GOOGLE_API_KEY` env var |
43
+ | Combined lab + field | PageSpeed Insights JSON | None for parsing; the user provides the JSON |
44
+ | Live trace, LCP attribution, INP attribution, layout shift attribution | Chrome DevTools MCP server (`performance_*`, `lighthouse_audit`) | `chrome-devtools` MCP server configured in the harness (see `skills/browser-testing-with-devtools`) |
45
+ | Manual terminal capture (Lighthouse, trace, screenshot) | Chrome DevTools MCP CLI (e.g. `chrome-devtools lighthouse_audit --output-format=json`) | `npx -p chrome-devtools-mcp chrome-devtools <tool>` or `npm i -g chrome-devtools-mcp` (CLI is independent of the harness) |
46
+
47
+ If a source is unavailable, do not fabricate. Skip the related section of the scorecard and continue with what you have.
48
+
49
+ ## Metric-Honesty Rule
50
+
51
+ **Never fabricate metrics.** An LLM reading static source code cannot measure real-world LCP, INP, or CLS. If no tool data is provided:
52
+
53
+ - Return a source-level findings report.
54
+ - Mark the entire scorecard as `not measured`.
55
+ - Label every finding as `potential impact`, not as a measurement.
56
+
57
+ When data IS provided, label each scorecard value with its source (`Field (CrUX)`, `Lab (Lighthouse)`, `Trace (DevTools)`). Field and lab data are not interchangeable: field is what real users experienced, lab is a single synthetic run. Treating them as the same number is a form of fabrication.
58
+
59
+ Violating this rule is worse than returning no scorecard at all.
60
+
61
+ ## Review Scope
62
+
63
+ Identify the framework and rendering model (React, Vue, Svelte, Angular, Next.js, Astro, vanilla HTML, etc.) before applying framework-specific checks. Do not recommend `<Image>` from `next/image` to a Vue app, or `React.memo` to a Svelte app.
64
+
65
+ ### 1. Core Web Vitals
66
+
67
+ - Does the LCP element load within 2.5s? Is it a hero image, heading, or block of text?
68
+ - Is the LCP image (if applicable) using `fetchpriority="high"` and not lazy-loaded?
69
+ - Are layout shifts caused by images, embeds, ads, fonts, or dynamically injected content?
70
+ - Do images, `<source>` elements, iframes, and embeds have explicit `width` and `height` to reserve space?
71
+ - Are long tasks (> 50ms) blocking the main thread and delaying INP?
72
+ - Are event handlers doing synchronous heavy work before yielding to the browser?
73
+ - Is `scheduler.yield()` (or a `yieldToMain` fallback) used inside long-running loops so input events can interleave?
74
+ - Is the page using **soft navigation** APIs correctly so INP and LCP are tracked across SPA route changes?
75
+ - Is the **Long Animation Frames (LoAF)** API used (or planned) to attribute INP regressions in production?
76
+
77
+ ### 2. Loading
78
+
79
+ - Is TTFB acceptable (< 800ms)? Are there slow server responses or missing CDN coverage?
80
+ - Are critical origins `preconnect`-ed and known third-party origins `dns-prefetch`-ed?
81
+ - Are LCP-critical resources preloaded with `fetchpriority="high"`?
82
+ - Is the **Speculation Rules API** used to `prerender` or `prefetch` likely-next navigations?
83
+ - Are fonts self-hosted, preloaded, and using `font-display: swap` (or `optional` for non-critical)?
84
+ - Are fonts subsetted (`unicode-range`) and limited in count/weights?
85
+ - Are images in modern formats (WebP, AVIF) with responsive `srcset` and `sizes`?
86
+ - Is the initial JavaScript bundle under 200KB gzipped?
87
+ - Is code splitting applied for routes and heavy features?
88
+ - Are blocking scripts in `<head>` without `defer` or `async`?
89
+ - Are third-party scripts loaded with `async`/`defer` and fronted by a facade when heavy (chat widgets, video embeds)?
90
+
91
+ ### 3. Rendering / JavaScript
92
+
93
+ - Are there unnecessary full-page re-renders? Is state lifted (or colocated) correctly?
94
+ - Are long lists virtualized?
95
+ - Are animations using `transform` and `opacity` (compositor-only)?
96
+ - Is there layout thrashing (reading layout properties, then writing, in a loop)?
97
+ - Is `content-visibility: auto` used for off-screen sections?
98
+ - Is the **View Transitions API** used appropriately to avoid perceived CLS on SPA navigations?
99
+ - Is **bfcache** preserved? (No `unload` handlers, no `Cache-Control: no-store` on HTML)
100
+ - **AI-generated patterns:**
101
+ - State duplication instead of lifting state.
102
+ - `React.memo` / `useMemo` / `useCallback` wrapping everything "just in case" (cost without benefit; can hurt perf).
103
+ - Over-eager `useEffect` dependencies causing redundant re-renders or update loops.
104
+ - **Vue:** watchers (`watch`/`watchEffect`) with broad dependencies that trigger unnecessary updates; `computed` with side effects.
105
+ - **Angular:** `ChangeDetectionStrategy.Default` where `OnPush` would suffice; subscriptions without `takeUntil`/`async pipe` that accumulate listeners.
106
+ - **Svelte:** `$:` blocks with expensive logic that re-runs more than needed.
107
+ - **Vanilla:** `scroll`/`resize` listeners without `passive: true` or debounce; DOM manipulation inside a loop that forces repeated reflow.
108
+
109
+ ### 4. Network
110
+
111
+ - Are static assets cached with long `max-age` + content hashing?
112
+ - Is HTTP/2 or HTTP/3 enabled?
113
+ - Are there unnecessary redirects?
114
+ - Are API responses paginated? Any `SELECT *` or unbounded fetch patterns?
115
+ - Are bulk operations used instead of loops of individual API calls?
116
+ - Is response compression enabled (gzip/brotli)?
117
+ - **AI-generated patterns:**
118
+ - Over-fetching data "just in case."
119
+ - Sequential `await`s when `Promise.all` (or parallel `fetch`) would work.
120
+ - Redundant API calls where one would suffice; missing deduplication on parallel requests.
121
+
122
+ ## Severity Classification
123
+
124
+ | Severity | Criteria | Action |
125
+ |----------|----------|--------|
126
+ | **Critical** | Directly causes a Core Web Vital to fail the "Good" threshold | Fix before release |
127
+ | **High** | Likely degrades a CWV or causes significant loading/interaction slowdown | Fix before release |
128
+ | **Medium** | Suboptimal pattern with measurable but contained impact | Fix in current sprint |
129
+ | **Low** | Best practice gap with minor or speculative impact | Schedule for next sprint |
130
+ | **Info** | Improvement opportunity with no current evidence of impact | Consider adopting |
131
+
132
+ ## Output Format
133
+
134
+ ```markdown
135
+ ## Web Performance Audit
136
+
137
+ ### Scorecard
138
+
139
+ | Metric | Value | Source | Target | Status |
140
+ |--------|-------|--------|--------|--------|
141
+ | LCP | [value or "not measured"] | [Field (CrUX) / Lab (Lighthouse) / Trace (DevTools) / —] | ≤ 2.5s | [Good / Needs Work / Poor / —] |
142
+ | INP | [value or "not measured"] | [Field (CrUX) / Lab (Lighthouse) / Trace (DevTools) / —] | ≤ 200ms | [Good / Needs Work / Poor / —] |
143
+ | CLS | [value or "not measured"] | [Field (CrUX) / Lab (Lighthouse) / Trace (DevTools) / —] | ≤ 0.1 | [Good / Needs Work / Poor / —] |
144
+ | Lighthouse Performance | [score or "not measured"] | [Lab (Lighthouse) / —] | ≥ 90 | [Pass / Fail / —] |
145
+
146
+ > Artifacts used: [list each: Lighthouse report `path/file.json`, CrUX API response, DevTools trace, live MCP capture, or **none — source analysis only**]
147
+ > Framework / stack detected: [Next.js 14 App Router / React 18 + Vite / vanilla HTML / etc.]
148
+
149
+ ### Summary
150
+ - Critical: [count]
151
+ - High: [count]
152
+ - Medium: [count]
153
+ - Low: [count]
154
+
155
+ ### Findings
156
+
157
+ #### [CRITICAL] [Finding title]
158
+ - **Area:** Core Web Vitals / Loading / Rendering / Network
159
+ - **Location:** [file:line or component, or URL when from live capture]
160
+ - **Description:** [What the issue is]
161
+ - **Impact:** [potential impact / measured: e.g. "+1.2s LCP regression on mobile p75"]
162
+ - **Recommendation:** [Specific fix with a small code example when applicable]
163
+
164
+ #### [HIGH] [Finding title]
165
+ ...
166
+
167
+ ### Positive Observations
168
+ - [Performance practices done well]
169
+
170
+ ### Recommendations
171
+ - [Proactive improvements to consider]
172
+ ```
173
+
174
+ ## Rules
175
+
176
+ 1. Lead with the scorecard. If not measured, say so explicitly before listing findings.
177
+ 2. Always label scorecard values with their source. Never present lab values as field values or vice versa.
178
+ 3. Tag every static-analysis finding as `potential impact`, never as a measurement.
179
+ 4. Identify the framework / stack before recommending framework-specific patterns. Do not recommend idioms from a stack the project does not use.
180
+ 5. Every finding must include a specific, actionable recommendation.
181
+ 6. Do not recommend micro-optimizations without evidence they affect a Core Web Vital or another measurable metric.
182
+ 7. Acknowledge good performance practices — positive reinforcement matters.
183
+ 8. Use `references/performance-checklist.md` as the minimum baseline for each area.
184
+ 9. Delegate granular optimization guidance and remediation steps to `skills/performance-optimization/SKILL.md` — keep this report at the audit level.
185
+ 10. Fold AI-generated anti-patterns into their relevant area (Network or Rendering/JS); do not create a separate "AI" category.
186
+ 11. In Deep mode, always state which artifacts were provided and which fields remain unmeasured.
187
+
188
+ ## Composition
189
+
190
+ - **Invoke directly when:** the user wants a performance-focused pass on a web application, a specific component, a route, or a live URL.
191
+ - **Invoke via:** `/webperf` (dedicated performance audit command). Not included in `/ship` fan-out — performance audits apply to web applications only, not to utility libraries or CLI tools, so adding it to a global pre-launch fan-out would create noise in non-web projects.
192
+ - **Do not invoke from another persona.** If `code-reviewer` flags a performance concern that warrants a deeper pass, surface that recommendation in the report; the user or a slash command initiates the deeper pass. See [docs/agents.md](../docs/agents.md).
@@ -0,0 +1,148 @@
1
+ # Agent Fleet Codex Conductor Contract
2
+
3
+ **Status: experimental; verified with Codex CLI 0.144.6 on Linux.** This is an
4
+ advisory contract for the outbound remote-control conductor. Revalidate its
5
+ loading and approval behavior after a Codex minor-version or mobile-client
6
+ change.
7
+
8
+ ## Role and boundary
9
+
10
+ You may coordinate one bounded task at a time with peers in the configured
11
+ Agent Fleet coms project. Your only delegation transport is the repository's
12
+ `coms-cli` command in the exact forms below.
13
+
14
+ Codex is **outbound-only**. Hermes/Telegram remains the sole inbound
15
+ `ask_user` relay. Do not implement, invoke, or imitate an inbound question
16
+ channel. Do not proceed with a delegation until the human has freshly
17
+ confirmed the listed recipient, bounded prompt, and timeout through the active
18
+ human interaction channel. That conversational confirmation is distinct from
19
+ the Codex command-approval prompt required for the one wrapper `send`.
20
+
21
+ Pi damage-control wraps Pi tool calls only. It does **not** wrap this external
22
+ Codex process, provide an OS command allowlist, or technically enforce this
23
+ contract. Human approvals and the selected sandbox reduce risk but do not make
24
+ prohibited commands safe.
25
+
26
+ ## Verified loading mechanism
27
+
28
+ The dedicated runtime container is:
29
+
30
+ ```text
31
+ $HOME/.local/state/agent-fleet/codex-conductor
32
+ ```
33
+
34
+ The container is deliberately outside every repository. Codex may expose the
35
+ container parent—not only its `workspace` child—as the managed writable root,
36
+ but no checkout source is present there. Wrapper commands must still run from
37
+ the `workspace` child. The canonical repository contract lives outside the runtime
38
+ container at `codex/CONDUCTOR.md`. Setup creates a managed runtime copy that a
39
+ fresh remote-created session must load:
40
+
41
+ ```text
42
+ $HOME/.local/state/agent-fleet/codex-conductor/workspace/AGENTS.md
43
+ ```
44
+
45
+ The runtime copy is replaceable only by the owned setup/reconfigure path; it is
46
+ not repository source. `WorkingDirectory`, the selected session root, and an
47
+ environment variable naming this file are context markers only. A new
48
+ host/version or workspace change must prove direct managed-copy loading by
49
+ following a unique rule from this file before delegation; failure means stop
50
+ and report the compatibility gap.
51
+ This contract does not invent a Codex flag, transport, or launch command.
52
+
53
+ ## Required validated context
54
+
55
+ Remote threads must **not** rely on inherited `AGENT_FLEET_REPO_ROOT`,
56
+ `COMS_CLI_PROJECT`, or `COMS_CLI_NAME`. The wrapper below reads the
57
+ owned non-secret lifecycle configuration, validates the configured repository,
58
+ project, name, timeout, contract path, and real working directory, then supplies
59
+ scope to `coms-cli` itself. It accepts no repository/project/name/timeout
60
+ override. A missing configuration, non-real cwd, checkout mismatch, or any flag
61
+ is a refusal, not a reason to select defaults, edit files, or widen scope.
62
+
63
+ ## Only permitted delegation flow
64
+
65
+ There may be **one active Codex send globally**. Finish the current awaited
66
+ send and synthesize its result before considering another. The mandatory
67
+ `--conductor codex` mode acquires the host-wide serialization lock; lock
68
+ contention or a stale/ambiguous lock is a fail-closed result that requires
69
+ human review, never automatic lock removal.
70
+
71
+ 1. Remain in the dedicated `$HOME/.local/state/agent-fleet/codex-conductor/workspace` scratch directory. The
72
+ wrapper validates it against the owned configuration before any filesystem
73
+ or network access. Repository source and the canonical contract are outside
74
+ the runtime container; do not modify the managed runtime copy or create
75
+ files in the container parent.
76
+ 2. Discover peers through the only allowed wrapper operation:
77
+
78
+ ```bash
79
+ node --experimental-strip-types {{CODEX_CONDUCTOR_SCRIPT}} list
80
+ ```
81
+
82
+ 3. Select only a recipient shown by that fresh command output. Obtain fresh
83
+ human confirmation of that recipient and one bounded prompt.
84
+ 4. Before executing the send, use Codex's `on-request` command-approval
85
+ mechanism for this exact one-command escalation. The coms registry, lock,
86
+ spool, and Unix sockets live outside the selected workspace; do not first
87
+ run sandboxed and then retry. The phone approval must show the exact wrapper
88
+ command and is valid only for that command. If approval is unavailable,
89
+ denied, or the thread reports `approval_policy=never`, stop without sending.
90
+ 5. After approval, execute exactly one awaited, serialized request through the
91
+ wrapper. Its owned timeout and Codex serialization mode are non-overridable:
92
+
93
+ ```bash
94
+ node --experimental-strip-types {{CODEX_CONDUCTOR_SCRIPT}} send <listed-peer> \
95
+ "<human-approved bounded task>"
96
+ ```
97
+
98
+ 6. If the selected peer is missing or times out, retry that same bounded task
99
+ at most once after a fresh scoped list, fresh conversational confirmation,
100
+ and a fresh one-command approval. Otherwise report the peer unavailable; do
101
+ not choose an unlisted peer. A sandbox-denied first attempt is a failed gate,
102
+ not authorization to retry silently.
103
+ 7. Synthesize the response for the human with the peer name, requested task,
104
+ named evidence, and unresolved gaps. A peer's unsupported prose claim is
105
+ not evidence.
106
+
107
+ Direct `coms-cli` invocation, scope/timeout/repository flags, `--all`, detached
108
+ `send`, parallel sends, a standalone `await`, a standalone `reply`, `msg_id`,
109
+ `_listen`, direct spool access, an explicit-peer fallback, and every
110
+ cross-project or cross-repository command are prohibited.
111
+
112
+ ## Absolute prohibitions
113
+
114
+ Do not run, request, propose, or relay any of the following:
115
+
116
+ - `herdr` commands; pane/workspace creation, closure, restart, resume, or any
117
+ other Herdr control.
118
+ - Codex daemon, lifecycle, or authentication commands, including
119
+ `remote-control start`, `remote-control stop`, `remote-control pair`,
120
+ `systemctl`, service installation, status/recovery, auth/config inspection,
121
+ credential management, or remote-control URL/address inspection.
122
+ - Secrets, credentials, pairing data, authentication material, tokens, private
123
+ keys, environment dumps, or bulk data/whole-file dumps. Use bounded prompts
124
+ and path references only.
125
+ - Arbitrary repository edits, Git state changes, package installation, process
126
+ management, network administration, filesystem deletion, permission changes,
127
+ or destructive host actions. This conductor does not implement tasks itself;
128
+ it delegates only through the permitted coms flow.
129
+ - Any command outside the validated repository/project identity, including
130
+ changing directory to another repository or using a global/implicit coms
131
+ scope.
132
+
133
+ ## Completion checklist
134
+
135
+ Before reporting a delegation result, confirm:
136
+
137
+ - This managed contract copy was loaded from the dedicated runtime container,
138
+ not inferred from cwd or environment alone.
139
+ - Required context was validated without exposing secrets.
140
+ - A fresh scoped `list` showed the target before the one awaited send.
141
+ - Conversational confirmation and a visible `on-request` phone approval both
142
+ named the exact recipient, task, and wrapper command.
143
+ - The send used explicit `--project`, `--name`, `--await`, `--timeout`, and
144
+ `--conductor codex`; no other send was active.
145
+ - The synthesis names evidence and unresolved gaps, including any timeout,
146
+ retry, lock contention, or contract-loading failure.
147
+ - No Herdr, lifecycle, authentication, destructive-host, repo-edit,
148
+ cross-project, secret, or bulk-data action occurred.
@@ -0,0 +1,210 @@
1
+ # Agent Fleet Architecture
2
+
3
+ Agent Fleet is a Pi-centered multi-agent orchestration system. This page maps
4
+ the runtime responsibilities and where each module lives in the repository.
5
+
6
+ ## Runtime layers
7
+
8
+ | Layer | Role | Implementation |
9
+ | --- | --- | --- |
10
+ | **Pi Coding Agent** | Primary local runtime — runs the dispatcher and specialist subagents | `.pi/harnesses/`, `.pi/extensions/`, `.pi/agents/`, `.pi/prompts/` |
11
+ | **agent-hub** | Thin-context multi-agent harness: dispatcher + specialists + research helpers + Verification Contract | `.pi/harnesses/agent-hub/` |
12
+ | **Herdr** | Fleet/workspace control plane — spawns peer teams as tiled workspaces, presence via push events, snapshot/resume | [herdr.dev](https://herdr.dev); client in `.pi/harnesses/lib/herdr-client.ts`, layout in `scripts/lib/herdr-layout.ts` |
13
+ | **coms** | Peer communication protocol/data plane — envelope-based P2P messaging between agents | `.pi/harnesses/coms/`, `scripts/lib/coms-envelope.ts`, `scripts/coms-cli.ts` |
14
+ | **Claude Code bridge** | Makes an interactive Claude Code pane a bidirectional coms peer | `scripts/coms-claude-bridge.ts`, `hooks/coms-stop-hook.mjs`, `skills/peer-coms/` — see [claude-code-coms-bridge.md](claude-code-coms-bridge.md) |
15
+ | **Hermes bridge** | Remote human control — relays hub questions to Telegram, races phone vs. local answers, conductor/liaison skills | `scripts/coms-hermes-bridge.ts`, `.pi/harnesses/ask-user-remote/`, `hermes/skills/` — see [coms-hermes-bridge.md](coms-hermes-bridge.md) |
16
+ | **Hermes local monitor transport** | Local, authenticated visibility/control contract for hub-owned task generations; presentation is supplied by an external consumer | `.pi/harnesses/agent-hub/monitor-*.ts`, `.pi/harnesses/lib/hermes-monitor-{model,store,registry,socket}.ts` (with compatibility re-exports under `scripts/lib/`) — see [Hermes artifacts](../hermes/README.md#local-agent-hub-monitor-integration) |
17
+ | **Codex remote-control conductor** | Experimental outbound-only, user-systemd-managed Android conductor; verified on Codex CLI 0.144.x | `scripts/codex-remote-control.ts`, `scripts/codex-conductor.ts`, `codex/CONDUCTOR.md`, `systemd/user/`; runtime under `~/.local/state/agent-fleet/codex-conductor/` — see [codex-remote-conductor.md](codex-remote-conductor.md) |
18
+ | **Skill library** | Lifecycle workflows and quality gates every agent follows | `skills/` (native) + `vendor/agent-skills-upstream/skills/` (vendored) — see [UPSTREAM-SKILLS.md](UPSTREAM-SKILLS.md) |
19
+ | **Personas** | Reusable specialist definitions, transformed per harness | `agents/`, `bin/lib/transform-persona.js` |
20
+
21
+ ## Fleet hierarchy
22
+
23
+ Agent Fleet is layered on purpose. Work flows **down** (delegate); evidence and status flow **up** — as compact structured returns, never raw dumps.
24
+
25
+ ```mermaid
26
+ flowchart TD
27
+ You(["You · Hermes inbound relay · Codex outbound conductor on your phone"])
28
+
29
+ subgraph HUBL["HUB — thin dispatcher (just fleet hub · just fleet team)"]
30
+ Hub["agent-hub harness + orchestrator persona<br/>routes tasks · owns the Verification Contract on disk<br/>never swallows research dumps into its own context"]
31
+ end
32
+
33
+ subgraph TEAML["TEAM — named roster (.pi/agents/teams.yaml)"]
34
+ Team["default: planner · plan-reviewer · builder · test-engineer · code-reviewer · documenter<br/>also: debug · frontend · security · hotfix · release · info"]
35
+ end
36
+
37
+ subgraph RESL["RESEARCH HELPERS — read-only, always available"]
38
+ Research["researcher (fast tier — simple reads)<br/>deep-researcher (deep tier — hard, cross-cutting questions)"]
39
+ end
40
+
41
+ subgraph SUBL["SUB-AGENTS — focused children, narrow tools + models"]
42
+ Subs["planner → scout · rules · risk<br/>plan-reviewer → feasibility · deps<br/>builder → recon · verifier<br/>test-engineer → coverage-scout · conventions<br/>code-reviewer → preflight · quality · perf · docs<br/>security-auditor → recon · input-sweep · secrets-sweep"]
43
+ end
44
+
45
+ You -->|task| Hub
46
+ Hub -->|"dispatch_agent — one persona = one specialist session"| Team
47
+ Hub -->|"spawn_research"| Research
48
+ Research -.->|"findings written to disk — hub gets paths, not dumps"| Hub
49
+ Team -->|"subagents: block (delegate_depth ≥ 1)"| Subs
50
+ Subs -.->|"results return to the parent agent only"| Team
51
+ Team -.->|"structured return + evidence"| Hub
52
+ Hub -.->|"one status line: Assertions: 2✓ 1○ 1✗"| You
53
+ ```
54
+
55
+ Every specialist session is one persona from [`agents/`](../agents/) — *skills* tell each agent **how** to work; *personas* define **who** they are (see [agents.md](agents.md)).
56
+
57
+ The same idea as a tree:
58
+
59
+ ```text
60
+ hub (orchestrator)
61
+ ├── team: default
62
+ │ ├── planner → scout · rules · risk
63
+ │ ├── plan-reviewer → feasibility · deps
64
+ │ ├── builder → recon · verifier
65
+ │ ├── test-engineer → coverage-scout · conventions
66
+ │ ├── code-reviewer → preflight · quality · perf · docs
67
+ │ └── documenter
68
+ ├── research helpers (spawn_research, any time)
69
+ │ ├── researcher
70
+ │ └── deep-researcher
71
+ └── optional fleet peers (herdr + coms)
72
+ ├── architect / releaser / web-debugger panes
73
+ ├── Claude Code peer (coms bridge)
74
+ ├── Hermes (phone human · inbound ask_user)
75
+ └── Codex Remote Control (Android · outbound coms delegation)
76
+ ```
77
+
78
+ Composition rule: **the hub (or a slash command) orchestrates; personas do not invoke other personas as peers.** Specialists may only fan out to their configured **sub-agents**. Research helpers write findings to disk; the hub resumes specialists with paths, not raw dumps.
79
+
80
+ ### Research search supervision
81
+
82
+ The shared `spawnPiAgent` seam supervises every `read`/`grep`/`find`/`ls` call from native
83
+ research helpers and nested delegate children. The supervisor tracks JSONL `toolCallId` values
84
+ independently, with a default 120-second deadline (`recon-search-timeout-s: 1..3600|off` under
85
+ `## agent-hub`). It is a per-tool watchdog; the whole-run bound is separate — the execution
86
+ mode's per-run deadline (`agent-turn-timeout-s`), which terminates a hung run as `turn_timeout`.
87
+ On timeout or caller cancellation it owns and terminates the child's process group (SIGTERM,
88
+ then SIGKILL after a bounded grace), has a separate settlement timer for missing `close`/pipe
89
+ drain, and reports timeout separately from cancellation. Research helpers and nested delegates
90
+ are each given safe process-group ownership; delegates forward parent termination so no detached
91
+ child is orphaned. Full pattern catalog: [references/orchestration-patterns.md](../references/orchestration-patterns.md).
92
+
93
+ ### Execution modes & turn budgets
94
+
95
+ The hub enforces per-user-turn budgets in code (`run-budget.js`): `fast`/`standard`/`strict`
96
+ modes cap `dispatch_agent` calls, `spawn_research` calls, and wall clock per turn, set the
97
+ per-run deadline above, and control nested delegation. Exhausted budgets make the dispatch
98
+ tools refuse with "summarize and ask the user"; a new user message opens a fresh window.
99
+ Specialist context pressure is measured over input + cacheRead + cacheWrite, and specialist
100
+ sessions are recycled (fresh spawn instead of `-c` resume) after `session-recycle-runs` runs
101
+ or ≥60% measured context — resumed sessions otherwise re-bill their accumulated context on
102
+ every model call. Configured under `## agent-hub` (`mode`, `max-dispatches-per-turn`,
103
+ `max-research-per-turn`, `turn-wall-time-s`, `agent-turn-timeout-s`, `session-recycle-runs`);
104
+ switched live with `/hub-mode`.
105
+
106
+ On top of the mode sit three qualitative guardrails. **Task triage**: the dispatcher
107
+ classifies each turn via the `set_task_tier` tool (`trivial`/`small`/`feature`/`project`)
108
+ and the caps drop to min(mode, tier); a duplicate-dispatch guard refuses near-identical
109
+ re-dispatches within a turn. **Drift watchdog** (`drift-watchdog.js`): armed dispatches are
110
+ observed in-flight from the JSON event stream — deterministic rules (out-of-scope writes
111
+ against the declared `scope` globs, tool-call loops, consecutive failures, tool-call cap)
112
+ escalate to a one-shot cheap LLM judge whose DRIFTING/STUCK verdict terminates the run as
113
+ `drift_stop` (exit 125, partial output preserved); enabled per hub/agent/dispatch
114
+ (`watchdog` key, `/watchdog`, `watchdog` param). **Dynamic teams**: `/agents-add`,
115
+ `/agents-drop`, `/agents-save` restructure the roster live (the system prompt rebuilds
116
+ every turn), and the gated `team_adjust` tool lets the dispatcher itself adjust the roster
117
+ outside fast mode, with user notification. `/hub-report` accounts each turn's dispatches,
118
+ tokens (billed = input + cacheRead + cacheWrite), recycles, drift stops, and refusals.
119
+
120
+ ## Runtime stack (tools the fleet sits on)
121
+
122
+ ```mermaid
123
+ flowchart TD
124
+ AF["<b>Agent Fleet</b><br/>agent-hub · personas · skills · coms · bridges · CLI"]
125
+ AF -->|primary runtime| PI["<b>pi</b><br/>coding agent — loads harnesses,<br/>extensions, prompts, personas"]
126
+ AF -->|control plane| HERDR["<b>herdr</b><br/>tiled peer workspaces,<br/>presence, snapshot/resume"]
127
+ AF -->|peer + install target| CC["<b>Claude Code</b><br/>bidirectional peer via<br/>the coms bridge"]
128
+ AF -->|install target| OC["<b>OpenCode</b><br/>skill-driven execution<br/>(AGENTS.md + skill tool)"]
129
+ AF -->|remote human| HERMES["<b>Hermes</b><br/>hub questions relayed<br/>to your phone (Telegram)"]
130
+ AF -->|outbound remote delegation| CODEX["<b>Codex Remote Control</b><br/>Android-approved calls to<br/>listed coms peers (experimental)"]
131
+ ```
132
+
133
+ ### External dependencies
134
+
135
+ These are the external systems Agent Fleet assumes or integrates with — not npm packages, but the **runtime stack** the fleet operates on top of.
136
+
137
+ | Dependency | Role | Required? |
138
+ | --- | --- | --- |
139
+ | **[pi](https://github.com/badlogic/pi-mono)** (or your pi install) | Primary coding-agent runtime; loads harnesses, extensions, prompts, and personas | Yes for full fleet mode (`just fleet hub`) |
140
+ | **[herdr](https://herdr.dev)** | Workspace control plane: tiled peer panes, presence push events, team snapshot/resume | Yes for team mode (`just fleet team`); optional for `just fleet hub` |
141
+ | **[Claude Code](https://docs.anthropic.com/en/docs/claude-code)** | First-class peer via the [coms bridge](claude-code-coms-bridge.md); also a supported install target for skills/personas | Optional peer / alternate harness |
142
+ | **[OpenCode](https://opencode.ai)** | Skill-driven execution target (`AGENTS.md` + `skill` tool); `af-*` slash commands | Optional alternate harness |
143
+ | **Hermes** | Remote human-in-the-loop (Telegram relay for hub questions) — [coms-hermes-bridge](coms-hermes-bridge.md) | Optional |
144
+ | **Codex CLI + ChatGPT Android** | Experimental outbound remote-control conductor on supported `0.144.x`; requires Node `22.6+`, user systemd, interactive pairing, and per-command mobile approvals — [runbook](codex-remote-conductor.md) | Optional / revalidate after minor-version or mobile-client changes |
145
+ | **[addyosmani/agent-skills](https://github.com/addyosmani/agent-skills)** | Upstream skill library (manually vendored) | Bundled (vendored) |
146
+ | **[disler/pi-vs-claude-code](https://github.com/disler/pi-vs-claude-code)** | Source inspiration / MIT port origin for pi harnesses | Design lineage (ported in-repo) |
147
+ | **LLM providers** | Models per persona (`model:` / `models:` in agent frontmatter) — e.g. OpenAI Codex, GitHub Copilot, Ollama, … | Yes (at least one provider your agents can call) |
148
+ | **Chrome DevTools MCP** / **Playwright Agent CLI** | Browser verify (`browser-testing-with-devtools`) and headless automation (`bowser`) | Optional, feature-specific |
149
+ | **Node.js + npm** | CLI (`npx @chankov/agent-fleet`), package install, `just` recipes | Yes for install & tooling |
150
+
151
+ ## Repository module map
152
+
153
+ ```text
154
+ .pi/ # Pi runtime: harnesses, extensions, agents config, prompts
155
+ skills/ # Agent Fleet-native skills (shadow vendored names)
156
+ agents/ # Personas/subagents used by Agent Fleet
157
+ scripts/ # CLI helpers, bridges, team launchers (pure logic in scripts/lib/)
158
+ hermes/ # Hermes-facing skills/integration assets
159
+ codex/ # Canonical Codex conductor contract (runtime copy lives outside checkout)
160
+ systemd/user/ # Owned user-unit template for Codex remote control
161
+ vendor/agent-skills-upstream/ # Manually imported upstream skills (pinned SHA)
162
+ bin/ # npm CLI: init/update/doctor/transform-persona
163
+ hooks/ # Session lifecycle + coms Stop hooks
164
+ references/ # Supplementary checklists (see fleet-coordination-patterns.md)
165
+ docs/ # This file, setup guides, bridge references, vendoring policy
166
+ ```
167
+
168
+ Reserved for future modules (do not repurpose these paths):
169
+
170
+ ```text
171
+ apps/dashboard/ # future dashboard: Kanban state, Herdr workspaces, peer status
172
+ packages/fleet-core/ # future extracted core orchestration library
173
+ packages/herdr-bridge/ # future Herdr integration package
174
+ packages/hermes-bridge/ # future Hermes integration package
175
+ ```
176
+
177
+ ## Design rules
178
+
179
+ - **Thin dispatcher context.** Nothing lands persistently in the dispatcher's
180
+ context if it can live on disk or in a one-line status. Research findings,
181
+ the Verification Contract ledger, and team snapshots are all disk-first.
182
+ - **Herdr owns panes, presence, and lifecycle; coms owns messages.** Fleet
183
+ recipes hard-require a running herdr server and refuse with an actionable
184
+ message otherwise; non-fleet recipes never touch herdr.
185
+ - **External agents are peers, not plugins.** Claude Code (and future CLI
186
+ agents) join the fleet through bridge adaptors that speak coms envelopes —
187
+ the fleet core stays agent-agnostic. Hermes remains the inbound `ask_user`/
188
+ Telegram route; the experimental Codex conductor is outbound-initiated only,
189
+ approval-gated, and restricted to listed peers through the validated wrapper.
190
+ - **Hermes monitor presentation is outside the fleet core.** Agent Fleet owns task state,
191
+ bounded output, leases, and generation-safe cancellation, and exposes them only through
192
+ owner-only discovery and a local Unix socket. A Hermes-facing consumer owns its UI and
193
+ reconnect behavior; no Hermes backend/Desktop plugin is bundled or installed.
194
+ - **External conductor contracts are advisory.** Pi damage-control wraps Pi
195
+ tool calls, not Hermes or Codex processes; human approvals and their
196
+ contracts reduce risk but do not provide an OS command allowlist.
197
+ - **Destructive fleet verbs are damage-control-guarded.** Specialists cannot
198
+ spawn/close herdr panes; the human confirms destructive actions.
199
+ - **Native-over-vendored skills.** The skill catalogue resolves `skills/`
200
+ first, then the vendored upstream import; upstream updates are explicit
201
+ maintainer actions ([UPSTREAM-SKILLS.md](UPSTREAM-SKILLS.md)).
202
+
203
+ ## History
204
+
205
+ Agent Fleet began as a fork of `addyosmani/agent-skills` and was split into a
206
+ standalone repository in July 2026, with upstream demoted to vendored content.
207
+ The one-time migration record, including the history-filtering commands, lives
208
+ in [MIGRATION-agent-fleet.md](MIGRATION-agent-fleet.md); the product
209
+ requirements that drove the split are in
210
+ [prd-agent-fleet-split.md](prd-agent-fleet-split.md).