@chankov/agent-fleet 1.0.3 → 1.0.4

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 (310) hide show
  1. package/.pi/harnesses/agent-hub/README.md +25 -11
  2. package/.pi/harnesses/agent-hub/delegate.ts +14 -3
  3. package/.pi/harnesses/agent-hub/index.ts +212 -40
  4. package/.pi/harnesses/agent-hub/package.json +1 -1
  5. package/.pi/harnesses/agent-hub/spawn.ts +25 -3
  6. package/.pi/harnesses/coms/package.json +1 -1
  7. package/.pi/harnesses/damage-control-continue/package.json +1 -1
  8. package/.pi/harnesses/lib/fleet-dashboard-ops.ts +2 -2
  9. package/.pi/harnesses/lib/fleet-detail-view.ts +95 -16
  10. package/.pi/harnesses/lib/fleet-transcript-store.ts +244 -0
  11. package/.pi/prompts/af-plan.md +6 -5
  12. package/.versions/1.0.4/.pi/agents/dispatch-policy.yaml +32 -0
  13. package/.versions/1.0.4/.pi/agents/model-profiles.yaml +27 -0
  14. package/.versions/1.0.4/.pi/agents/peers.yaml +142 -0
  15. package/.versions/1.0.4/.pi/agents/teams.yaml +41 -0
  16. package/.versions/1.0.4/.pi/damage-control-rules.yaml +297 -0
  17. package/.versions/1.0.4/.pi/extensions/agent-fleet-update-check/README.md +57 -0
  18. package/.versions/1.0.4/.pi/extensions/agent-fleet-update-check/index.ts +161 -0
  19. package/.versions/1.0.4/.pi/extensions/agent-fleet-update-check/package.json +6 -0
  20. package/.versions/1.0.4/.pi/extensions/btw/README.md +120 -0
  21. package/.versions/1.0.4/.pi/extensions/btw/index.ts +914 -0
  22. package/.versions/1.0.4/.pi/extensions/btw/package.json +6 -0
  23. package/.versions/1.0.4/.pi/extensions/btw/state.js +179 -0
  24. package/.versions/1.0.4/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
  25. package/.versions/1.0.4/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
  26. package/.versions/1.0.4/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
  27. package/.versions/1.0.4/.pi/extensions/compact-and-continue/README.md +42 -0
  28. package/.versions/1.0.4/.pi/extensions/compact-and-continue/index.ts +120 -0
  29. package/.versions/1.0.4/.pi/extensions/compact-and-continue/package.json +6 -0
  30. package/.versions/1.0.4/.pi/extensions/mcp-bridge/README.md +46 -0
  31. package/.versions/1.0.4/.pi/extensions/mcp-bridge/index.ts +206 -0
  32. package/.versions/1.0.4/.pi/extensions/mcp-bridge/package.json +6 -0
  33. package/.versions/1.0.4/.pi/extensions/package-lock.json +1175 -0
  34. package/.versions/1.0.4/.pi/extensions/package.json +9 -0
  35. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/README.md +205 -0
  36. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/config.ts +198 -0
  37. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
  38. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/index.ts +248 -0
  39. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/package.json +6 -0
  40. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/providers.ts +214 -0
  41. package/.versions/1.0.4/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
  42. package/.versions/1.0.4/.pi/harnesses/agent-hub/README.md +1170 -0
  43. package/.versions/1.0.4/.pi/harnesses/agent-hub/access-approval.ts +135 -0
  44. package/.versions/1.0.4/.pi/harnesses/agent-hub/artifacts.js +146 -0
  45. package/.versions/1.0.4/.pi/harnesses/agent-hub/assertion-ledger.js +58 -0
  46. package/.versions/1.0.4/.pi/harnesses/agent-hub/backend-policy.js +174 -0
  47. package/.versions/1.0.4/.pi/harnesses/agent-hub/budget-continuation.ts +73 -0
  48. package/.versions/1.0.4/.pi/harnesses/agent-hub/capability-confirmation.ts +47 -0
  49. package/.versions/1.0.4/.pi/harnesses/agent-hub/capability-packs.ts +180 -0
  50. package/.versions/1.0.4/.pi/harnesses/agent-hub/context-budget-snapshot.ts +105 -0
  51. package/.versions/1.0.4/.pi/harnesses/agent-hub/context-pressure.ts +191 -0
  52. package/.versions/1.0.4/.pi/harnesses/agent-hub/context-window.js +106 -0
  53. package/.versions/1.0.4/.pi/harnesses/agent-hub/delegate.ts +446 -0
  54. package/.versions/1.0.4/.pi/harnesses/agent-hub/docs-lane.js +122 -0
  55. package/.versions/1.0.4/.pi/harnesses/agent-hub/drift-watchdog.js +218 -0
  56. package/.versions/1.0.4/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
  57. package/.versions/1.0.4/.pi/harnesses/agent-hub/execution-profile.ts +69 -0
  58. package/.versions/1.0.4/.pi/harnesses/agent-hub/external-blocker.js +85 -0
  59. package/.versions/1.0.4/.pi/harnesses/agent-hub/footer.ts +36 -0
  60. package/.versions/1.0.4/.pi/harnesses/agent-hub/helpers.ts +266 -0
  61. package/.versions/1.0.4/.pi/harnesses/agent-hub/hub-state-audit.js +59 -0
  62. package/.versions/1.0.4/.pi/harnesses/agent-hub/index.ts +10171 -0
  63. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
  64. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
  65. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
  66. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
  67. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
  68. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
  69. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
  70. package/.versions/1.0.4/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
  71. package/.versions/1.0.4/.pi/harnesses/agent-hub/package.json +7 -0
  72. package/.versions/1.0.4/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
  73. package/.versions/1.0.4/.pi/harnesses/agent-hub/posture.ts +158 -0
  74. package/.versions/1.0.4/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
  75. package/.versions/1.0.4/.pi/harnesses/agent-hub/research-retention.js +34 -0
  76. package/.versions/1.0.4/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
  77. package/.versions/1.0.4/.pi/harnesses/agent-hub/return-contract.js +293 -0
  78. package/.versions/1.0.4/.pi/harnesses/agent-hub/return-extract.js +75 -0
  79. package/.versions/1.0.4/.pi/harnesses/agent-hub/review-findings.js +102 -0
  80. package/.versions/1.0.4/.pi/harnesses/agent-hub/run-budget.js +537 -0
  81. package/.versions/1.0.4/.pi/harnesses/agent-hub/run-namespace.js +87 -0
  82. package/.versions/1.0.4/.pi/harnesses/agent-hub/safety-routing.ts +22 -0
  83. package/.versions/1.0.4/.pi/harnesses/agent-hub/scope-gate.js +103 -0
  84. package/.versions/1.0.4/.pi/harnesses/agent-hub/session-health.js +110 -0
  85. package/.versions/1.0.4/.pi/harnesses/agent-hub/spawn.ts +388 -0
  86. package/.versions/1.0.4/.pi/harnesses/agent-hub/version.ts +42 -0
  87. package/.versions/1.0.4/.pi/harnesses/ask-user-remote/README.md +53 -0
  88. package/.versions/1.0.4/.pi/harnesses/ask-user-remote/index.ts +532 -0
  89. package/.versions/1.0.4/.pi/harnesses/ask-user-remote/race-core.js +106 -0
  90. package/.versions/1.0.4/.pi/harnesses/coms/README.md +100 -0
  91. package/.versions/1.0.4/.pi/harnesses/coms/index.ts +1767 -0
  92. package/.versions/1.0.4/.pi/harnesses/coms/package.json +7 -0
  93. package/.versions/1.0.4/.pi/harnesses/coms/version.ts +42 -0
  94. package/.versions/1.0.4/.pi/harnesses/damage-control-continue/README.md +124 -0
  95. package/.versions/1.0.4/.pi/harnesses/damage-control-continue/index.ts +536 -0
  96. package/.versions/1.0.4/.pi/harnesses/damage-control-continue/package.json +7 -0
  97. package/.versions/1.0.4/.pi/harnesses/damage-control-continue/version.ts +42 -0
  98. package/.versions/1.0.4/.pi/harnesses/lib/coms-registry-entry.ts +94 -0
  99. package/.versions/1.0.4/.pi/harnesses/lib/context-budget-child-prompt.ts +179 -0
  100. package/.versions/1.0.4/.pi/harnesses/lib/context-budget-hub-prompt.ts +116 -0
  101. package/.versions/1.0.4/.pi/harnesses/lib/context-budget-view.ts +107 -0
  102. package/.versions/1.0.4/.pi/harnesses/lib/context-budget.ts +114 -0
  103. package/.versions/1.0.4/.pi/harnesses/lib/damage-control-shared.ts +197 -0
  104. package/.versions/1.0.4/.pi/harnesses/lib/fixtures/context-budget-profiles.json +11 -0
  105. package/.versions/1.0.4/.pi/harnesses/lib/fixtures/hub-prompt-operator.legacy.txt +73 -0
  106. package/.versions/1.0.4/.pi/harnesses/lib/fixtures/hub-prompt-orchestrator.legacy.txt +73 -0
  107. package/.versions/1.0.4/.pi/harnesses/lib/fleet-dashboard-ops.ts +155 -0
  108. package/.versions/1.0.4/.pi/harnesses/lib/fleet-dashboard-view.ts +142 -0
  109. package/.versions/1.0.4/.pi/harnesses/lib/fleet-detail-view.ts +247 -0
  110. package/.versions/1.0.4/.pi/harnesses/lib/fleet-overlay.ts +26 -0
  111. package/.versions/1.0.4/.pi/harnesses/lib/fleet-panel.ts +34 -0
  112. package/.versions/1.0.4/.pi/harnesses/lib/fleet-read-model.ts +131 -0
  113. package/.versions/1.0.4/.pi/harnesses/lib/fleet-selection.ts +24 -0
  114. package/.versions/1.0.4/.pi/harnesses/lib/fleet-transcript-store.ts +244 -0
  115. package/.versions/1.0.4/.pi/harnesses/lib/herdr-client.ts +472 -0
  116. package/.versions/1.0.4/.pi/harnesses/lib/herdr-presence.ts +399 -0
  117. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
  118. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
  119. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
  120. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
  121. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
  122. package/.versions/1.0.4/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
  123. package/.versions/1.0.4/.pi/harnesses/lib/spawned-peers.js +190 -0
  124. package/.versions/1.0.4/.pi/harnesses/package-lock.json +2039 -0
  125. package/.versions/1.0.4/.pi/harnesses/package.json +10 -0
  126. package/.versions/1.0.4/.pi/prompts/af-build.md +24 -0
  127. package/.versions/1.0.4/.pi/prompts/af-code-simplify.md +22 -0
  128. package/.versions/1.0.4/.pi/prompts/af-plan.md +17 -0
  129. package/.versions/1.0.4/.pi/prompts/af-review.md +16 -0
  130. package/.versions/1.0.4/.pi/prompts/af-set-hermes-telegram.md +15 -0
  131. package/.versions/1.0.4/.pi/prompts/af-set-hermes-watchdog.md +6 -0
  132. package/.versions/1.0.4/.pi/prompts/af-ship.md +17 -0
  133. package/.versions/1.0.4/.pi/prompts/af-spec.md +15 -0
  134. package/.versions/1.0.4/.pi/prompts/af-test.md +19 -0
  135. package/.versions/1.0.4/.pi/skills/bowser/SKILL.md +145 -0
  136. package/.versions/1.0.4/.version +1 -0
  137. package/.versions/1.0.4/agents/architect.md +25 -0
  138. package/.versions/1.0.4/agents/bowser.md +28 -0
  139. package/.versions/1.0.4/agents/builder.md +56 -0
  140. package/.versions/1.0.4/agents/code-reviewer.md +209 -0
  141. package/.versions/1.0.4/agents/deep-researcher.md +33 -0
  142. package/.versions/1.0.4/agents/documenter.md +19 -0
  143. package/.versions/1.0.4/agents/orchestrator.md +21 -0
  144. package/.versions/1.0.4/agents/plan-reviewer.md +84 -0
  145. package/.versions/1.0.4/agents/planner.md +71 -0
  146. package/.versions/1.0.4/agents/releaser.md +25 -0
  147. package/.versions/1.0.4/agents/researcher.md +29 -0
  148. package/.versions/1.0.4/agents/security-auditor.md +168 -0
  149. package/.versions/1.0.4/agents/test-engineer.md +154 -0
  150. package/.versions/1.0.4/agents/web-debugger.md +44 -0
  151. package/.versions/1.0.4/agents/web-performance-auditor.md +194 -0
  152. package/.versions/1.0.4/bin/catalog/harness-runtime-closure.json +38 -0
  153. package/.versions/1.0.4/codex/CONDUCTOR.md +148 -0
  154. package/.versions/1.0.4/docs/ARCHITECTURE.md +375 -0
  155. package/.versions/1.0.4/docs/agent-fleet-setup.md +468 -0
  156. package/.versions/1.0.4/docs/claude-code-coms-bridge.md +128 -0
  157. package/.versions/1.0.4/docs/codex-remote-conductor.md +170 -0
  158. package/.versions/1.0.4/docs/coms-hermes-bridge.md +189 -0
  159. package/.versions/1.0.4/docs/getting-started.md +98 -0
  160. package/.versions/1.0.4/docs/npm-install.md +292 -0
  161. package/.versions/1.0.4/docs/pi-extensions.md +441 -0
  162. package/.versions/1.0.4/docs/pi-setup.md +74 -0
  163. package/.versions/1.0.4/docs/skill-anatomy.md +150 -0
  164. package/.versions/1.0.4/hermes/README.md +347 -0
  165. package/.versions/1.0.4/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
  166. package/.versions/1.0.4/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
  167. package/.versions/1.0.4/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
  168. package/.versions/1.0.4/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
  169. package/.versions/1.0.4/hermes/gates/gate-o-capability.md +8 -0
  170. package/.versions/1.0.4/hermes/gates/gate-o-validator-fixtures.json +1 -0
  171. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +770 -0
  172. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
  173. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
  174. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
  175. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
  176. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
  177. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
  178. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
  179. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
  180. package/.versions/1.0.4/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
  181. package/.versions/1.0.4/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
  182. package/.versions/1.0.4/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
  183. package/.versions/1.0.4/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
  184. package/.versions/1.0.4/hermes/skills/hub-conductor/SKILL.md +84 -0
  185. package/.versions/1.0.4/hermes/skills/hub-liaison/SKILL.md +84 -0
  186. package/.versions/1.0.4/hermes/skills/hub-watchdog/SKILL.md +76 -0
  187. package/.versions/1.0.4/hermes/skills/hub-watchdog/manifest.json +1 -0
  188. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
  189. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
  190. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
  191. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
  192. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
  193. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
  194. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
  195. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
  196. package/.versions/1.0.4/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
  197. package/.versions/1.0.4/hermes/watchdog-tests/__init__.py +0 -0
  198. package/.versions/1.0.4/hooks/coms-stop-hook.mjs +84 -0
  199. package/.versions/1.0.4/install-manifest.json +2745 -0
  200. package/.versions/1.0.4/justfile +272 -0
  201. package/.versions/1.0.4/manifest-meta.json +882 -0
  202. package/.versions/1.0.4/references/accessibility-checklist.md +160 -0
  203. package/.versions/1.0.4/references/definition-of-done.md +67 -0
  204. package/.versions/1.0.4/references/fleet-coordination-patterns.md +151 -0
  205. package/.versions/1.0.4/references/observability-checklist.md +91 -0
  206. package/.versions/1.0.4/references/orchestration-patterns.md +370 -0
  207. package/.versions/1.0.4/references/performance-checklist.md +153 -0
  208. package/.versions/1.0.4/references/prompting-patterns.md +380 -0
  209. package/.versions/1.0.4/references/security-checklist.md +179 -0
  210. package/.versions/1.0.4/references/testing-patterns.md +236 -0
  211. package/.versions/1.0.4/scripts/codex-conductor.ts +41 -0
  212. package/.versions/1.0.4/scripts/codex-remote-control.ts +167 -0
  213. package/.versions/1.0.4/scripts/coms-claude-bridge.ts +411 -0
  214. package/.versions/1.0.4/scripts/coms-cli.ts +484 -0
  215. package/.versions/1.0.4/scripts/coms-hermes-bridge.ts +413 -0
  216. package/.versions/1.0.4/scripts/fleet.ts +185 -0
  217. package/.versions/1.0.4/scripts/hermes-monitor-capability-runner.ts +25 -0
  218. package/.versions/1.0.4/scripts/hermes-monitor-scenario.ts +474 -0
  219. package/.versions/1.0.4/scripts/hermes-watchdog-capability-probe.ts +45 -0
  220. package/.versions/1.0.4/scripts/install-hermes-plugin.sh +180 -0
  221. package/.versions/1.0.4/scripts/lib/claude-bridge-core.ts +210 -0
  222. package/.versions/1.0.4/scripts/lib/codex-conductor.ts +88 -0
  223. package/.versions/1.0.4/scripts/lib/codex-remote-control.ts +480 -0
  224. package/.versions/1.0.4/scripts/lib/coms-envelope.ts +582 -0
  225. package/.versions/1.0.4/scripts/lib/fake-herdr-server.ts +88 -0
  226. package/.versions/1.0.4/scripts/lib/fleet-command.ts +266 -0
  227. package/.versions/1.0.4/scripts/lib/herdr-layout.ts +281 -0
  228. package/.versions/1.0.4/scripts/lib/hermes-bridge-core.ts +241 -0
  229. package/.versions/1.0.4/scripts/lib/hermes-monitor-events.ts +1 -0
  230. package/.versions/1.0.4/scripts/lib/hermes-monitor-herdr.ts +2 -0
  231. package/.versions/1.0.4/scripts/lib/hermes-monitor-model.ts +3 -0
  232. package/.versions/1.0.4/scripts/lib/hermes-monitor-registry.ts +2 -0
  233. package/.versions/1.0.4/scripts/lib/hermes-monitor-socket.ts +2 -0
  234. package/.versions/1.0.4/scripts/lib/hermes-monitor-store.ts +2 -0
  235. package/.versions/1.0.4/scripts/lib/monitor-env.ts +146 -0
  236. package/.versions/1.0.4/scripts/lib/peer-launch.ts +318 -0
  237. package/.versions/1.0.4/scripts/lib/persona-banner.ts +62 -0
  238. package/.versions/1.0.4/scripts/lib/spawn-stagger.ts +101 -0
  239. package/.versions/1.0.4/scripts/lib/team-project.ts +213 -0
  240. package/.versions/1.0.4/scripts/lib/team-snapshot.ts +147 -0
  241. package/.versions/1.0.4/scripts/peer-banner.ts +40 -0
  242. package/.versions/1.0.4/scripts/peer-launch.ts +259 -0
  243. package/.versions/1.0.4/scripts/team-snapshot.ts +237 -0
  244. package/.versions/1.0.4/scripts/team-up.ts +406 -0
  245. package/.versions/1.0.4/skills/_internal/grilling.md +59 -0
  246. package/.versions/1.0.4/skills/browser-testing-with-devtools/SKILL.md +351 -0
  247. package/.versions/1.0.4/skills/code-review-and-quality/SKILL.md +381 -0
  248. package/.versions/1.0.4/skills/compound-learning/SKILL.md +137 -0
  249. package/.versions/1.0.4/skills/context-engineering/SKILL.md +291 -0
  250. package/.versions/1.0.4/skills/deprecation-and-migration/SKILL.md +206 -0
  251. package/.versions/1.0.4/skills/designing-agents/SKILL.md +394 -0
  252. package/.versions/1.0.4/skills/designing-agents/pi-harness-authoring.md +222 -0
  253. package/.versions/1.0.4/skills/frontend-ui-engineering/SKILL.md +328 -0
  254. package/.versions/1.0.4/skills/git-workflow-and-versioning/SKILL.md +316 -0
  255. package/.versions/1.0.4/skills/idea-refine/SKILL.md +182 -0
  256. package/.versions/1.0.4/skills/idea-refine/examples.md +238 -0
  257. package/.versions/1.0.4/skills/idea-refine/frameworks.md +99 -0
  258. package/.versions/1.0.4/skills/idea-refine/refinement-criteria.md +113 -0
  259. package/.versions/1.0.4/skills/idea-refine/scripts/idea-refine.sh +15 -0
  260. package/.versions/1.0.4/skills/incremental-implementation/SKILL.md +298 -0
  261. package/.versions/1.0.4/skills/interview-me/SKILL.md +226 -0
  262. package/.versions/1.0.4/skills/orchestration-verification/SKILL.md +181 -0
  263. package/.versions/1.0.4/skills/peer-coms/SKILL.md +90 -0
  264. package/.versions/1.0.4/skills/performance-optimization/SKILL.md +350 -0
  265. package/.versions/1.0.4/skills/planning-and-task-breakdown/SKILL.md +263 -0
  266. package/.versions/1.0.4/skills/security-and-hardening/SKILL.md +461 -0
  267. package/.versions/1.0.4/skills/spec-driven-development/SKILL.md +256 -0
  268. package/.versions/1.0.4/skills/using-agent-skills/SKILL.md +197 -0
  269. package/.versions/1.0.4/systemd/user/agent-fleet-codex-remote-control.service.in +23 -0
  270. package/.versions/1.0.4/vendor/agent-skills-upstream/LICENSE +21 -0
  271. package/.versions/1.0.4/vendor/agent-skills-upstream/README.md +11 -0
  272. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +294 -0
  273. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
  274. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
  275. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
  276. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
  277. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +289 -0
  278. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
  279. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
  280. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +278 -0
  281. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
  282. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
  283. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
  284. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
  285. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
  286. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
  287. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
  288. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
  289. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
  290. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
  291. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +203 -0
  292. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +350 -0
  293. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +234 -0
  294. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +467 -0
  295. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +310 -0
  296. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +194 -0
  297. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +206 -0
  298. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +383 -0
  299. package/.versions/1.0.4/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +191 -0
  300. package/CHANGELOG.md +7 -0
  301. package/agents/builder.md +1 -0
  302. package/agents/planner.md +1 -1
  303. package/install-manifest.json +3 -3
  304. package/package.json +2 -2
  305. package/skills/_internal/grilling.md +53 -5
  306. package/skills/idea-refine/SKILL.md +2 -2
  307. package/skills/incremental-implementation/SKILL.md +12 -1
  308. package/skills/planning-and-task-breakdown/SKILL.md +14 -5
  309. package/skills/spec-driven-development/SKILL.md +10 -11
  310. package/skills/using-agent-skills/SKILL.md +13 -15
@@ -0,0 +1,191 @@
1
+ ---
2
+ name: using-agent-skills
3
+ description: Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
4
+ ---
5
+
6
+ # Using Agent Skills
7
+
8
+ ## Overview
9
+
10
+ Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.
11
+
12
+ ## Skill Discovery
13
+
14
+ When a task arrives, identify the development phase and apply the corresponding skill:
15
+
16
+ ```
17
+ Task arrives
18
+ │
19
+ ├── Don't know what you want yet? ──────→ interview-me
20
+ ├── Have a rough concept, need variants? → idea-refine
21
+ ├── New project/feature/change? ──→ spec-driven-development
22
+ ├── Have a spec, need tasks? ──────→ planning-and-task-breakdown
23
+ ├── Implementing code? ────────────→ incremental-implementation
24
+ │ ├── UI work? ─────────────────→ frontend-ui-engineering
25
+ │ ├── API work? ────────────────→ api-and-interface-design
26
+ │ ├── Need better context? ─────→ context-engineering
27
+ │ ├── Need doc-verified code? ───→ source-driven-development
28
+ │ └── Stakes high / unfamiliar code? ──→ doubt-driven-development
29
+ ├── Writing/running tests? ────────→ test-driven-development
30
+ │ └── Browser-based? ───────────→ browser-testing-with-devtools
31
+ ├── Something broke? ──────────────→ debugging-and-error-recovery
32
+ ├── Reviewing code? ───────────────→ code-review-and-quality
33
+ │ ├── Too complex? ─────────────→ code-simplification
34
+ │ ├── Security concerns? ───────→ security-and-hardening
35
+ │ └── Performance concerns? ────→ performance-optimization
36
+ ├── Committing/branching? ─────────→ git-workflow-and-versioning
37
+ ├── CI/CD pipeline work? ──────────→ ci-cd-and-automation
38
+ ├── Deprecating/migrating? ────────→ deprecation-and-migration
39
+ ├── Writing docs/ADRs? ───────────→ documentation-and-adrs
40
+ ├── Adding logs/metrics/alerts? ───→ observability-and-instrumentation
41
+ └── Deploying/launching? ─────────→ shipping-and-launch
42
+ ```
43
+
44
+ ## Core Operating Behaviors
45
+
46
+ These behaviors apply at all times, across all skills. They are non-negotiable.
47
+
48
+ ### 1. Surface Assumptions
49
+
50
+ Before implementing anything non-trivial, explicitly state your assumptions:
51
+
52
+ ```
53
+ ASSUMPTIONS I'M MAKING:
54
+ 1. [assumption about requirements]
55
+ 2. [assumption about architecture]
56
+ 3. [assumption about scope]
57
+ → Correct me now or I'll proceed with these.
58
+ ```
59
+
60
+ Don't silently fill in ambiguous requirements. The most common failure mode is making wrong assumptions and running with them unchecked. Surface uncertainty early — it's cheaper than rework.
61
+
62
+ ### 2. Manage Confusion Actively
63
+
64
+ When you encounter inconsistencies, conflicting requirements, or unclear specifications:
65
+
66
+ 1. **STOP.** Do not proceed with a guess.
67
+ 2. Name the specific confusion.
68
+ 3. Present the tradeoff or ask the clarifying question.
69
+ 4. Wait for resolution before continuing.
70
+
71
+ **Bad:** Silently picking one interpretation and hoping it's right.
72
+ **Good:** "I see X in the spec but Y in the existing code. Which takes precedence?"
73
+
74
+ ### 3. Push Back When Warranted
75
+
76
+ You are not a yes-machine. When an approach has clear problems:
77
+
78
+ - Point out the issue directly
79
+ - Explain the concrete downside (quantify when possible — "this adds ~200ms latency" not "this might be slower")
80
+ - Propose an alternative
81
+ - Accept the human's decision if they override with full information
82
+
83
+ Sycophancy is a failure mode. "Of course!" followed by implementing a bad idea helps no one. Honest technical disagreement is more valuable than false agreement.
84
+
85
+ ### 4. Enforce Simplicity
86
+
87
+ Your natural tendency is to overcomplicate. Actively resist it.
88
+
89
+ Before finishing any implementation, ask:
90
+ - Can this be done in fewer lines?
91
+ - Are these abstractions earning their complexity?
92
+ - Would a staff engineer look at this and say "why didn't you just..."?
93
+
94
+ If you build 1000 lines and 100 would suffice, you have failed. Prefer the boring, obvious solution. Cleverness is expensive.
95
+
96
+ ### 5. Maintain Scope Discipline
97
+
98
+ Touch only what you're asked to touch.
99
+
100
+ Do NOT:
101
+ - Remove comments you don't understand
102
+ - "Clean up" code orthogonal to the task
103
+ - Refactor adjacent systems as a side effect
104
+ - Delete code that seems unused without explicit approval
105
+ - Add features not in the spec because they "seem useful"
106
+
107
+ Your job is surgical precision, not unsolicited renovation.
108
+
109
+ ### 6. Verify, Don't Assume
110
+
111
+ Every skill includes a verification step. A task is not complete until verification passes. "Seems right" is never sufficient — there must be evidence (passing tests, build output, runtime data).
112
+
113
+ Per-skill verification is the local check. The project-wide bar that applies to *every* change, regardless of which skill is active, is the Definition of Done: tests pass, no regressions, behavior verified at runtime, docs updated. See `references/definition-of-done.md`. It complements each task's acceptance criteria rather than replacing them.
114
+
115
+ ## Failure Modes to Avoid
116
+
117
+ These are the subtle errors that look like productivity but create problems:
118
+
119
+ 1. Making wrong assumptions without checking
120
+ 2. Not managing your own confusion — plowing ahead when lost
121
+ 3. Not surfacing inconsistencies you notice
122
+ 4. Not presenting tradeoffs on non-obvious decisions
123
+ 5. Being sycophantic ("Of course!") to approaches with clear problems
124
+ 6. Overcomplicating code and APIs
125
+ 7. Modifying code or comments orthogonal to the task
126
+ 8. Removing things you don't fully understand
127
+ 9. Building without a spec because "it's obvious"
128
+ 10. Skipping verification because "it looks right"
129
+
130
+ ## Skill Rules
131
+
132
+ 1. **Check for an applicable skill before starting work.** Skills encode processes that prevent common mistakes.
133
+
134
+ 2. **Skills are workflows, not suggestions.** Follow the steps in order. Don't skip verification steps.
135
+
136
+ 3. **Multiple skills can apply.** A feature implementation might involve `idea-refine` → `spec-driven-development` → `planning-and-task-breakdown` → `incremental-implementation` → `test-driven-development` → `code-review-and-quality` → `code-simplification` → `shipping-and-launch` in sequence.
137
+
138
+ 4. **When in doubt, start with a spec.** If the task is non-trivial and there's no spec, begin with `spec-driven-development`.
139
+
140
+ ## Lifecycle Sequence
141
+
142
+ For a complete feature, the typical skill sequence is:
143
+
144
+ ```
145
+ 1. interview-me → Extract what the user actually wants
146
+ 2. idea-refine → Refine vague ideas
147
+ 3. spec-driven-development → Define what we're building
148
+ 4. planning-and-task-breakdown → Break into verifiable chunks
149
+ 5. context-engineering → Load the right context
150
+ 6. source-driven-development → Verify against official docs
151
+ 7. incremental-implementation → Build slice by slice
152
+ 8. observability-and-instrumentation → Instrument as you build (runs parallel with 7-9, not after)
153
+ 9. doubt-driven-development → Cross-examine non-trivial decisions in-flight
154
+ 10. test-driven-development → Prove each slice works
155
+ 11. code-review-and-quality → Review before merge
156
+ 12. code-simplification → Reduce unnecessary complexity while preserving behavior
157
+ 13. git-workflow-and-versioning → Clean commit history
158
+ 14. documentation-and-adrs → Document decisions
159
+ 15. deprecation-and-migration → Retire old systems and move users safely when needed
160
+ 16. shipping-and-launch → Deploy safely
161
+ ```
162
+
163
+ Not every task needs every skill. A bug fix might only need: `debugging-and-error-recovery` → `test-driven-development` → `code-review-and-quality`.
164
+
165
+ ## Quick Reference
166
+
167
+ | Phase | Skill | One-Line Summary |
168
+ |-------|-------|-----------------|
169
+ | Define | interview-me | Surface what the user actually wants before any plan, spec, or code exists |
170
+ | Define | idea-refine | Refine ideas through structured divergent and convergent thinking |
171
+ | Define | spec-driven-development | Requirements and acceptance criteria before code |
172
+ | Plan | planning-and-task-breakdown | Decompose into small, verifiable tasks |
173
+ | Build | incremental-implementation | Thin vertical slices, test each before expanding |
174
+ | Build | source-driven-development | Verify against official docs before implementing |
175
+ | Build | doubt-driven-development | Adversarial fresh-context review of every non-trivial decision |
176
+ | Build | context-engineering | Right context at the right time |
177
+ | Build | frontend-ui-engineering | Production-quality UI with accessibility |
178
+ | Build | api-and-interface-design | Stable interfaces with clear contracts |
179
+ | Verify | test-driven-development | Failing test first, then make it pass |
180
+ | Verify | browser-testing-with-devtools | Chrome DevTools MCP for runtime verification |
181
+ | Verify | debugging-and-error-recovery | Reproduce → localize → fix → guard |
182
+ | Review | code-review-and-quality | Five-axis review with quality gates |
183
+ | Review | code-simplification | Preserve behavior while reducing unnecessary complexity |
184
+ | Review | security-and-hardening | OWASP prevention, input validation, least privilege |
185
+ | Review | performance-optimization | Measure first, optimize only what matters |
186
+ | Ship | git-workflow-and-versioning | Atomic commits, clean history |
187
+ | Ship | ci-cd-and-automation | Automated quality gates on every change |
188
+ | Ship | deprecation-and-migration | Remove old systems and migrate users safely |
189
+ | Ship | documentation-and-adrs | Document the why, not just the what |
190
+ | Ship | observability-and-instrumentation | Structured logs, RED metrics, traces, symptom-based alerts |
191
+ | Ship | shipping-and-launch | Pre-launch checklist, monitoring, rollback plan |
package/CHANGELOG.md CHANGED
@@ -1,5 +1,12 @@
1
1
  # Agent Fleet changelog
2
2
 
3
+ ## 1.0.4
4
+
5
+ ### Patch Changes
6
+
7
+ - 7730d44: Add Compact/Verbose Fleet Detail logs with immediate event-driven refresh and a two-second recovery ticker. Local specialists, research helpers, and delegate children now expose wrapped assistant output, provider-emitted thinking, tool arguments, complete textual tool results, status, and duration. Per-run JSONL transcripts are owner-only, bounded in live memory, and redact common secret formats before persistence and display.
8
+ - 6885455: Make grilling of unspecified design forks mandatory during planning, spec writing, and implementation. Already-stated requirements in chat, prompts, PRDs, and rules are not re-asked; remaining multiple-valid-way, contradiction, and competing-code-pattern choices wait for an explicit decision.
9
+
3
10
  ## 1.0.3
4
11
 
5
12
  ### Patch Changes
package/agents/builder.md CHANGED
@@ -29,6 +29,7 @@ You are a builder agent. Implement the requested changes thoroughly. Write clean
29
29
  - If the task carries acceptance assertions (`A1`, `A2`, …) or a parity/touchpoint inventory, treat them as the definition of done and keep them verbatim — they come from the dispatcher; implement against every listed site, not just the exemplar one with fixtures.
30
30
  - When you report back, use the structured-return schema in `skills/orchestration-verification/SKILL.md` if it exists: list `assertions_proven` (each with named evidence — test name, command output, or file:line), `assertions_unproven`, and `assertions_failed`. Report what you could not prove honestly rather than declaring "done"; an unproven assertion is not done, and naming it lets the dispatcher gate on it. Never mark an assertion proven without naming its evidence.
31
31
  - If you lack information your own tools cannot answer, do not guess — pause per the research protocol with `NEEDS_RESEARCH: <one specific, self-contained question>` lines (nothing after them); you will be resumed in the same session with findings file paths to read.
32
+ - If implementation requires a choice not already settled in the task, plan, PRD, chat, prompt, or rules (multiple valid approaches, contradiction, competing code patterns), do not pick silently. Follow `skills/_internal/grilling.md` if it exists and pause with `ASK_USER: <question>` (one focused question, 2–4 options plus a recommended choice). Already-stated requirements are not re-asked. Do not continue the slice in the same turn as an `ASK_USER` request.
32
33
 
33
34
  ## Delegation pre-pass (when a `delegate` tool is available)
34
35
 
package/agents/planner.md CHANGED
@@ -68,4 +68,4 @@ of the Process below.
68
68
  - Resolve the plan directory from `.ai/agent-fleet-overrides.md` → `## planning-and-task-breakdown` → `plan-dir`; default `docs/plans/{area}`. Name the file per the `naming` key (default `PLAN-{prd-name}.md`; add the `-{phase}` suffix only when the plan is deliberately split across multiple files). Embed the task list in the plan as a `## Task List` section unless the override says `todo: separate`.
69
69
  - Write the plan file, then end your final response with `PLAN_FILE: <repo-relative path>` on its own line, so the result can be handed to an implementer.
70
70
  - If you lack information that your read-only tools cannot answer, do not guess — pause for research. End your turn with one or more lines of the form `NEEDS_RESEARCH: <one specific, self-contained question>` and nothing after them (mirror of the ASK_USER protocol). Your session pauses there; read-only research helpers are spawned for you and you are resumed **in the same session** with the paths of their findings files — read them and continue planning from where you left off. Do not produce a partial or speculative plan in the same turn as a `NEEDS_RESEARCH` request.
71
- - If the requirements themselves are ambiguous, do not invent answers — ask (via the ASK_USER protocol when available) rather than produce a speculative plan.
71
+ - Before writing tasks, follow `skills/_internal/grilling.md` if it exists. Do **not** re-ask points already explicit in chat, prompt, PRD, spec, or rules. For every remaining unspecified fork (multiple valid approaches, contradiction, competing code patterns), do not invent an answer — ask via `ASK_USER: <question>` (one focused question, 2–4 options plus a recommended choice) rather than produce a speculative plan. Do not write the plan file in the same turn as an `ASK_USER` request. If grilling finds no open forks, say so briefly and write the plan.
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "schemaVersion": 2,
3
- "packageVersion": "1.0.3",
3
+ "packageVersion": "1.0.4",
4
4
  "groups": [
5
5
  {
6
6
  "id": "skills",
@@ -2411,7 +2411,7 @@
2411
2411
  "group": "skills",
2412
2412
  "subcategory": "build",
2413
2413
  "title": "incremental-implementation",
2414
- "summary": "Delivers changes incrementally.",
2414
+ "summary": "Delivers changes incrementally and grills unspecified forks instead of silently picking among them.",
2415
2415
  "recommended": true,
2416
2416
  "stability": "stable",
2417
2417
  "consent": "file",
@@ -2567,7 +2567,7 @@
2567
2567
  "group": "skills",
2568
2568
  "subcategory": "plan",
2569
2569
  "title": "planning-and-task-breakdown",
2570
- "summary": "Breaks work into ordered tasks.",
2570
+ "summary": "Breaks work into ordered tasks and grills unspecified design forks before writing them.",
2571
2571
  "recommended": true,
2572
2572
  "stability": "stable",
2573
2573
  "consent": "file",
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@chankov/agent-fleet",
3
- "version": "1.0.3",
3
+ "version": "1.0.4",
4
4
  "description": "Multi-agent fleet orchestration for coding agents. Pi as the primary runtime, Herdr as the workspace control plane, coms as the peer data plane, and Hermes for remote control — plus skills, personas, harnesses, and a guided setup CLI.",
5
5
  "keywords": [
6
6
  "ai",
@@ -104,7 +104,7 @@
104
104
  "access": "public"
105
105
  },
106
106
  "scripts": {
107
- "test": "node bin/cli.js --version && node bin/cli.js --help && node --test \"bin/test/*.test.js\" scripts/agent-hub-helpers.test.mjs scripts/agent-hub-spawn.test.mjs scripts/agent-hub-delegate.test.mjs scripts/agent-hub-research.test.mjs .pi/harnesses/lib/herdr-client.test.ts .pi/harnesses/lib/herdr-presence.test.ts .pi/harnesses/lib/coms-registry-entry.test.ts .pi/harnesses/lib/fleet-overlay.test.ts .pi/harnesses/lib/fleet-selection.test.ts .pi/harnesses/lib/fleet-panel.test.ts .pi/harnesses/lib/context-budget.test.ts .pi/harnesses/lib/context-budget-view.test.ts .pi/harnesses/lib/context-budget-hub-prompt.test.ts .pi/harnesses/lib/context-budget-child-prompt.test.ts .pi/harnesses/agent-hub/context-budget-snapshot.test.ts .pi/harnesses/agent-hub/context-budget.integration.test.ts .pi/harnesses/agent-hub/context-pressure.test.ts .pi/harnesses/agent-hub/capability-packs.test.ts .pi/harnesses/agent-hub/capability-confirmation.test.ts .pi/harnesses/agent-hub/capability-matrix.test.ts .pi/harnesses/lib/fleet-read-model.test.ts .pi/harnesses/lib/fleet-dashboard-view.test.ts .pi/harnesses/lib/fleet-dashboard-ops.test.ts .pi/harnesses/lib/fleet-detail-view.test.ts .pi/harnesses/agent-hub/fleet-dashboard.integration.test.ts scripts/coms-cli.test.ts scripts/lib/codex-conductor.test.ts scripts/lib/codex-remote-control.test.ts scripts/lib/fleet-command.test.ts scripts/lib/team-project.test.ts scripts/lib/herdr-layout.test.ts scripts/lib/peer-launch.test.ts scripts/lib/spawn-stagger.test.ts scripts/lib/monitor-env.test.ts scripts/lib/fleet-extras.test.ts scripts/lib/team-snapshot.test.ts scripts/team-snapshot.command.test.ts scripts/lib/coms-envelope.test.ts scripts/lib/claude-bridge-core.test.ts scripts/lib/hermes-bridge-core.test.ts scripts/coms-hermes-bridge.test.ts .pi/harnesses/ask-user-remote/race-core.test.js .pi/harnesses/ask-user-remote/index.test.ts .pi/harnesses/agent-hub/extension-loader.test.ts .pi/extensions/btw/state.test.js .pi/extensions/btw/index.test.ts .pi/harnesses/agent-hub/execution-profile.test.ts .pi/harnesses/agent-hub/footer.test.ts .pi/harnesses/agent-hub/view-default.test.ts .pi/harnesses/agent-hub/overlay-migration.test.ts .pi/harnesses/agent-hub/safety-routing.test.ts .pi/harnesses/agent-hub/approval-routing.integration.test.ts .pi/harnesses/agent-hub/run-budget.test.js .pi/harnesses/agent-hub/budget-continuation.test.ts .pi/harnesses/agent-hub/budget-continuation.integration.test.ts .pi/harnesses/agent-hub/hub-state-audit.test.js .pi/harnesses/agent-hub/docs-lane.test.js .pi/harnesses/agent-hub/external-blocker.test.js .pi/harnesses/agent-hub/run-namespace.test.js .pi/harnesses/agent-hub/review-findings.test.js .pi/harnesses/agent-hub/assertion-ledger.test.js .pi/harnesses/agent-hub/provider-semaphore.test.js .pi/harnesses/lib/spawned-peers.test.js .pi/harnesses/agent-hub/context-window.test.js .pi/harnesses/agent-hub/drift-watchdog.test.js .pi/harnesses/agent-hub/session-health.test.js .pi/harnesses/agent-hub/return-contract.test.js .pi/harnesses/agent-hub/return-extract.test.js .pi/harnesses/agent-hub/backend-policy.test.js .pi/harnesses/agent-hub/artifacts.test.js .pi/harnesses/agent-hub/scope-gate.test.js .pi/harnesses/agent-hub/evidence-rules.test.js .pi/harnesses/agent-hub/research-retention.test.js .pi/harnesses/lib/damage-control-shared.test.ts .pi/harnesses/damage-control-continue/herdr-rules.test.js .pi/harnesses/damage-control-continue/exemptions.test.js scripts/lib/hermes-monitor-model.test.ts scripts/lib/hermes-monitor-events.test.ts scripts/lib/hermes-monitor-store.test.ts scripts/lib/hermes-monitor-retention.integration.test.ts scripts/lib/hermes-monitor-registry.test.ts scripts/lib/hermes-monitor-socket.test.ts scripts/lib/hermes-monitor-data-path.test.ts scripts/lib/hermes-monitor-slice7-9-backend.test.ts scripts/lib/hermes-monitor-control-socket.test.ts scripts/lib/hermes-monitor-e2e.test.ts scripts/lib/hermes-monitor-plugin-handshake.test.ts scripts/hermes-monitor-capability-runner.test.ts scripts/hermes-monitor-scenario.test.ts scripts/hermes-watchdog-capability-probe.test.ts .pi/harnesses/agent-hub/monitor-invoke.test.ts .pi/harnesses/agent-hub/monitor-invoke-journal.test.ts .pi/harnesses/agent-hub/monitor-control.test.ts .pi/harnesses/agent-hub/monitor-live-bridge-gaps.test.ts .pi/harnesses/agent-hub/monitor-review-live-wiring.red.test.ts .pi/harnesses/agent-hub/monitor-runtime.test.ts .pi/harnesses/agent-hub/monitor-bridge-runtime.test.ts .pi/harnesses/agent-hub/monitor-reconcile.test.ts .pi/harnesses/agent-hub/monitor-recovery.test.ts .pi/harnesses/agent-hub/monitor-lifecycle-lease.test.ts .pi/harnesses/agent-hub/monitor-session-bridge-race.test.ts .pi/harnesses/agent-hub/monitor-session-bridge.test.ts .pi/harnesses/agent-hub/monitor-cancel-race.test.ts .pi/harnesses/agent-hub/monitor-wait-only.test.ts .pi/harnesses/agent-hub/monitor-publisher.test.ts .pi/harnesses/agent-hub/monitor-index.integration.test.ts hermes/desktop-plugins/agent-fleet-herdr/presentation.test.js scripts/docs-links.test.mjs && npm run test:watchdog-py",
107
+ "test": "node bin/cli.js --version && node bin/cli.js --help && node --test \"bin/test/*.test.js\" scripts/agent-hub-helpers.test.mjs scripts/agent-hub-spawn.test.mjs scripts/agent-hub-delegate.test.mjs scripts/agent-hub-research.test.mjs .pi/harnesses/lib/herdr-client.test.ts .pi/harnesses/lib/herdr-presence.test.ts .pi/harnesses/lib/coms-registry-entry.test.ts .pi/harnesses/lib/fleet-overlay.test.ts .pi/harnesses/lib/fleet-selection.test.ts .pi/harnesses/lib/fleet-panel.test.ts .pi/harnesses/lib/context-budget.test.ts .pi/harnesses/lib/context-budget-view.test.ts .pi/harnesses/lib/context-budget-hub-prompt.test.ts .pi/harnesses/lib/context-budget-child-prompt.test.ts .pi/harnesses/agent-hub/context-budget-snapshot.test.ts .pi/harnesses/agent-hub/context-budget.integration.test.ts .pi/harnesses/agent-hub/context-pressure.test.ts .pi/harnesses/agent-hub/capability-packs.test.ts .pi/harnesses/agent-hub/capability-confirmation.test.ts .pi/harnesses/agent-hub/capability-matrix.test.ts .pi/harnesses/lib/fleet-read-model.test.ts .pi/harnesses/lib/fleet-dashboard-view.test.ts .pi/harnesses/lib/fleet-dashboard-ops.test.ts .pi/harnesses/lib/fleet-detail-view.test.ts .pi/harnesses/lib/fleet-transcript-store.test.ts .pi/harnesses/agent-hub/fleet-dashboard.integration.test.ts scripts/coms-cli.test.ts scripts/lib/codex-conductor.test.ts scripts/lib/codex-remote-control.test.ts scripts/lib/fleet-command.test.ts scripts/lib/team-project.test.ts scripts/lib/herdr-layout.test.ts scripts/lib/peer-launch.test.ts scripts/lib/spawn-stagger.test.ts scripts/lib/monitor-env.test.ts scripts/lib/fleet-extras.test.ts scripts/lib/team-snapshot.test.ts scripts/team-snapshot.command.test.ts scripts/lib/coms-envelope.test.ts scripts/lib/claude-bridge-core.test.ts scripts/lib/hermes-bridge-core.test.ts scripts/coms-hermes-bridge.test.ts .pi/harnesses/ask-user-remote/race-core.test.js .pi/harnesses/ask-user-remote/index.test.ts .pi/harnesses/agent-hub/extension-loader.test.ts .pi/extensions/btw/state.test.js .pi/extensions/btw/index.test.ts .pi/harnesses/agent-hub/execution-profile.test.ts .pi/harnesses/agent-hub/footer.test.ts .pi/harnesses/agent-hub/view-default.test.ts .pi/harnesses/agent-hub/overlay-migration.test.ts .pi/harnesses/agent-hub/safety-routing.test.ts .pi/harnesses/agent-hub/approval-routing.integration.test.ts .pi/harnesses/agent-hub/run-budget.test.js .pi/harnesses/agent-hub/budget-continuation.test.ts .pi/harnesses/agent-hub/budget-continuation.integration.test.ts .pi/harnesses/agent-hub/hub-state-audit.test.js .pi/harnesses/agent-hub/docs-lane.test.js .pi/harnesses/agent-hub/external-blocker.test.js .pi/harnesses/agent-hub/run-namespace.test.js .pi/harnesses/agent-hub/review-findings.test.js .pi/harnesses/agent-hub/assertion-ledger.test.js .pi/harnesses/agent-hub/provider-semaphore.test.js .pi/harnesses/lib/spawned-peers.test.js .pi/harnesses/agent-hub/context-window.test.js .pi/harnesses/agent-hub/drift-watchdog.test.js .pi/harnesses/agent-hub/session-health.test.js .pi/harnesses/agent-hub/return-contract.test.js .pi/harnesses/agent-hub/return-extract.test.js .pi/harnesses/agent-hub/backend-policy.test.js .pi/harnesses/agent-hub/artifacts.test.js .pi/harnesses/agent-hub/scope-gate.test.js .pi/harnesses/agent-hub/evidence-rules.test.js .pi/harnesses/agent-hub/research-retention.test.js .pi/harnesses/lib/damage-control-shared.test.ts .pi/harnesses/damage-control-continue/herdr-rules.test.js .pi/harnesses/damage-control-continue/exemptions.test.js scripts/lib/hermes-monitor-model.test.ts scripts/lib/hermes-monitor-events.test.ts scripts/lib/hermes-monitor-store.test.ts scripts/lib/hermes-monitor-retention.integration.test.ts scripts/lib/hermes-monitor-registry.test.ts scripts/lib/hermes-monitor-socket.test.ts scripts/lib/hermes-monitor-data-path.test.ts scripts/lib/hermes-monitor-slice7-9-backend.test.ts scripts/lib/hermes-monitor-control-socket.test.ts scripts/lib/hermes-monitor-e2e.test.ts scripts/lib/hermes-monitor-plugin-handshake.test.ts scripts/hermes-monitor-capability-runner.test.ts scripts/hermes-monitor-scenario.test.ts scripts/hermes-watchdog-capability-probe.test.ts .pi/harnesses/agent-hub/monitor-invoke.test.ts .pi/harnesses/agent-hub/monitor-invoke-journal.test.ts .pi/harnesses/agent-hub/monitor-control.test.ts .pi/harnesses/agent-hub/monitor-live-bridge-gaps.test.ts .pi/harnesses/agent-hub/monitor-review-live-wiring.red.test.ts .pi/harnesses/agent-hub/monitor-runtime.test.ts .pi/harnesses/agent-hub/monitor-bridge-runtime.test.ts .pi/harnesses/agent-hub/monitor-reconcile.test.ts .pi/harnesses/agent-hub/monitor-recovery.test.ts .pi/harnesses/agent-hub/monitor-lifecycle-lease.test.ts .pi/harnesses/agent-hub/monitor-session-bridge-race.test.ts .pi/harnesses/agent-hub/monitor-session-bridge.test.ts .pi/harnesses/agent-hub/monitor-cancel-race.test.ts .pi/harnesses/agent-hub/monitor-wait-only.test.ts .pi/harnesses/agent-hub/monitor-publisher.test.ts .pi/harnesses/agent-hub/monitor-index.integration.test.ts hermes/desktop-plugins/agent-fleet-herdr/presentation.test.js scripts/docs-links.test.mjs && npm run test:watchdog-py",
108
108
  "test:watchdog-py": "PYTHONDONTWRITEBYTECODE=1 python3 -m unittest discover -s hermes/watchdog-tests -p 'test_*.py'",
109
109
  "pack:dry": "npm pack --dry-run",
110
110
  "changeset": "changeset",
@@ -1,11 +1,59 @@
1
1
  # Grilling (Internal Helper)
2
2
 
3
- Use this helper from a parent skill when the user asks to grill or stress-test a plan, spec, or design, or when an important design choice is being silently assumed.
3
+ Use this helper from a parent skill whenever a plan, spec, design, or
4
+ implementation must take a decision. Explicit invocation ("grill this",
5
+ "stress-test this") still triggers it; so does any unspecified fork. Do not
6
+ wait for the user to ask.
4
7
 
5
- Interview the user relentlessly until the important decisions are explicitly accepted, rejected, or deferred. Walk the design tree one dependency at a time: choose the next question based on prior answers, and skip questions made irrelevant by earlier decisions.
8
+ Interview until each **open** decision is explicitly accepted, rejected, or
9
+ deferred. Walk the design tree one dependency at a time: choose the next
10
+ question from prior answers, and skip questions made irrelevant by earlier
11
+ decisions.
6
12
 
7
- Ask one focused question at a time. Offer 2-4 concrete options plus your recommended answer and a brief reason, then wait for the user's decision before continuing. This should feel like guided architectural interrogation, not a questionnaire dump.
13
+ ## Do not re-ask what is already settled
8
14
 
9
- If a question can be answered by reading the codebase, docs, tests, or runtime evidence, investigate first and ask only about the remaining decision.
15
+ Do **not** grill a point that is already explicit in any of:
10
16
 
11
- Keep grilling until shared understanding is strong enough to write or revise the downstream artifact. When review exposes gaps later, convert each gap into one targeted follow-up question.
17
+ - the current chat, user prompt, or spoken/written instruction
18
+ - a PRD, spec, plan, ticket, or other written requirement
19
+ - a project rule, skill, or standing instruction
20
+
21
+ Treat those as accepted. Re-asking wastes attention and implies the agent did
22
+ not read the source of truth.
23
+
24
+ ## Must grill — unspecified forks
25
+
26
+ Grill every remaining point that is load-bearing and still open:
27
+
28
+ - **Multiple valid ways** — architecture, library, naming, scope cut, data
29
+ model, error behavior, where two or more approaches would all work and the
30
+ trade-off is preference-dependent
31
+ - **Doubt or contradiction** — sources disagree (chat vs code, spec vs tests,
32
+ two rules, two existing implementations)
33
+ - **Code variants** — the codebase already has several patterns and one must
34
+ be chosen for this change; propose one recommended option among them
35
+
36
+ If a question can be answered by reading the codebase, docs, tests, or runtime
37
+ evidence, investigate first and ask only about the remaining decision.
38
+
39
+ If grilling produces **zero** questions (everything load-bearing was already
40
+ settled), say so briefly and proceed. Do not invent questions to look thorough.
41
+
42
+ ## How to ask
43
+
44
+ Ask one focused question at a time. Offer 2-4 concrete options plus your
45
+ recommended answer and a brief reason, then wait for the user's decision
46
+ before continuing. This should feel like guided architectural interrogation,
47
+ not a questionnaire dump.
48
+
49
+ ## When it applies
50
+
51
+ Planning, spec writing, **and implementation** — whenever a decision must be
52
+ taken. A plan that silently picks a library, and an implementer that silently
53
+ picks among existing code patterns, are the same failure.
54
+
55
+ Keep grilling until shared understanding is strong enough to write or revise
56
+ the downstream artifact. Record each accepted, rejected, or deferred choice in
57
+ that artifact (Architecture Decisions, Boundaries, or the slice summary).
58
+ When review exposes gaps later, convert each gap into one targeted follow-up
59
+ question.
@@ -88,7 +88,7 @@ Read `frameworks.md` in this skill directory for additional ideation frameworks
88
88
 
89
89
  After the user reacts to Phase 1 (indicates which ideas resonate, pushes back, adds context), shift to convergent mode.
90
90
 
91
- **Grilling mode:** If the user asks to "grill" or stress-test a specific plan/design, read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md) and use that one-question-at-a-time decision interview before producing the one-pager. Treat the answers as inputs to Key Assumptions, MVP Scope, Not Doing, and Open Questions.
91
+ **Grilling:** When converging on a direction — and whenever the user asks to "grill" or stress-test a plan/design — read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md). Skip points already explicit in chat, prompt, PRD, or rules. Grill remaining unspecified forks one question at a time, with a recommended option, before producing the one-pager. Treat the answers as inputs to Key Assumptions, MVP Scope, Not Doing, and Open Questions.
92
92
 
93
93
  1. **Cluster** the ideas that resonated into 2-3 distinct directions. Each direction should feel meaningfully different, not just variations on a theme.
94
94
 
@@ -176,7 +176,7 @@ After completing an ideation session:
176
176
  - [ ] The target user and success criteria are defined
177
177
  - [ ] Multiple directions were explored, not just the first idea
178
178
  - [ ] Hidden assumptions are explicitly listed with validation strategies
179
- - [ ] If grilling was invoked, decisions were resolved one at a time and reflected in the one-pager
179
+ - [ ] Unspecified forks were grilled one at a time (or grilling found none); already-stated points were not re-asked; decisions are reflected in the one-pager
180
180
  - [ ] A "Not Doing" list makes trade-offs explicit
181
181
  - [ ] The output is a concrete artifact (markdown one-pager), not just conversation
182
182
  - [ ] The user confirmed the final direction before any implementation work
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: incremental-implementation
3
- description: Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
3
+ description: Delivers changes incrementally and grills unspecified forks instead of silently picking among them. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
4
4
  ---
5
5
 
6
6
  # Incremental Implementation
@@ -160,6 +160,12 @@ NOTICED BUT NOT TOUCHING:
160
160
  → Want me to create tasks for these?
161
161
  ```
162
162
 
163
+ ### Rule 0.6: Grill unspecified forks; do not re-ask settled ones
164
+
165
+ A plan does not freeze every decision. Before (and during) a slice, if a load-bearing choice is **not** already explicit in the task, plan, PRD, chat, prompt, or rules — multiple valid approaches, a contradiction, or several existing code patterns — read [`../_internal/grilling.md`](../_internal/grilling.md) and ask one question at a time, with a recommended option. Wait. Do not pick silently and do not re-confirm what those sources already stated.
166
+
167
+ If grilling produces zero questions, proceed with the slice.
168
+
163
169
  ### Rule 1: One Thing at a Time
164
170
 
165
171
  Each increment changes one logical thing. Don't mix concerns:
@@ -238,6 +244,7 @@ After each increment, verify:
238
244
  - [ ] Type checking passes (`npx tsc --noEmit`)
239
245
  - [ ] Linting passes (`npm run lint`)
240
246
  - [ ] The new functionality works as expected
247
+ - [ ] Unspecified load-bearing forks were grilled (or grilling found none); already-stated requirements were not re-asked
241
248
  - [ ] The Standard Slice Summary was presented to the user
242
249
  - [ ] Explicit user approval was received before starting the next slice
243
250
  - [ ] The agent did not run `git add`, `git commit`, `git reset`, or `git restore` during this slice (whatever the user staged or committed between slices is preserved as-is)
@@ -255,6 +262,8 @@ After each increment, verify:
255
262
  | "This refactor is small enough to include" | Refactors mixed with features make both harder to review and debug. Separate them. |
256
263
  | "I'll just stage it to make their life easier" | Don't. The user explicitly controls staging and commits. Do not run any git state-changing command — and do not "tidy up" by unstaging or resetting what the user staged between slices. |
257
264
  | "They didn't answer but it's obviously fine, I'll continue" | No. Silence is not approval. Wait for an explicit response before starting the next slice. |
265
+ | "The plan didn't specify which existing pattern to follow, I'll just pick one" | That is an unspecified fork. Grill it. The programmer needs to know which variant was chosen and why. |
266
+ | "I'll re-confirm the PRD acceptance criteria before coding" | Already-stated requirements are not re-asked. Grill only what is still open. |
258
267
  | "Let me run the build command again just to be sure" | After a successful run, repeating the same command adds nothing unless the code has changed since. Run it again after subsequent edits, not as reassurance. |
259
268
 
260
269
  ## Red Flags
@@ -268,6 +277,8 @@ After each increment, verify:
268
277
  - Staging or committing changes on the user's behalf
269
278
  - Unstaging, resetting, restoring, or stashing changes the user staged or committed between slices ("enforcing" an unstaged working tree is not the agent's job)
270
279
  - Building abstractions before the third use case demands it
280
+ - Silently picking among several valid approaches or existing code patterns
281
+ - Re-asking a requirement already explicit in the task, plan, PRD, chat, or rules
271
282
  - Touching files outside the task scope "while I'm here"
272
283
  - Creating new utility files for one-time operations
273
284
  - Running the same build/test command twice in a row without any intervening code change
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: planning-and-task-breakdown
3
- description: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, when parallel work is possible, or when the user wants to grill a plan before implementation.
3
+ description: Breaks work into ordered tasks and grills unspecified design forks before writing them. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, when parallel work is possible, or when more than one valid approach exists and the plan must lock a choice.
4
4
  ---
5
5
 
6
6
  # Planning and Task Breakdown
@@ -16,9 +16,9 @@ Decompose work into small, verifiable tasks with explicit acceptance criteria. G
16
16
  - Work needs to be parallelized across multiple agents or sessions
17
17
  - You need to communicate scope to a human
18
18
  - The implementation order isn't obvious
19
- - The user asks to grill or stress-test a draft plan before implementation
19
+ - More than one valid approach, a contradiction, or competing code patterns must be locked before tasks are written
20
20
 
21
- **When NOT to use:** Single-file changes with obvious scope, or when the spec already contains well-defined tasks.
21
+ **When NOT to use:** Single-file changes with obvious scope, or when the spec already contains well-defined tasks. Skipping a plan file does **not** skip grilling: if the change can be done several ways and none is mandated, ask before coding.
22
22
 
23
23
  ## Proportionality gate (check before writing anything)
24
24
 
@@ -37,6 +37,7 @@ Rules that follow from this:
37
37
  - **Plan the ask, not the neighbourhood.** Adjacent problems you notice go in a short "Out of scope / noticed" list at the end for the human to decide on. They do not become tasks.
38
38
  - **Split by phase when the phases have different owners.** Repository work, cloud/infrastructure preparation, deployment, and retirement belong in separate plans: bundling them means the whole plan is blocked on whichever phase stalls, and every review re-reads all of it.
39
39
  - **Review findings do not silently enlarge the plan.** When a plan revision adds requirements nobody asked for, say so explicitly and let the human accept or drop them.
40
+ - **Unspecified forks still get grilled.** Skipping a plan file does not skip a load-bearing choice. Already-stated requirements (chat, prompt, PRD, rules) are not re-asked.
40
41
 
41
42
  ## Output Location
42
43
 
@@ -65,7 +66,7 @@ Before writing any code, operate in read-only mode:
65
66
 
66
67
  **Do NOT write code during planning.** The output is a plan document, not implementation.
67
68
 
68
- **Grilling mode:** If the user asks to grill/stress-test the plan, or Step 1 reveals a load-bearing assumption, read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md) before writing tasks. Resolve decisions one at a time; update Architecture Decisions, Risks, and Open Questions with accepted, rejected, or deferred choices.
69
+ **Grilling (required before writing tasks):** Read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md). Inventory load-bearing decisions. Skip anything already explicit in chat, prompt, PRD, spec, or rules. Grill every remaining fork (multiple valid ways, contradiction, competing code patterns) one question at a time, with a recommended option. Do not write tasks while a load-bearing choice is still silently assumed. Update Architecture Decisions, Risks, and Open Questions with accepted, rejected, or deferred choices. If nothing is open, note that grilling found no unspecified forks and continue.
69
70
 
70
71
  ### Step 2: Identify the Dependency Graph
71
72
 
@@ -226,6 +227,9 @@ When multiple agents or sessions are available:
226
227
  | "The tasks are obvious" | Write them down anyway. Explicit tasks surface hidden dependencies and forgotten edge cases. |
227
228
  | "Planning is overhead" | Planning is the task. Implementation without a plan is just typing. |
228
229
  | "I can hold it all in my head" | Context windows are finite. Written plans survive session boundaries and compaction. |
230
+ | "The PRD already covers everything, no need to grill" | Then grilling produces zero questions. Still run the inventory so silent forks do not slip through. |
231
+ | "I'll pick the obvious variant and note it in Architecture Decisions" | If more than one variant exists and none was mandated, it is not obvious to the programmer who was not in the room. Ask, then record the choice. |
232
+ | "Re-confirming the PRD points shows thoroughness" | Re-asking settled requirements wastes the user and implies the agent did not read them. Skip them. |
229
233
 
230
234
  ## Red Flags
231
235
 
@@ -235,6 +239,9 @@ When multiple agents or sessions are available:
235
239
  - All tasks touches more than 8+ files
236
240
  - No checkpoints between tasks
237
241
  - Dependency order isn't considered
242
+ - Writing tasks that silently pick a library, pattern, or behavior not mandated in chat/PRD/rules
243
+ - Re-asking a requirement already explicit in chat, prompt, PRD, spec, or rules
244
+ - Leaving an unspecified fork as an Open Question without asking
238
245
 
239
246
  ## Verification
240
247
 
@@ -246,7 +253,9 @@ Before starting implementation, confirm:
246
253
  - [ ] No task touches more than ~5 files
247
254
  - [ ] Checkpoints exist between major phases
248
255
  - [ ] The human has reviewed and approved the plan
249
- - [ ] If grilling was invoked, each load-bearing decision has an accepted/rejected/deferred status in the plan
256
+ - [ ] Grilling ran before tasks were written (inventory of load-bearing decisions)
257
+ - [ ] Already-stated requirements (chat, prompt, PRD, spec, rules) were not re-asked
258
+ - [ ] Each remaining load-bearing decision has an accepted/rejected/deferred status in the plan
250
259
  - [ ] No open questions left (All are resolved/answered/commented)
251
260
 
252
261
  ## See Also
@@ -69,18 +69,13 @@ Writing a spec without reading what already exists leads to duplication, contrad
69
69
 
70
70
  Then start with a high-level vision. Ask the human clarifying questions until requirements are concrete.
71
71
 
72
- **Grilling mode:** If the user asks to grill a concept/spec, or a requirement depends on unconfirmed design choices, read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md) before locking the spec. Resolve decisions one at a time; fold each answer into Success Criteria, Boundaries, Proposed decisions, or Open Questions.
72
+ **Grilling (required before locking the spec):** Read the shared internal helper at [`../_internal/grilling.md`](../_internal/grilling.md). Skip anything already explicit in chat, prompt, PRD, or rules — do not re-confirm it. Grill every remaining unconfirmed design choice (multiple valid ways, contradiction, competing code patterns) one question at a time, with a recommended option. Fold each answer into Success Criteria, Boundaries, Proposed decisions, or Open Questions. If nothing is open, note that grilling found no unspecified forks and continue.
73
73
 
74
- **Surface assumptions immediately.** Before writing any spec content, list what you're assuming:
74
+ **Surface assumptions immediately.** Before writing any spec content, classify what you would otherwise assume:
75
75
 
76
- ```
77
- ASSUMPTIONS I'M MAKING:
78
- 1. This is a web application (not native mobile)
79
- 2. Authentication uses session-based cookies (not JWT)
80
- 3. The database is PostgreSQL (based on existing Prisma schema)
81
- 4. We're targeting modern browsers only (no IE11)
82
- → Correct me now or I'll proceed with these.
83
- ```
76
+ - Already explicit in chat, prompt, or rules → do not re-ask.
77
+ - Confirmed in code, tests, or trusted docs (e.g. PostgreSQL because the Prisma schema is already Postgres) → do not re-ask; mark Confirmed.
78
+ - Load-bearing and still open (native vs web, cookies vs JWT when neither is mandated) → grill per the helper above and **wait**. Do not dump a list and proceed unless corrected.
84
79
 
85
80
  Don't silently fill in ambiguous requirements. The spec's entire purpose is to surface misunderstandings *before* code gets written — assumptions are the most dangerous form of misunderstanding.
86
81
 
@@ -244,6 +239,8 @@ The spec is a living document, not a one-time artifact:
244
239
  - Implementing features not mentioned in any spec or task list
245
240
  - Making architectural decisions without documenting them
246
241
  - Skipping the spec because "it's obvious what to build"
242
+ - Re-asking a requirement already explicit in chat, prompt, or rules
243
+ - Locking a spec that silently picks among several valid approaches
247
244
 
248
245
  ## Verification
249
246
 
@@ -251,7 +248,9 @@ Before proceeding to implementation, confirm:
251
248
 
252
249
  - [ ] The spec covers all six core areas
253
250
  - [ ] The human has reviewed and approved the spec
254
- - [ ] If grilling was invoked, each load-bearing decision is recorded as accepted, rejected, or deferred
251
+ - [ ] Grilling ran before the spec was locked (inventory of load-bearing decisions)
252
+ - [ ] Already-stated requirements (chat, prompt, rules) were not re-asked
253
+ - [ ] Each remaining load-bearing decision is recorded as accepted, rejected, or deferred
255
254
  - [ ] Success criteria are specific and testable
256
255
  - [ ] Boundaries (Always/Ask First/Never) are defined
257
256
  - [ ] The spec is saved to its output location (see Output Location)
@@ -49,17 +49,13 @@ Task arrives
49
49
 
50
50
  These behaviors apply at all times, across all skills. They are non-negotiable.
51
51
 
52
- ### 1. Surface Assumptions
52
+ ### 1. Surface Assumptions — grill unspecified forks
53
53
 
54
- Before implementing anything non-trivial, explicitly state your assumptions:
54
+ Whenever a decision must be taken — planning **or** implementation — follow [`../_internal/grilling.md`](../_internal/grilling.md):
55
55
 
56
- ```
57
- ASSUMPTIONS I'M MAKING:
58
- 1. [assumption about requirements]
59
- 2. [assumption about architecture]
60
- 3. [assumption about scope]
61
- → Correct me now or I'll proceed with these.
62
- ```
56
+ - **Already stated** in chat, prompt, PRD, spec, plan, or rules → do not re-ask. Treat as accepted.
57
+ - **Unspecified and load-bearing** (multiple valid ways, contradiction, competing code patterns) → grill one question at a time, with a recommended option, and **wait**. Do not "proceed unless corrected."
58
+ - **Non-load-bearing working detail** (which test file to open first) → state it and continue unless redirected.
63
59
 
64
60
  Don't silently fill in ambiguous requirements. The most common failure mode is making wrong assumptions and running with them unchecked. Surface uncertainty early — it's cheaper than rework.
65
61
 
@@ -124,12 +120,14 @@ These are the subtle errors that look like productivity but create problems:
124
120
  2. Not managing your own confusion — plowing ahead when lost
125
121
  3. Not surfacing inconsistencies you notice
126
122
  4. Not presenting tradeoffs on non-obvious decisions
127
- 5. Being sycophantic ("Of course!") to approaches with clear problems
128
- 6. Overcomplicating code and APIs
129
- 7. Modifying code or comments orthogonal to the task
130
- 8. Removing things you don't fully understand
131
- 9. Building without a spec because "it's obvious"
132
- 10. Skipping verification because "it looks right"
123
+ 5. Re-asking a requirement that was already explicit in chat, PRD, or rules
124
+ 6. Silently picking among several valid approaches or existing code patterns
125
+ 7. Being sycophantic ("Of course!") to approaches with clear problems
126
+ 8. Overcomplicating code and APIs
127
+ 9. Modifying code or comments orthogonal to the task
128
+ 10. Removing things you don't fully understand
129
+ 11. Building without a spec because "it's obvious"
130
+ 12. Skipping verification because "it looks right"
133
131
 
134
132
  ## Skill Rules
135
133