@bonesofspring/ai-rules 0.2.18 → 0.2.20

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 (697) hide show
  1. package/CHANGELOG.md +59 -0
  2. package/README.md +5 -3
  3. package/bin/cli.js +111 -4
  4. package/package.json +6 -3
  5. package/presets/_shared/README.md +3 -3
  6. package/presets/_shared/assets/docs-specs/schemas/frontmatter-v1.schema.json +1 -1
  7. package/presets/_shared/core/agent-team/agent-artifact-contracts.md +38 -0
  8. package/presets/_shared/core/agent-team/agent-team-orchestrator.md +1 -0
  9. package/presets/_shared/core/agent-team/task-classification.md +21 -0
  10. package/presets/_shared/core/architecture/feature-delivery-workflow.md +2 -1
  11. package/presets/_shared/core/architecture/product-specs-authoring.md +6 -3
  12. package/presets/_shared/core/architecture/product-specs.md +8 -3
  13. package/presets/_shared/core/meta/preset-no-cross-stack-leakage.md +1 -0
  14. package/presets/_shared/core/quality/anti-sycophancy-discipline.md +1 -1
  15. package/presets/_shared/core/quality/code-quality-and-refactoring.md +1 -1
  16. package/presets/_shared/core/quality/debug-investigation.md +24 -0
  17. package/presets/_shared/core/quality/mcp-usage.md +84 -0
  18. package/presets/_shared/core/quality/verification-before-completion.md +25 -0
  19. package/presets/_shared/core/review/receiving-code-review.md +24 -0
  20. package/presets/claude/android-kotlin/MCP.md +20 -1
  21. package/presets/claude/android-kotlin/agents/accessibility-reviewer.md +6 -0
  22. package/presets/claude/android-kotlin/agents/build-verifier.md +6 -0
  23. package/presets/claude/android-kotlin/agents/ci-investigator.md +9 -0
  24. package/presets/claude/android-kotlin/agents/code-reviewer.md +2 -0
  25. package/presets/claude/android-kotlin/agents/debugger.md +13 -0
  26. package/presets/claude/android-kotlin/agents/feature-developer.md +30 -0
  27. package/presets/claude/android-kotlin/agents/migration-specialist.md +6 -0
  28. package/presets/claude/android-kotlin/agents/performance-auditor.md +6 -0
  29. package/presets/claude/android-kotlin/agents/solution-architect.md +6 -0
  30. package/presets/claude/android-kotlin/agents/task-analyst.md +27 -0
  31. package/presets/claude/android-kotlin/agents/task-router.md +20 -0
  32. package/presets/claude/android-kotlin/commands/spec-start.md +1 -1
  33. package/presets/claude/android-kotlin/mcp.json +1 -1
  34. package/presets/claude/android-kotlin/rules/README.md +1 -0
  35. package/presets/claude/android-kotlin/rules/architecture/feature-delivery.md +3 -1
  36. package/presets/claude/android-kotlin/rules/architecture/product-specs-authoring.md +6 -4
  37. package/presets/claude/android-kotlin/rules/architecture/product-specs.md +8 -4
  38. package/presets/claude/android-kotlin/rules/tooling-and-review/agent-team-orchestrator.md +2 -1
  39. package/presets/claude/android-kotlin/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  40. package/presets/claude/android-kotlin/rules/tooling-and-review/code-quality.md +1 -1
  41. package/presets/claude/android-kotlin/rules/tooling-and-review/mcp-usage.md +100 -0
  42. package/presets/claude/android-kotlin/rules/tooling-and-review/preset-no-cross-stack-leakage.md +2 -0
  43. package/presets/claude/android-kotlin/skills/README.md +2 -0
  44. package/presets/claude/android-kotlin/skills/ci-investigation/SKILL.md +8 -0
  45. package/presets/claude/android-kotlin/skills/code-review/SKILL.md +6 -0
  46. package/presets/claude/android-kotlin/skills/debug-investigation/SKILL.md +40 -4
  47. package/presets/claude/android-kotlin/skills/feature-delivery/SKILL.md +6 -0
  48. package/presets/claude/android-kotlin/skills/spec-discovery/SKILL.md +58 -0
  49. package/presets/claude/android-kotlin/team/README.md +8 -0
  50. package/presets/claude/android-kotlin/team/fixtures/feature-full.json +1 -0
  51. package/presets/claude/android-kotlin/team/fixtures/memlog.example.md +9 -0
  52. package/presets/claude/go/MCP.md +22 -1
  53. package/presets/claude/go/agents/build-verifier.md +6 -0
  54. package/presets/claude/go/agents/ci-investigator.md +9 -0
  55. package/presets/claude/go/agents/code-reviewer.md +2 -0
  56. package/presets/claude/go/agents/debugger.md +15 -0
  57. package/presets/claude/go/agents/feature-developer.md +30 -0
  58. package/presets/claude/go/agents/migration-specialist.md +6 -0
  59. package/presets/claude/go/agents/performance-auditor.md +6 -0
  60. package/presets/claude/go/agents/solution-architect.md +6 -0
  61. package/presets/claude/go/agents/task-analyst.md +27 -0
  62. package/presets/claude/go/agents/task-router.md +20 -0
  63. package/presets/claude/go/commands/feature-continue.md +11 -40
  64. package/presets/claude/go/commands/spec-start.md +1 -1
  65. package/presets/claude/go/mcp.json +1 -1
  66. package/presets/claude/go/rules/README.md +2 -1
  67. package/presets/claude/go/rules/architecture/feature-delivery.md +2 -1
  68. package/presets/claude/go/rules/architecture/product-specs-authoring.md +6 -4
  69. package/presets/claude/go/rules/architecture/product-specs.md +8 -4
  70. package/presets/claude/go/rules/tooling-and-review/agent-team-orchestrator.md +1 -0
  71. package/presets/claude/go/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  72. package/presets/claude/go/rules/tooling-and-review/code-quality.md +1 -1
  73. package/presets/claude/go/rules/tooling-and-review/mcp-usage.md +99 -0
  74. package/presets/claude/go/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  75. package/presets/claude/go/skills/README.md +1 -1
  76. package/presets/claude/go/skills/ci-investigation/SKILL.md +7 -0
  77. package/presets/claude/go/skills/code-review/SKILL.md +7 -0
  78. package/presets/claude/go/skills/debug-investigation/SKILL.md +38 -2
  79. package/presets/claude/go/skills/feature-delivery/SKILL.md +7 -1
  80. package/presets/claude/go/skills/spec-discovery/SKILL.md +58 -0
  81. package/presets/claude/go/team/README.md +8 -0
  82. package/presets/claude/go/team/fixtures/feature-full.json +46 -10
  83. package/presets/claude/go/team/fixtures/memlog.example.md +9 -0
  84. package/presets/claude/ios-swift/MCP.md +20 -1
  85. package/presets/claude/ios-swift/agents/accessibility-reviewer.md +7 -10
  86. package/presets/claude/ios-swift/agents/api-contract-reviewer.md +2 -11
  87. package/presets/claude/ios-swift/agents/build-verifier.md +6 -0
  88. package/presets/claude/ios-swift/agents/ci-investigator.md +11 -11
  89. package/presets/claude/ios-swift/agents/code-reviewer.md +2 -0
  90. package/presets/claude/ios-swift/agents/debugger.md +15 -11
  91. package/presets/claude/ios-swift/agents/feature-developer.md +30 -0
  92. package/presets/claude/ios-swift/agents/migration-specialist.md +8 -11
  93. package/presets/claude/ios-swift/agents/performance-auditor.md +8 -11
  94. package/presets/claude/ios-swift/agents/qa-tester.md +2 -11
  95. package/presets/claude/ios-swift/agents/security-reviewer.md +2 -11
  96. package/presets/claude/ios-swift/agents/solution-architect.md +6 -0
  97. package/presets/claude/ios-swift/agents/task-analyst.md +27 -0
  98. package/presets/claude/ios-swift/agents/task-router.md +20 -0
  99. package/presets/claude/ios-swift/agents/unit-test-generator.md +2 -11
  100. package/presets/claude/ios-swift/agents/unit-test-healer.md +2 -11
  101. package/presets/claude/ios-swift/agents/unit-test-planner.md +2 -11
  102. package/presets/claude/ios-swift/agents/xcuitest-test-generator.md +1 -11
  103. package/presets/claude/ios-swift/agents/xcuitest-test-healer.md +1 -11
  104. package/presets/claude/ios-swift/agents/xcuitest-test-planner.md +1 -13
  105. package/presets/claude/ios-swift/commands/spec-start.md +1 -1
  106. package/presets/claude/ios-swift/mcp.json +1 -1
  107. package/presets/claude/ios-swift/rules/README.md +3 -1
  108. package/presets/claude/ios-swift/rules/architecture/feature-delivery.md +2 -1
  109. package/presets/claude/ios-swift/rules/architecture/product-specs-authoring.md +6 -4
  110. package/presets/claude/ios-swift/rules/architecture/product-specs.md +8 -4
  111. package/presets/claude/ios-swift/rules/tooling-and-review/agent-team-orchestrator.md +2 -1
  112. package/presets/claude/ios-swift/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  113. package/presets/claude/ios-swift/rules/tooling-and-review/code-quality.md +1 -1
  114. package/presets/claude/ios-swift/rules/tooling-and-review/mcp-usage.md +100 -0
  115. package/presets/claude/ios-swift/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  116. package/presets/claude/ios-swift/skills/README.md +2 -0
  117. package/presets/claude/ios-swift/skills/ci-investigation/SKILL.md +8 -0
  118. package/presets/claude/ios-swift/skills/code-review/SKILL.md +7 -1
  119. package/presets/claude/ios-swift/skills/debug-investigation/SKILL.md +41 -5
  120. package/presets/claude/ios-swift/skills/feature-delivery/SKILL.md +7 -1
  121. package/presets/claude/ios-swift/skills/spec-discovery/SKILL.md +58 -0
  122. package/presets/claude/ios-swift/team/README.md +8 -0
  123. package/presets/claude/ios-swift/team/fixtures/feature-full.json +39 -9
  124. package/presets/claude/ios-swift/team/fixtures/memlog.example.md +9 -0
  125. package/presets/claude/java/CLAUDE.md +1 -1
  126. package/presets/claude/java/MCP.md +21 -0
  127. package/presets/claude/java/agents/build-verifier.md +6 -0
  128. package/presets/claude/java/agents/ci-investigator.md +9 -0
  129. package/presets/claude/java/agents/code-reviewer.md +2 -0
  130. package/presets/claude/java/agents/debugger.md +15 -0
  131. package/presets/claude/java/agents/feature-developer.md +30 -0
  132. package/presets/claude/java/agents/migration-specialist.md +6 -0
  133. package/presets/claude/java/agents/performance-auditor.md +6 -0
  134. package/presets/claude/java/agents/solution-architect.md +6 -0
  135. package/presets/claude/java/agents/task-analyst.md +27 -0
  136. package/presets/claude/java/agents/task-router.md +20 -0
  137. package/presets/claude/java/commands/feature-continue.md +11 -40
  138. package/presets/claude/java/commands/spec-start.md +1 -1
  139. package/presets/claude/java/mcp.json +1 -1
  140. package/presets/claude/java/rules/README.md +1 -0
  141. package/presets/claude/java/rules/architecture/feature-delivery.md +2 -1
  142. package/presets/claude/java/rules/architecture/product-specs-authoring.md +6 -4
  143. package/presets/claude/java/rules/architecture/product-specs.md +8 -4
  144. package/presets/claude/java/rules/tooling-and-review/agent-team-orchestrator.md +1 -0
  145. package/presets/claude/java/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  146. package/presets/claude/java/rules/tooling-and-review/code-quality.md +1 -1
  147. package/presets/claude/java/rules/tooling-and-review/mcp-usage.md +98 -0
  148. package/presets/claude/java/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  149. package/presets/claude/java/skills/README.md +1 -1
  150. package/presets/claude/java/skills/ci-investigation/SKILL.md +7 -0
  151. package/presets/claude/java/skills/code-review/SKILL.md +7 -0
  152. package/presets/claude/java/skills/debug-investigation/SKILL.md +38 -2
  153. package/presets/claude/java/skills/feature-delivery/SKILL.md +7 -1
  154. package/presets/claude/java/skills/spec-discovery/SKILL.md +58 -0
  155. package/presets/claude/java/team/README.md +8 -0
  156. package/presets/claude/java/team/fixtures/feature-full.json +46 -10
  157. package/presets/claude/java/team/fixtures/memlog.example.md +9 -0
  158. package/presets/claude/mcp-ts/MCP.md +20 -1
  159. package/presets/claude/mcp-ts/agents/build-verifier.md +6 -0
  160. package/presets/claude/mcp-ts/agents/feature-developer.md +30 -0
  161. package/presets/claude/mcp-ts/agents/solution-architect.md +5 -0
  162. package/presets/claude/mcp-ts/agents/task-analyst.md +27 -0
  163. package/presets/claude/mcp-ts/agents/task-router.md +20 -0
  164. package/presets/claude/mcp-ts/commands/spec-start.md +1 -1
  165. package/presets/claude/mcp-ts/mcp.json +1 -1
  166. package/presets/claude/mcp-ts/rules/README.md +1 -0
  167. package/presets/claude/mcp-ts/rules/architecture/feature-delivery.md +3 -1
  168. package/presets/claude/mcp-ts/rules/architecture/product-specs-authoring.md +6 -4
  169. package/presets/claude/mcp-ts/rules/architecture/product-specs.md +8 -4
  170. package/presets/claude/mcp-ts/rules/tooling-and-review/agent-team-orchestrator.md +1 -0
  171. package/presets/claude/mcp-ts/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  172. package/presets/claude/mcp-ts/rules/tooling-and-review/code-quality.md +1 -1
  173. package/presets/claude/mcp-ts/rules/tooling-and-review/mcp-usage.md +99 -0
  174. package/presets/claude/mcp-ts/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  175. package/presets/claude/mcp-ts/skills/README.md +2 -0
  176. package/presets/claude/mcp-ts/skills/code-review/SKILL.md +7 -0
  177. package/presets/claude/mcp-ts/skills/debug-investigation/SKILL.md +36 -1
  178. package/presets/claude/mcp-ts/skills/feature-delivery/SKILL.md +7 -1
  179. package/presets/claude/mcp-ts/skills/spec-discovery/SKILL.md +58 -0
  180. package/presets/claude/mcp-ts/team/README.md +7 -0
  181. package/presets/claude/mcp-ts/team/fixtures/feature-full.json +5 -2
  182. package/presets/claude/mcp-ts/team/fixtures/memlog.example.md +9 -0
  183. package/presets/claude/next/MCP.md +22 -0
  184. package/presets/claude/next/agents/accessibility-reviewer.md +8 -0
  185. package/presets/claude/next/agents/build-verifier.md +6 -0
  186. package/presets/claude/next/agents/ci-investigator.md +9 -0
  187. package/presets/claude/next/agents/code-reviewer.md +2 -0
  188. package/presets/claude/next/agents/debugger.md +17 -0
  189. package/presets/claude/next/agents/feature-developer.md +32 -0
  190. package/presets/claude/next/agents/migration-specialist.md +6 -0
  191. package/presets/claude/next/agents/performance-auditor.md +8 -0
  192. package/presets/claude/next/agents/playwright-test-generator.md +11 -1
  193. package/presets/claude/next/agents/playwright-test-healer.md +8 -1
  194. package/presets/claude/next/agents/solution-architect.md +6 -0
  195. package/presets/claude/next/agents/task-analyst.md +28 -1
  196. package/presets/claude/next/agents/task-router.md +20 -0
  197. package/presets/claude/next/commands/feature-continue.md +11 -40
  198. package/presets/claude/next/commands/spec-start.md +1 -1
  199. package/presets/claude/next/mcp.json +3 -3
  200. package/presets/claude/next/rules/README.md +5 -3
  201. package/presets/claude/next/rules/architecture/feature-delivery-workflow.md +2 -1
  202. package/presets/claude/next/rules/architecture/product-specs-authoring.md +6 -4
  203. package/presets/claude/next/rules/architecture/product-specs.md +8 -4
  204. package/presets/claude/next/rules/testing/tests-unit.md +5 -0
  205. package/presets/claude/next/rules/tooling-and-review/agent-team-orchestrator.md +2 -1
  206. package/presets/claude/next/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  207. package/presets/claude/next/rules/tooling-and-review/code-quality.md +1 -1
  208. package/presets/claude/next/rules/tooling-and-review/mcp-usage.md +101 -0
  209. package/presets/claude/next/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  210. package/presets/claude/next/skills/README.md +2 -0
  211. package/presets/claude/next/skills/ci-investigation/SKILL.md +8 -0
  212. package/presets/claude/next/skills/code-review/SKILL.md +7 -1
  213. package/presets/claude/next/skills/debug-investigation/SKILL.md +39 -12
  214. package/presets/claude/next/skills/feature-delivery/SKILL.md +9 -1
  215. package/presets/claude/next/skills/spec-discovery/SKILL.md +58 -0
  216. package/presets/claude/next/team/README.md +11 -0
  217. package/presets/claude/next/team/fixtures/feature-full.json +43 -9
  218. package/presets/claude/next/team/fixtures/memlog.example.md +9 -0
  219. package/presets/claude/nuxt/MCP.md +22 -0
  220. package/presets/claude/nuxt/agents/accessibility-reviewer.md +8 -0
  221. package/presets/claude/nuxt/agents/build-verifier.md +6 -0
  222. package/presets/claude/nuxt/agents/ci-investigator.md +9 -0
  223. package/presets/claude/nuxt/agents/code-reviewer.md +2 -0
  224. package/presets/claude/nuxt/agents/debugger.md +17 -0
  225. package/presets/claude/nuxt/agents/feature-developer.md +32 -0
  226. package/presets/claude/nuxt/agents/migration-specialist.md +6 -0
  227. package/presets/claude/nuxt/agents/performance-auditor.md +8 -0
  228. package/presets/claude/nuxt/agents/playwright-test-generator.md +11 -1
  229. package/presets/claude/nuxt/agents/playwright-test-healer.md +8 -1
  230. package/presets/claude/nuxt/agents/solution-architect.md +6 -0
  231. package/presets/claude/nuxt/agents/task-analyst.md +28 -1
  232. package/presets/claude/nuxt/agents/task-router.md +24 -4
  233. package/presets/claude/nuxt/commands/spec-start.md +1 -1
  234. package/presets/claude/nuxt/mcp.json +3 -3
  235. package/presets/claude/nuxt/rules/README.md +2 -0
  236. package/presets/claude/nuxt/rules/architecture/feature-delivery-workflow.md +2 -1
  237. package/presets/claude/nuxt/rules/architecture/product-specs-authoring.md +6 -4
  238. package/presets/claude/nuxt/rules/architecture/product-specs.md +8 -4
  239. package/presets/claude/nuxt/rules/tooling-and-review/agent-team-orchestrator.md +2 -1
  240. package/presets/claude/nuxt/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  241. package/presets/claude/nuxt/rules/tooling-and-review/code-quality.md +1 -1
  242. package/presets/claude/nuxt/rules/tooling-and-review/mcp-usage.md +106 -0
  243. package/presets/claude/nuxt/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  244. package/presets/claude/nuxt/skills/README.md +2 -0
  245. package/presets/claude/nuxt/skills/ci-investigation/SKILL.md +8 -0
  246. package/presets/claude/nuxt/skills/code-review/SKILL.md +7 -1
  247. package/presets/claude/nuxt/skills/debug-investigation/SKILL.md +41 -12
  248. package/presets/claude/nuxt/skills/feature-delivery/SKILL.md +9 -1
  249. package/presets/claude/nuxt/skills/spec-discovery/SKILL.md +58 -0
  250. package/presets/claude/nuxt/team/README.md +11 -0
  251. package/presets/claude/nuxt/team/fixtures/feature-full.json +43 -9
  252. package/presets/claude/nuxt/team/fixtures/memlog.example.md +9 -0
  253. package/presets/claude/php-hexagonal/CLAUDE.md +1 -1
  254. package/presets/claude/php-hexagonal/MCP.md +20 -1
  255. package/presets/claude/php-hexagonal/agents/build-verifier.md +6 -0
  256. package/presets/claude/php-hexagonal/agents/ci-investigator.md +9 -0
  257. package/presets/claude/php-hexagonal/agents/code-reviewer.md +2 -0
  258. package/presets/claude/php-hexagonal/agents/debugger.md +15 -0
  259. package/presets/claude/php-hexagonal/agents/feature-developer.md +30 -0
  260. package/presets/claude/php-hexagonal/agents/migration-specialist.md +6 -0
  261. package/presets/claude/php-hexagonal/agents/performance-auditor.md +6 -0
  262. package/presets/claude/php-hexagonal/agents/solution-architect.md +6 -0
  263. package/presets/claude/php-hexagonal/agents/task-analyst.md +27 -0
  264. package/presets/claude/php-hexagonal/agents/task-router.md +20 -0
  265. package/presets/claude/php-hexagonal/commands/feature-continue.md +11 -40
  266. package/presets/claude/php-hexagonal/commands/spec-start.md +1 -1
  267. package/presets/claude/php-hexagonal/mcp.json +1 -1
  268. package/presets/claude/php-hexagonal/rules/README.md +1 -0
  269. package/presets/claude/php-hexagonal/rules/architecture/feature-delivery.md +2 -1
  270. package/presets/claude/php-hexagonal/rules/architecture/product-specs-authoring.md +6 -4
  271. package/presets/claude/php-hexagonal/rules/architecture/product-specs.md +8 -4
  272. package/presets/claude/php-hexagonal/rules/tooling-and-review/agent-team-orchestrator.md +1 -0
  273. package/presets/claude/php-hexagonal/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  274. package/presets/claude/php-hexagonal/rules/tooling-and-review/code-quality.md +1 -1
  275. package/presets/claude/php-hexagonal/rules/tooling-and-review/mcp-usage.md +98 -0
  276. package/presets/claude/php-hexagonal/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  277. package/presets/claude/php-hexagonal/skills/README.md +1 -1
  278. package/presets/claude/php-hexagonal/skills/ci-investigation/SKILL.md +7 -0
  279. package/presets/claude/php-hexagonal/skills/code-review/SKILL.md +7 -0
  280. package/presets/claude/php-hexagonal/skills/debug-investigation/SKILL.md +38 -2
  281. package/presets/claude/php-hexagonal/skills/feature-delivery/SKILL.md +7 -1
  282. package/presets/claude/php-hexagonal/skills/spec-discovery/SKILL.md +58 -0
  283. package/presets/claude/php-hexagonal/team/README.md +8 -0
  284. package/presets/claude/php-hexagonal/team/fixtures/feature-full.json +46 -10
  285. package/presets/claude/php-hexagonal/team/fixtures/memlog.example.md +9 -0
  286. package/presets/claude/php-laravel/MCP.md +21 -0
  287. package/presets/claude/php-laravel/agents/build-verifier.md +6 -0
  288. package/presets/claude/php-laravel/agents/ci-investigator.md +9 -0
  289. package/presets/claude/php-laravel/agents/code-reviewer.md +2 -0
  290. package/presets/claude/php-laravel/agents/debugger.md +15 -0
  291. package/presets/claude/php-laravel/agents/feature-developer.md +30 -0
  292. package/presets/claude/php-laravel/agents/migration-specialist.md +6 -0
  293. package/presets/claude/php-laravel/agents/performance-auditor.md +6 -0
  294. package/presets/claude/php-laravel/agents/solution-architect.md +6 -0
  295. package/presets/claude/php-laravel/agents/task-analyst.md +27 -0
  296. package/presets/claude/php-laravel/agents/task-router.md +20 -0
  297. package/presets/claude/php-laravel/commands/feature-continue.md +11 -40
  298. package/presets/claude/php-laravel/commands/spec-start.md +1 -1
  299. package/presets/claude/php-laravel/mcp.json +1 -1
  300. package/presets/claude/php-laravel/rules/README.md +1 -0
  301. package/presets/claude/php-laravel/rules/architecture/feature-delivery.md +3 -1
  302. package/presets/claude/php-laravel/rules/architecture/product-specs-authoring.md +6 -4
  303. package/presets/claude/php-laravel/rules/architecture/product-specs.md +8 -4
  304. package/presets/claude/php-laravel/rules/tooling-and-review/agent-team-orchestrator.md +1 -0
  305. package/presets/claude/php-laravel/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  306. package/presets/claude/php-laravel/rules/tooling-and-review/code-quality.md +1 -1
  307. package/presets/claude/php-laravel/rules/tooling-and-review/mcp-usage.md +98 -0
  308. package/presets/claude/php-laravel/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  309. package/presets/claude/php-laravel/skills/README.md +1 -1
  310. package/presets/claude/php-laravel/skills/ci-investigation/SKILL.md +7 -0
  311. package/presets/claude/php-laravel/skills/code-review/SKILL.md +7 -0
  312. package/presets/claude/php-laravel/skills/debug-investigation/SKILL.md +38 -2
  313. package/presets/claude/php-laravel/skills/feature-delivery/SKILL.md +7 -1
  314. package/presets/claude/php-laravel/skills/spec-discovery/SKILL.md +58 -0
  315. package/presets/claude/php-laravel/team/README.md +7 -0
  316. package/presets/claude/php-laravel/team/fixtures/feature-full.json +38 -9
  317. package/presets/claude/php-laravel/team/fixtures/memlog.example.md +9 -0
  318. package/presets/claude/svelte/MCP.md +22 -0
  319. package/presets/claude/svelte/agents/accessibility-reviewer.md +8 -0
  320. package/presets/claude/svelte/agents/build-verifier.md +6 -0
  321. package/presets/claude/svelte/agents/ci-investigator.md +9 -0
  322. package/presets/claude/svelte/agents/code-reviewer.md +2 -0
  323. package/presets/claude/svelte/agents/debugger.md +17 -0
  324. package/presets/claude/svelte/agents/feature-developer.md +32 -0
  325. package/presets/claude/svelte/agents/migration-specialist.md +6 -0
  326. package/presets/claude/svelte/agents/performance-auditor.md +8 -0
  327. package/presets/claude/svelte/agents/playwright-test-generator.md +11 -1
  328. package/presets/claude/svelte/agents/playwright-test-healer.md +8 -1
  329. package/presets/claude/svelte/agents/solution-architect.md +6 -0
  330. package/presets/claude/svelte/agents/task-analyst.md +28 -1
  331. package/presets/claude/svelte/agents/task-router.md +20 -0
  332. package/presets/claude/svelte/commands/spec-start.md +1 -1
  333. package/presets/claude/svelte/mcp.json +3 -3
  334. package/presets/claude/svelte/rules/README.md +2 -0
  335. package/presets/claude/svelte/rules/architecture/feature-delivery-workflow.md +2 -1
  336. package/presets/claude/svelte/rules/architecture/product-specs-authoring.md +6 -4
  337. package/presets/claude/svelte/rules/architecture/product-specs.md +8 -4
  338. package/presets/claude/svelte/rules/tooling-and-review/agent-team-orchestrator.md +2 -1
  339. package/presets/claude/svelte/rules/tooling-and-review/anti-sycophancy-discipline.md +1 -1
  340. package/presets/claude/svelte/rules/tooling-and-review/code-quality.md +1 -1
  341. package/presets/claude/svelte/rules/tooling-and-review/mcp-usage.md +101 -0
  342. package/presets/claude/svelte/rules/tooling-and-review/preset-no-cross-stack-leakage.md +1 -0
  343. package/presets/claude/svelte/skills/README.md +2 -0
  344. package/presets/claude/svelte/skills/ci-investigation/SKILL.md +8 -0
  345. package/presets/claude/svelte/skills/code-review/SKILL.md +7 -1
  346. package/presets/claude/svelte/skills/debug-investigation/SKILL.md +41 -12
  347. package/presets/claude/svelte/skills/feature-delivery/SKILL.md +9 -1
  348. package/presets/claude/svelte/skills/spec-discovery/SKILL.md +58 -0
  349. package/presets/claude/svelte/team/README.md +11 -0
  350. package/presets/claude/svelte/team/fixtures/feature-full.json +43 -9
  351. package/presets/claude/svelte/team/fixtures/memlog.example.md +9 -0
  352. package/presets/cursor/android-kotlin/MCP.md +20 -1
  353. package/presets/cursor/android-kotlin/agents/accessibility-reviewer.md +6 -0
  354. package/presets/cursor/android-kotlin/agents/build-verifier.md +6 -0
  355. package/presets/cursor/android-kotlin/agents/ci-investigator.md +9 -0
  356. package/presets/cursor/android-kotlin/agents/code-reviewer.md +2 -0
  357. package/presets/cursor/android-kotlin/agents/debugger.md +13 -0
  358. package/presets/cursor/android-kotlin/agents/feature-developer.md +30 -0
  359. package/presets/cursor/android-kotlin/agents/migration-specialist.md +6 -0
  360. package/presets/cursor/android-kotlin/agents/performance-auditor.md +6 -0
  361. package/presets/cursor/android-kotlin/agents/solution-architect.md +6 -0
  362. package/presets/cursor/android-kotlin/agents/task-analyst.md +27 -0
  363. package/presets/cursor/android-kotlin/agents/task-router.md +20 -0
  364. package/presets/cursor/android-kotlin/commands/spec-start.md +1 -1
  365. package/presets/cursor/android-kotlin/mcp.json +1 -1
  366. package/presets/cursor/android-kotlin/rules/README.md +2 -0
  367. package/presets/cursor/android-kotlin/rules/agent-team-orchestrator.mdc +2 -1
  368. package/presets/cursor/android-kotlin/rules/anti-sycophancy-discipline.mdc +1 -1
  369. package/presets/cursor/android-kotlin/rules/code-quality-and-refactoring.mdc +1 -1
  370. package/presets/cursor/android-kotlin/rules/feature-delivery-workflow.mdc +3 -1
  371. package/presets/cursor/android-kotlin/rules/mcp-usage.mdc +99 -0
  372. package/presets/cursor/android-kotlin/rules/preset-no-cross-stack-leakage.mdc +3 -1
  373. package/presets/cursor/android-kotlin/rules/product-specs-authoring.mdc +6 -4
  374. package/presets/cursor/android-kotlin/rules/product-specs.mdc +8 -4
  375. package/presets/cursor/android-kotlin/skills/README.md +2 -0
  376. package/presets/cursor/android-kotlin/skills/ci-investigation/SKILL.md +8 -0
  377. package/presets/cursor/android-kotlin/skills/code-review/SKILL.md +6 -0
  378. package/presets/cursor/android-kotlin/skills/debug-investigation/SKILL.md +40 -4
  379. package/presets/cursor/android-kotlin/skills/feature-delivery/SKILL.md +6 -0
  380. package/presets/cursor/android-kotlin/skills/spec-discovery/SKILL.md +58 -0
  381. package/presets/cursor/android-kotlin/team/README.md +8 -0
  382. package/presets/cursor/android-kotlin/team/fixtures/feature-full.json +1 -0
  383. package/presets/cursor/android-kotlin/team/fixtures/memlog.example.md +9 -0
  384. package/presets/cursor/go/MCP.md +22 -1
  385. package/presets/cursor/go/agents/build-verifier.md +6 -0
  386. package/presets/cursor/go/agents/ci-investigator.md +9 -0
  387. package/presets/cursor/go/agents/code-reviewer.md +2 -0
  388. package/presets/cursor/go/agents/debugger.md +15 -0
  389. package/presets/cursor/go/agents/feature-developer.md +30 -0
  390. package/presets/cursor/go/agents/migration-specialist.md +6 -0
  391. package/presets/cursor/go/agents/performance-auditor.md +6 -0
  392. package/presets/cursor/go/agents/solution-architect.md +6 -0
  393. package/presets/cursor/go/agents/task-analyst.md +27 -0
  394. package/presets/cursor/go/agents/task-router.md +20 -0
  395. package/presets/cursor/go/commands/spec-start.md +1 -1
  396. package/presets/cursor/go/mcp.json +1 -1
  397. package/presets/cursor/go/rules/README.md +2 -1
  398. package/presets/cursor/go/rules/agent-team-orchestrator.mdc +1 -0
  399. package/presets/cursor/go/rules/anti-sycophancy-discipline.mdc +1 -1
  400. package/presets/cursor/go/rules/code-quality-and-refactoring.mdc +1 -1
  401. package/presets/cursor/go/rules/feature-delivery-workflow.mdc +2 -1
  402. package/presets/cursor/go/rules/mcp-usage.mdc +98 -0
  403. package/presets/cursor/go/rules/preset-no-cross-stack-leakage.mdc +1 -0
  404. package/presets/cursor/go/rules/product-specs-authoring.mdc +6 -4
  405. package/presets/cursor/go/rules/product-specs.mdc +8 -4
  406. package/presets/cursor/go/skills/README.md +1 -1
  407. package/presets/cursor/go/skills/ci-investigation/SKILL.md +7 -0
  408. package/presets/cursor/go/skills/code-review/SKILL.md +7 -0
  409. package/presets/cursor/go/skills/debug-investigation/SKILL.md +38 -2
  410. package/presets/cursor/go/skills/feature-delivery/SKILL.md +7 -1
  411. package/presets/cursor/go/skills/spec-discovery/SKILL.md +58 -0
  412. package/presets/cursor/go/team/README.md +8 -0
  413. package/presets/cursor/go/team/fixtures/feature-full.json +46 -10
  414. package/presets/cursor/go/team/fixtures/memlog.example.md +9 -0
  415. package/presets/cursor/ios-swift/MCP.md +20 -1
  416. package/presets/cursor/ios-swift/agents/accessibility-reviewer.md +7 -10
  417. package/presets/cursor/ios-swift/agents/api-contract-reviewer.md +2 -11
  418. package/presets/cursor/ios-swift/agents/build-verifier.md +6 -0
  419. package/presets/cursor/ios-swift/agents/ci-investigator.md +11 -11
  420. package/presets/cursor/ios-swift/agents/code-reviewer.md +2 -0
  421. package/presets/cursor/ios-swift/agents/debugger.md +15 -11
  422. package/presets/cursor/ios-swift/agents/feature-developer.md +30 -0
  423. package/presets/cursor/ios-swift/agents/migration-specialist.md +8 -11
  424. package/presets/cursor/ios-swift/agents/performance-auditor.md +8 -11
  425. package/presets/cursor/ios-swift/agents/qa-tester.md +2 -11
  426. package/presets/cursor/ios-swift/agents/security-reviewer.md +2 -11
  427. package/presets/cursor/ios-swift/agents/solution-architect.md +6 -0
  428. package/presets/cursor/ios-swift/agents/task-analyst.md +27 -0
  429. package/presets/cursor/ios-swift/agents/task-router.md +20 -0
  430. package/presets/cursor/ios-swift/agents/unit-test-generator.md +2 -11
  431. package/presets/cursor/ios-swift/agents/unit-test-healer.md +2 -11
  432. package/presets/cursor/ios-swift/agents/unit-test-planner.md +2 -11
  433. package/presets/cursor/ios-swift/agents/xcuitest-test-generator.md +1 -11
  434. package/presets/cursor/ios-swift/agents/xcuitest-test-healer.md +1 -11
  435. package/presets/cursor/ios-swift/agents/xcuitest-test-planner.md +1 -13
  436. package/presets/cursor/ios-swift/commands/spec-start.md +1 -1
  437. package/presets/cursor/ios-swift/mcp.json +1 -1
  438. package/presets/cursor/ios-swift/rules/README.md +2 -0
  439. package/presets/cursor/ios-swift/rules/agent-team-orchestrator.mdc +2 -1
  440. package/presets/cursor/ios-swift/rules/anti-sycophancy-discipline.mdc +1 -1
  441. package/presets/cursor/ios-swift/rules/code-quality-and-refactoring.mdc +1 -1
  442. package/presets/cursor/ios-swift/rules/feature-delivery-workflow.mdc +2 -1
  443. package/presets/cursor/ios-swift/rules/mcp-usage.mdc +99 -0
  444. package/presets/cursor/ios-swift/rules/preset-no-cross-stack-leakage.mdc +1 -0
  445. package/presets/cursor/ios-swift/rules/product-specs-authoring.mdc +6 -4
  446. package/presets/cursor/ios-swift/rules/product-specs.mdc +8 -4
  447. package/presets/cursor/ios-swift/skills/README.md +2 -0
  448. package/presets/cursor/ios-swift/skills/ci-investigation/SKILL.md +8 -0
  449. package/presets/cursor/ios-swift/skills/code-review/SKILL.md +7 -1
  450. package/presets/cursor/ios-swift/skills/debug-investigation/SKILL.md +41 -5
  451. package/presets/cursor/ios-swift/skills/feature-delivery/SKILL.md +7 -1
  452. package/presets/cursor/ios-swift/skills/spec-discovery/SKILL.md +58 -0
  453. package/presets/cursor/ios-swift/team/README.md +8 -0
  454. package/presets/cursor/ios-swift/team/fixtures/feature-full.json +39 -9
  455. package/presets/cursor/ios-swift/team/fixtures/memlog.example.md +9 -0
  456. package/presets/cursor/java/AGENTS.md +1 -1
  457. package/presets/cursor/java/MCP.md +20 -1
  458. package/presets/cursor/java/agents/build-verifier.md +6 -0
  459. package/presets/cursor/java/agents/ci-investigator.md +9 -0
  460. package/presets/cursor/java/agents/code-reviewer.md +2 -0
  461. package/presets/cursor/java/agents/debugger.md +15 -0
  462. package/presets/cursor/java/agents/feature-developer.md +30 -0
  463. package/presets/cursor/java/agents/migration-specialist.md +6 -0
  464. package/presets/cursor/java/agents/performance-auditor.md +6 -0
  465. package/presets/cursor/java/agents/solution-architect.md +6 -0
  466. package/presets/cursor/java/agents/task-analyst.md +27 -0
  467. package/presets/cursor/java/agents/task-router.md +20 -0
  468. package/presets/cursor/java/commands/spec-start.md +1 -1
  469. package/presets/cursor/java/mcp.json +1 -1
  470. package/presets/cursor/java/rules/README.md +2 -1
  471. package/presets/cursor/java/rules/agent-team-orchestrator.mdc +1 -0
  472. package/presets/cursor/java/rules/anti-sycophancy-discipline.mdc +1 -1
  473. package/presets/cursor/java/rules/code-quality-and-refactoring.mdc +1 -1
  474. package/presets/cursor/java/rules/feature-delivery-workflow.mdc +2 -1
  475. package/presets/cursor/java/rules/mcp-usage.mdc +97 -0
  476. package/presets/cursor/java/rules/preset-no-cross-stack-leakage.mdc +1 -0
  477. package/presets/cursor/java/rules/product-specs-authoring.mdc +6 -4
  478. package/presets/cursor/java/rules/product-specs.mdc +8 -4
  479. package/presets/cursor/java/skills/README.md +1 -1
  480. package/presets/cursor/java/skills/ci-investigation/SKILL.md +7 -0
  481. package/presets/cursor/java/skills/code-review/SKILL.md +7 -0
  482. package/presets/cursor/java/skills/debug-investigation/SKILL.md +38 -2
  483. package/presets/cursor/java/skills/feature-delivery/SKILL.md +7 -1
  484. package/presets/cursor/java/skills/spec-discovery/SKILL.md +58 -0
  485. package/presets/cursor/java/team/README.md +8 -0
  486. package/presets/cursor/java/team/fixtures/feature-full.json +46 -10
  487. package/presets/cursor/java/team/fixtures/memlog.example.md +9 -0
  488. package/presets/cursor/mcp-ts/MCP.md +20 -1
  489. package/presets/cursor/mcp-ts/agents/build-verifier.md +6 -0
  490. package/presets/cursor/mcp-ts/agents/feature-developer.md +30 -0
  491. package/presets/cursor/mcp-ts/agents/solution-architect.md +5 -0
  492. package/presets/cursor/mcp-ts/agents/task-analyst.md +27 -0
  493. package/presets/cursor/mcp-ts/agents/task-router.md +20 -0
  494. package/presets/cursor/mcp-ts/commands/spec-start.md +1 -1
  495. package/presets/cursor/mcp-ts/mcp.json +1 -1
  496. package/presets/cursor/mcp-ts/rules/README.md +3 -2
  497. package/presets/cursor/mcp-ts/rules/agent-team-orchestrator.mdc +1 -0
  498. package/presets/cursor/mcp-ts/rules/anti-sycophancy-discipline.mdc +1 -1
  499. package/presets/cursor/mcp-ts/rules/code-quality-and-refactoring.mdc +1 -1
  500. package/presets/cursor/mcp-ts/rules/feature-delivery-workflow.mdc +2 -1
  501. package/presets/cursor/mcp-ts/rules/mcp-usage.mdc +98 -0
  502. package/presets/cursor/mcp-ts/rules/preset-no-cross-stack-leakage.mdc +1 -0
  503. package/presets/cursor/mcp-ts/rules/product-specs-authoring.mdc +6 -4
  504. package/presets/cursor/mcp-ts/rules/product-specs.mdc +8 -4
  505. package/presets/cursor/mcp-ts/skills/README.md +2 -0
  506. package/presets/cursor/mcp-ts/skills/code-review/SKILL.md +7 -0
  507. package/presets/cursor/mcp-ts/skills/debug-investigation/SKILL.md +36 -1
  508. package/presets/cursor/mcp-ts/skills/feature-delivery/SKILL.md +7 -1
  509. package/presets/cursor/mcp-ts/skills/spec-discovery/SKILL.md +58 -0
  510. package/presets/cursor/mcp-ts/team/README.md +7 -0
  511. package/presets/cursor/mcp-ts/team/fixtures/feature-full.json +5 -2
  512. package/presets/cursor/mcp-ts/team/fixtures/memlog.example.md +9 -0
  513. package/presets/cursor/next/MCP.md +21 -1
  514. package/presets/cursor/next/agents/accessibility-reviewer.md +8 -0
  515. package/presets/cursor/next/agents/build-verifier.md +6 -0
  516. package/presets/cursor/next/agents/ci-investigator.md +9 -0
  517. package/presets/cursor/next/agents/code-reviewer.md +2 -0
  518. package/presets/cursor/next/agents/debugger.md +17 -0
  519. package/presets/cursor/next/agents/feature-developer.md +32 -0
  520. package/presets/cursor/next/agents/migration-specialist.md +6 -0
  521. package/presets/cursor/next/agents/performance-auditor.md +8 -0
  522. package/presets/cursor/next/agents/playwright-test-generator.md +9 -1
  523. package/presets/cursor/next/agents/playwright-test-healer.md +9 -1
  524. package/presets/cursor/next/agents/playwright-test-planner.md +1 -1
  525. package/presets/cursor/next/agents/solution-architect.md +6 -0
  526. package/presets/cursor/next/agents/task-analyst.md +28 -1
  527. package/presets/cursor/next/agents/task-router.md +20 -0
  528. package/presets/cursor/next/commands/spec-start.md +1 -1
  529. package/presets/cursor/next/mcp.json +3 -3
  530. package/presets/cursor/next/rules/README.md +3 -2
  531. package/presets/cursor/next/rules/agent-team-orchestrator.mdc +2 -1
  532. package/presets/cursor/next/rules/anti-sycophancy-discipline.mdc +1 -1
  533. package/presets/cursor/next/rules/code-quality-and-refactoring.mdc +1 -1
  534. package/presets/cursor/next/rules/feature-delivery-workflow.mdc +2 -1
  535. package/presets/cursor/next/rules/mcp-usage.mdc +100 -0
  536. package/presets/cursor/next/rules/preset-no-cross-stack-leakage.mdc +1 -0
  537. package/presets/cursor/next/rules/product-specs-authoring.mdc +6 -4
  538. package/presets/cursor/next/rules/product-specs.mdc +8 -4
  539. package/presets/cursor/next/rules/tests-unit.mdc +5 -0
  540. package/presets/cursor/next/skills/README.md +2 -0
  541. package/presets/cursor/next/skills/ci-investigation/SKILL.md +8 -0
  542. package/presets/cursor/next/skills/code-review/SKILL.md +7 -1
  543. package/presets/cursor/next/skills/debug-investigation/SKILL.md +39 -12
  544. package/presets/cursor/next/skills/feature-delivery/SKILL.md +9 -1
  545. package/presets/cursor/next/skills/spec-discovery/SKILL.md +58 -0
  546. package/presets/cursor/next/team/README.md +11 -0
  547. package/presets/cursor/next/team/fixtures/feature-full.json +1 -0
  548. package/presets/cursor/next/team/fixtures/memlog.example.md +9 -0
  549. package/presets/cursor/nuxt/MCP.md +21 -1
  550. package/presets/cursor/nuxt/agents/accessibility-reviewer.md +8 -0
  551. package/presets/cursor/nuxt/agents/build-verifier.md +6 -0
  552. package/presets/cursor/nuxt/agents/ci-investigator.md +9 -0
  553. package/presets/cursor/nuxt/agents/code-reviewer.md +2 -0
  554. package/presets/cursor/nuxt/agents/debugger.md +17 -0
  555. package/presets/cursor/nuxt/agents/feature-developer.md +32 -0
  556. package/presets/cursor/nuxt/agents/migration-specialist.md +6 -0
  557. package/presets/cursor/nuxt/agents/performance-auditor.md +8 -0
  558. package/presets/cursor/nuxt/agents/playwright-test-generator.md +9 -1
  559. package/presets/cursor/nuxt/agents/playwright-test-healer.md +9 -1
  560. package/presets/cursor/nuxt/agents/playwright-test-planner.md +1 -1
  561. package/presets/cursor/nuxt/agents/solution-architect.md +6 -0
  562. package/presets/cursor/nuxt/agents/task-analyst.md +28 -1
  563. package/presets/cursor/nuxt/agents/task-router.md +20 -0
  564. package/presets/cursor/nuxt/commands/spec-start.md +1 -1
  565. package/presets/cursor/nuxt/mcp.json +3 -3
  566. package/presets/cursor/nuxt/rules/README.md +2 -1
  567. package/presets/cursor/nuxt/rules/agent-team-orchestrator.mdc +2 -1
  568. package/presets/cursor/nuxt/rules/anti-sycophancy-discipline.mdc +1 -1
  569. package/presets/cursor/nuxt/rules/code-quality-and-refactoring.mdc +1 -1
  570. package/presets/cursor/nuxt/rules/feature-delivery-workflow.mdc +2 -1
  571. package/presets/cursor/nuxt/rules/mcp-usage.mdc +100 -0
  572. package/presets/cursor/nuxt/rules/preset-no-cross-stack-leakage.mdc +1 -0
  573. package/presets/cursor/nuxt/rules/product-specs-authoring.mdc +6 -4
  574. package/presets/cursor/nuxt/rules/product-specs.mdc +8 -4
  575. package/presets/cursor/nuxt/skills/README.md +2 -0
  576. package/presets/cursor/nuxt/skills/ci-investigation/SKILL.md +8 -0
  577. package/presets/cursor/nuxt/skills/code-review/SKILL.md +7 -1
  578. package/presets/cursor/nuxt/skills/debug-investigation/SKILL.md +41 -12
  579. package/presets/cursor/nuxt/skills/feature-delivery/SKILL.md +9 -1
  580. package/presets/cursor/nuxt/skills/spec-discovery/SKILL.md +58 -0
  581. package/presets/cursor/nuxt/team/README.md +11 -0
  582. package/presets/cursor/nuxt/team/fixtures/feature-full.json +43 -9
  583. package/presets/cursor/nuxt/team/fixtures/memlog.example.md +9 -0
  584. package/presets/cursor/php-hexagonal/AGENTS.md +1 -1
  585. package/presets/cursor/php-hexagonal/MCP.md +20 -1
  586. package/presets/cursor/php-hexagonal/agents/build-verifier.md +6 -0
  587. package/presets/cursor/php-hexagonal/agents/ci-investigator.md +9 -0
  588. package/presets/cursor/php-hexagonal/agents/code-reviewer.md +2 -0
  589. package/presets/cursor/php-hexagonal/agents/debugger.md +15 -0
  590. package/presets/cursor/php-hexagonal/agents/feature-developer.md +30 -0
  591. package/presets/cursor/php-hexagonal/agents/migration-specialist.md +6 -0
  592. package/presets/cursor/php-hexagonal/agents/performance-auditor.md +6 -0
  593. package/presets/cursor/php-hexagonal/agents/solution-architect.md +6 -0
  594. package/presets/cursor/php-hexagonal/agents/task-analyst.md +27 -0
  595. package/presets/cursor/php-hexagonal/agents/task-router.md +20 -0
  596. package/presets/cursor/php-hexagonal/commands/spec-start.md +1 -1
  597. package/presets/cursor/php-hexagonal/mcp.json +1 -1
  598. package/presets/cursor/php-hexagonal/rules/README.md +2 -1
  599. package/presets/cursor/php-hexagonal/rules/agent-team-orchestrator.mdc +1 -0
  600. package/presets/cursor/php-hexagonal/rules/anti-sycophancy-discipline.mdc +1 -1
  601. package/presets/cursor/php-hexagonal/rules/code-quality-and-refactoring.mdc +1 -1
  602. package/presets/cursor/php-hexagonal/rules/feature-delivery-workflow.mdc +2 -1
  603. package/presets/cursor/php-hexagonal/rules/mcp-usage.mdc +97 -0
  604. package/presets/cursor/php-hexagonal/rules/preset-no-cross-stack-leakage.mdc +1 -0
  605. package/presets/cursor/php-hexagonal/rules/product-specs-authoring.mdc +6 -4
  606. package/presets/cursor/php-hexagonal/rules/product-specs.mdc +8 -4
  607. package/presets/cursor/php-hexagonal/skills/README.md +1 -1
  608. package/presets/cursor/php-hexagonal/skills/ci-investigation/SKILL.md +7 -0
  609. package/presets/cursor/php-hexagonal/skills/code-review/SKILL.md +7 -0
  610. package/presets/cursor/php-hexagonal/skills/debug-investigation/SKILL.md +38 -2
  611. package/presets/cursor/php-hexagonal/skills/feature-delivery/SKILL.md +7 -1
  612. package/presets/cursor/php-hexagonal/skills/spec-discovery/SKILL.md +58 -0
  613. package/presets/cursor/php-hexagonal/team/README.md +8 -0
  614. package/presets/cursor/php-hexagonal/team/fixtures/feature-full.json +46 -10
  615. package/presets/cursor/php-hexagonal/team/fixtures/memlog.example.md +9 -0
  616. package/presets/cursor/php-laravel/AGENTS.md +1 -1
  617. package/presets/cursor/php-laravel/MCP.md +21 -0
  618. package/presets/cursor/php-laravel/agents/build-verifier.md +6 -0
  619. package/presets/cursor/php-laravel/agents/ci-investigator.md +9 -0
  620. package/presets/cursor/php-laravel/agents/code-reviewer.md +2 -0
  621. package/presets/cursor/php-laravel/agents/debugger.md +15 -0
  622. package/presets/cursor/php-laravel/agents/feature-developer.md +30 -0
  623. package/presets/cursor/php-laravel/agents/migration-specialist.md +6 -0
  624. package/presets/cursor/php-laravel/agents/performance-auditor.md +6 -0
  625. package/presets/cursor/php-laravel/agents/solution-architect.md +6 -0
  626. package/presets/cursor/php-laravel/agents/task-analyst.md +27 -0
  627. package/presets/cursor/php-laravel/agents/task-router.md +20 -0
  628. package/presets/cursor/php-laravel/commands/spec-start.md +1 -1
  629. package/presets/cursor/php-laravel/mcp.json +1 -1
  630. package/presets/cursor/php-laravel/rules/README.md +2 -1
  631. package/presets/cursor/php-laravel/rules/agent-team-orchestrator.mdc +1 -0
  632. package/presets/cursor/php-laravel/rules/anti-sycophancy-discipline.mdc +1 -1
  633. package/presets/cursor/php-laravel/rules/code-quality-and-refactoring.mdc +1 -1
  634. package/presets/cursor/php-laravel/rules/feature-delivery-workflow.mdc +2 -1
  635. package/presets/cursor/php-laravel/rules/mcp-usage.mdc +97 -0
  636. package/presets/cursor/php-laravel/rules/preset-no-cross-stack-leakage.mdc +1 -0
  637. package/presets/cursor/php-laravel/rules/product-specs-authoring.mdc +6 -4
  638. package/presets/cursor/php-laravel/rules/product-specs.mdc +8 -4
  639. package/presets/cursor/php-laravel/skills/README.md +1 -1
  640. package/presets/cursor/php-laravel/skills/ci-investigation/SKILL.md +7 -0
  641. package/presets/cursor/php-laravel/skills/code-review/SKILL.md +7 -0
  642. package/presets/cursor/php-laravel/skills/debug-investigation/SKILL.md +38 -2
  643. package/presets/cursor/php-laravel/skills/feature-delivery/SKILL.md +7 -1
  644. package/presets/cursor/php-laravel/skills/spec-discovery/SKILL.md +58 -0
  645. package/presets/cursor/php-laravel/team/README.md +7 -0
  646. package/presets/cursor/php-laravel/team/fixtures/feature-full.json +38 -9
  647. package/presets/cursor/php-laravel/team/fixtures/memlog.example.md +9 -0
  648. package/presets/cursor/svelte/MCP.md +21 -1
  649. package/presets/cursor/svelte/agents/accessibility-reviewer.md +8 -0
  650. package/presets/cursor/svelte/agents/build-verifier.md +6 -0
  651. package/presets/cursor/svelte/agents/ci-investigator.md +9 -0
  652. package/presets/cursor/svelte/agents/code-reviewer.md +2 -0
  653. package/presets/cursor/svelte/agents/debugger.md +17 -0
  654. package/presets/cursor/svelte/agents/feature-developer.md +32 -0
  655. package/presets/cursor/svelte/agents/migration-specialist.md +6 -0
  656. package/presets/cursor/svelte/agents/performance-auditor.md +8 -0
  657. package/presets/cursor/svelte/agents/playwright-test-generator.md +9 -1
  658. package/presets/cursor/svelte/agents/playwright-test-healer.md +9 -1
  659. package/presets/cursor/svelte/agents/playwright-test-planner.md +1 -1
  660. package/presets/cursor/svelte/agents/solution-architect.md +6 -0
  661. package/presets/cursor/svelte/agents/task-analyst.md +28 -1
  662. package/presets/cursor/svelte/agents/task-router.md +20 -0
  663. package/presets/cursor/svelte/commands/spec-start.md +1 -1
  664. package/presets/cursor/svelte/mcp.json +3 -3
  665. package/presets/cursor/svelte/rules/README.md +2 -1
  666. package/presets/cursor/svelte/rules/agent-team-orchestrator.mdc +2 -1
  667. package/presets/cursor/svelte/rules/anti-sycophancy-discipline.mdc +1 -1
  668. package/presets/cursor/svelte/rules/code-quality-and-refactoring.mdc +1 -1
  669. package/presets/cursor/svelte/rules/feature-delivery-workflow.mdc +2 -1
  670. package/presets/cursor/svelte/rules/mcp-usage.mdc +100 -0
  671. package/presets/cursor/svelte/rules/preset-no-cross-stack-leakage.mdc +1 -0
  672. package/presets/cursor/svelte/rules/product-specs-authoring.mdc +6 -4
  673. package/presets/cursor/svelte/rules/product-specs.mdc +8 -4
  674. package/presets/cursor/svelte/skills/README.md +2 -0
  675. package/presets/cursor/svelte/skills/ci-investigation/SKILL.md +8 -0
  676. package/presets/cursor/svelte/skills/code-review/SKILL.md +7 -1
  677. package/presets/cursor/svelte/skills/debug-investigation/SKILL.md +41 -12
  678. package/presets/cursor/svelte/skills/feature-delivery/SKILL.md +9 -1
  679. package/presets/cursor/svelte/skills/spec-discovery/SKILL.md +58 -0
  680. package/presets/cursor/svelte/team/README.md +11 -0
  681. package/presets/cursor/svelte/team/fixtures/feature-full.json +43 -9
  682. package/presets/cursor/svelte/team/fixtures/memlog.example.md +9 -0
  683. package/scripts/aggregate-agent-task-metrics.mjs +212 -0
  684. package/scripts/check-hook-only-lifecycle.sh +46 -0
  685. package/scripts/check-preset-i18n.sh +61 -0
  686. package/scripts/check-preset-leakage.sh +450 -0
  687. package/scripts/check-preset-structure.sh +70 -0
  688. package/scripts/check-preset-token-budget.sh +139 -0
  689. package/scripts/check-preset-twin-map.sh +122 -0
  690. package/scripts/check-product-specs.sh +90 -0
  691. package/scripts/check-rule-eval.mjs +149 -0
  692. package/scripts/check-shared-core-drift.sh +154 -0
  693. package/scripts/close-agent-task-human-gate.mjs +61 -0
  694. package/scripts/sync-dogfood-cursor.sh +70 -0
  695. package/scripts/sync-shared-core-embeds.sh +114 -0
  696. package/scripts/test-agent-task-metrics-hooks.mjs +895 -0
  697. package/scripts/test-cli-mcp-merge.mjs +137 -0
@@ -13,4 +13,25 @@ Browser e2e MCP (Playwright / Chrome DevTools) are **not** part of the go preset
13
13
 
14
14
  Do not put secrets in the file. Optional: `CONTEXT7_API_KEY` in the environment. Figma — OAuth (do not commit the token). Optional Figma MCP is design context only — **not** a mockup-review pipeline (this preset never schedules `mockup-reviewer`).
15
15
 
16
- After init: Settings → MCP → enable servers. `init` overwrites the same-named `mcp.json`.
16
+
17
+ ## Agent usage
18
+
19
+ Load requestable rule `mcp-usage`. The **session MCP catalog** is source of truth (this file and `mcp.json` are hints). Discover tool schemas before calling; never invent them.
20
+
21
+ **Context7 (shipped):** query docs when a third-party API is not confirmed by lockfile + sibling files. Use the installed major. Cap ≤3 doc queries per question. If Context7 is down, mark `// VERIFY` and continue — do not block.
22
+
23
+ ## Local overlay (not shipped)
24
+
25
+ `init` **merges** `mcpServers`: preset keys are updated; extra local servers are kept. User-level MCP is never touched. Prefer user-level MCP if you do not want overlay servers in the project file.
26
+
27
+ Use an overlay only when it is **ready** (`serverStatus` not `error` / `needsAuth` / `loading`) **and** the task fits. Absence is not a blocker unless the user required that MCP as source of truth.
28
+
29
+ | Kind | Typical aliases | When |
30
+ |------|-----------------|------|
31
+ | Observability | `sentry`, `datadog`, `plugin-datadog-*` | production error, event/trace id, APM |
32
+ | Tickets | `linear`, `jira`, `notion`, `plugin-notion-*` | ticket/page URL; read-only; task-folder artifacts remain SoT |
33
+ | GitHub MCP | `github` | optional; native `gh` remains SoT for PRs and checks |
34
+
35
+ Do **not** require Storybook, Playwright, or Chrome DevTools MCP as delivery gates on this preset.
36
+
37
+ Optional Figma on this preset is ad-hoc design context only — not a mockup-review pipeline.
@@ -17,6 +17,12 @@ You are the build verifier for **Go hexagonal** services (and for **ai-rules pre
17
17
 
18
18
  **Never** require Playwright, XCUITest, `lint:js`/`lint:css`, or `xcodebuild`/`SwiftLint` as the Go gate.
19
19
 
20
+ ## Verification before completion
21
+
22
+ <!-- shared-core: quality/verification-before-completion.md -->
23
+
24
+ Before writing `validation-report.md` or claiming PASS: IDENTIFY the commands, RUN them, READ exit codes, VERIFY they match the verdict, THEN claim. Do not mark PASS from memory of a prior developer run.
25
+
20
26
  ## Preset-structure validation (when editing `packages/ai-rules/presets/**`)
21
27
 
22
28
  From `packages/ai-rules/`:
@@ -16,6 +16,15 @@ Triage red CI for Go repos (and ai-rules preset-structure when relevant).
16
16
 
17
17
  - Never treat `lint:js` / Playwright / xcodebuild as the Go default gate.
18
18
 
19
+
20
+ ## MCP usage
21
+
22
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
23
+
24
+ If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
25
+
26
+
19
27
  ## Anti-sycophancy discipline
20
28
 
21
29
  - When writing or changing code, load / follow rule `anti-sycophancy-discipline`.
30
+ - When acting on review feedback (`changes_requested` / human comments): verify each item against the codebase before implementing; no performative agreement.
@@ -16,6 +16,8 @@ You are a senior Go hexagonal code reviewer. Write only review artifacts under `
16
16
 
17
17
  Apply skill `code-review` and `code-review-mr.mdc`. Weigh `architecture-boundaries.mdc`, `domain-layer.mdc`, `application-usecases.mdc`, `ports-interfaces.mdc`, `adapters-driving.mdc`, `adapters-driven.mdc`, `composition-root.mdc`, `go-conventions.mdc`, `tests-unit.mdc`, `tests-integration.mdc`, `security-go.mdc`.
18
18
 
19
+ You **issue** reviews. Implementers acting on your findings must verify each item against the codebase and must not perform agreement. Do not require gratitude in replies.
20
+
19
21
  ## Review focus (Go hexagonal)
20
22
 
21
23
  - If the MR touches `docs/specs/**`, load **`product-specs`** (+ **`product-specs-authoring`** when new/changed specs): **WARN** code/spec drift; **FAIL** broken INDEX `path` link or missing required frontmatter keys/arrays on touched spec files; required body headings missing → **FAIL** on touched files. Do not invent missing product behavior.
@@ -6,6 +6,8 @@ readonly: false
6
6
 
7
7
  Investigate with **runtime evidence**: failing `go test` output, logs, stack traces, minimal repro.
8
8
 
9
+ Use the **`debug-investigation` skill** for the investigation loop.
10
+
9
11
  ## Approach
10
12
 
11
13
  1. Reproduce with `go test` / focused package tests.
@@ -20,6 +22,18 @@ Investigate with **runtime evidence**: failing `go test` output, logs, stack tra
20
22
 
21
23
  Write `.cursor/team/tasks/<slug>/debug-report.md`.
22
24
 
25
+
26
+ ## 3-fix architecture gate
27
+
28
+ After **three** unsuccessful fix attempts (or the same symptom returning twice): STOP. Do not attempt fix #4. Escalate architecture with the human or `solution-architect`. Follow skill `debug-investigation`. Before `fixApplied: true`, re-run the failing check.
29
+
30
+ ## MCP usage
31
+
32
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
33
+
34
+ If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
35
+
36
+
23
37
  ## Design guidance
24
38
 
25
39
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
@@ -27,3 +41,4 @@ Write `.cursor/team/tasks/<slug>/debug-report.md`.
27
41
  ## Anti-sycophancy discipline
28
42
 
29
43
  - When writing or changing code, load / follow rule `anti-sycophancy-discipline`.
44
+ - When acting on review feedback (`changes_requested` / human comments): verify each item against the codebase before implementing; no performative agreement.
@@ -45,6 +45,13 @@ Update `.cursor/team/tasks/<slug>/implementation.md` and the owned implementatio
45
45
  ## Anti-sycophancy discipline
46
46
 
47
47
  - When writing or changing code, load / follow rule `anti-sycophancy-discipline`.
48
+ - When acting on review feedback (`changes_requested` / human comments): verify each item against the codebase before implementing; no performative agreement.
49
+
50
+ ## Verification before completion
51
+
52
+ <!-- shared-core: quality/verification-before-completion.md -->
53
+
54
+ Before handoff, IDENTIFY→RUN→READ→VERIFY the scoped checks for this WP, THEN claim. Do not say the work is done without that evidence in the same turn. Full-project lint is `build-verifier`.
48
55
 
49
56
  ## Product specs (docs/specs)
50
57
 
@@ -53,6 +60,29 @@ When work touches a page/feature/route/alias: if `docs/specs/INDEX.md` exists (o
53
60
  Mechanical INDEX/frontmatter fixes only when implementation renames routes/ids. Substantive behavior edits → hand back to task-analyst (or tech-writer where present). If INDEX is absent and generation was not approved, treat specs as optional (greenfield).
54
61
 
55
62
 
63
+ **specMode `none`:** do not require INDEX; implement from brief/AC only.
64
+
65
+ **applyReadiness:** YAML frontmatter on `implementation.md`:
66
+
67
+ ```yaml
68
+ applyReadiness:
69
+ state: ready # blocked | ready | all_done
70
+ contextFiles: []
71
+ ```
72
+
73
+ `blocked` if human gate pending, required spec missing, required UX `INCOMPLETE`, or incomplete WP deps. `ready` when the current WP may be implemented. `all_done` on the final receipt when mechanical spec sync is done.
74
+
75
+ **Code Map + Suggested Review Order:** when this WP spans **>1 layer or module**, add to `implementation.md` a Code Map (3–8 annotated paths) and Suggested Review Order lines `concern | path:line | ≤15 words`. Omit for single-file / single-layer WPs.
76
+
77
+ **Memlog:** append implementation decisions to `.cursor/team/tasks/<slug>/.memlog.md` (append-only).
78
+
79
+
80
+
81
+ ## MCP usage
82
+
83
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
84
+
85
+
56
86
  ## Artifact contract
57
87
 
58
88
  - **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume handoff `artifactInputIds` when supplied, otherwise consume the manifest entries for `brief.md`, `decomposition.md`, current scope, and applicable prior findings.
@@ -26,6 +26,12 @@ Write `.cursor/team/tasks/<slug>/migration-plan.md`:
26
26
  - Do not invent a new HTTP framework mid-migration without AC.
27
27
  - Handoff to feature-developer for execution after human gate when required.
28
28
 
29
+
30
+ ## MCP usage
31
+
32
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
33
+
34
+
29
35
  ## Design guidance
30
36
 
31
37
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
@@ -17,6 +17,12 @@ Audit Go performance risks on the task scope.
17
17
 
18
18
  `.cursor/team/tasks/<slug>/perf-report.md`. No production edits. Not Instruments/Xcode.
19
19
 
20
+
21
+ ## MCP usage
22
+
23
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
24
+
25
+
20
26
  ## Design guidance
21
27
 
22
28
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
@@ -23,6 +23,12 @@ Design solutions for **Go hexagonal** services.
23
23
  - Do not invent Next/iOS layer names.
24
24
  - No production code.
25
25
 
26
+
27
+ ## MCP usage
28
+
29
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
30
+
31
+
26
32
  ## Design guidance
27
33
 
28
34
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
@@ -7,6 +7,16 @@ model: fast
7
7
 
8
8
  Analyze and decompose work for **Go hexagonal** backends.
9
9
 
10
+ ## Classify first
11
+
12
+ <!-- shared-core: agent-team/task-classification.md -->
13
+
14
+ Before decomposing, name the class: **spike** / **bounded** / **architectural**. Maps to existing pipeline profiles — do not invent a second orchestrator.
15
+
16
+ - **Spike** — research DoR; no implement tasks.
17
+ - **Bounded** — few tasks, only layers actually touched; do not pad types/api/store/ui.
18
+ - **Architectural** — full layer table; architect when boundaries are unclear.
19
+
10
20
  ## Deliverables
11
21
 
12
22
  - `brief.md` — goals, non-goals, AC, open questions
@@ -30,6 +40,15 @@ Emit an analysis receipt; the runtime applies any configured human gate.
30
40
 
31
41
  **Author mode (Generate / Bootstrap):** When the user runs `/spec-start`, router intent is `spec-gen` / bootstrap, or brief/AC requests generation: load **`product-specs`** + **`product-specs-authoring`** and skill **`spec-authoring`**. You are the **primary author** (INDEX bootstrap included). Follow frontmatter v1 + required headings; update INDEX in the **same change set**; default `status: draft`. Block handoff via `open_questions` until the authoring self-check passes.
32
42
 
43
+
44
+ **Spec mode:** Write `## Spec mode` in `brief.md` with exactly one of `consume` | `generate` | `none`. Infer if unset: spike/research/preset-only → `none`; `/spec-start` or router `spec-gen` → `generate`; otherwise `consume`. Router may echo `specMode` on `pipeline.json`.
45
+
46
+ **`none`:** skip INDEX row requirement and author mode; do not invent a dummy INDEX.
47
+
48
+ **Research-before-spec (opt-in):** load skill **`spec-discovery`** only when the user/AC asks research before authoring (not default consume `/task`). Run a **subset** of methods; **`claim-ledger` is mandatory** whenever the skill loads. Append chronological notes to `.cursor/team/tasks/<slug>/.memlog.md` (append-only; do not mutate `status.json`).
49
+
50
+ **applyReadiness (author blocked):** if specs are drafted but the human gate has not passed, or a required named spec is missing, emit `applyReadiness: { "state": "blocked", "contextFiles": ["…"] }` on the analysis receipt. Do not invoke feature-developer.
51
+
33
52
  ### Brief sections (when author mode or INDEX exists)
34
53
 
35
54
  Add to `brief.md`:
@@ -43,6 +62,14 @@ Add to `brief.md`:
43
62
  ```
44
63
 
45
64
 
65
+
66
+ ## MCP usage
67
+
68
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
69
+
70
+ If the prompt/brief has a tracker URL (Linear/Jira/Notion/…) and that MCP is ready, pull AC **read-only**. Task-folder artifacts remain SoT.
71
+
72
+
46
73
  ## Artifact contract
47
74
 
48
75
  - **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume `pipeline.json`, the manifest routing entry, user-approved decisions, and any authoritative architecture/approval entries.
@@ -39,6 +39,20 @@ You are a task router for a **Go hexagonal backend** agent team. You **do not**
39
39
 
40
40
  **Never skip `build-verifier`** after developer when Go sources changed.
41
41
 
42
+ ## Task class (spike / bounded / architectural)
43
+
44
+ <!-- shared-core: agent-team/task-classification.md -->
45
+
46
+ Name the class in `routingReasons`. Maps to profiles already in this file — do not add a parallel step table.
47
+
48
+ | Class | Use existing |
49
+ |-------|----------------|
50
+ | Spike | intent `spike` |
51
+ | Bounded | `profile: light` (or skip analyst when AC is complete) |
52
+ | Architectural | `profile: full` + `solution-architect` when boundaries unclear |
53
+
54
+ SoT: `agent-team/task-classification` (shared-core marker above; do not invent a second pipeline).
55
+
42
56
  ## Routing decision rubric
43
57
 
44
58
  Keep top-level `profile` and emit this top-level object in every new `pipeline.json`:
@@ -75,6 +89,7 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
75
89
  | Intent | Default humanGates |
76
90
  |--------|-------------------|
77
91
  | feature, refactor, test-only | `["after:task-analyst"]` |
92
+ | spec-gen | `["after:task-analyst"]` |
78
93
  | migration | `["after:migration-specialist"]` |
79
94
  | unit-only | `["after:unit-test-planner"]` when new plan |
80
95
  | e2e-only / integration | `["after:integration-test-planner"]` when new plan |
@@ -100,6 +115,11 @@ Detect and set routing reasons when the user asks to **generate / bootstrap prod
100
115
 
101
116
  Do **not** add a dedicated `spec-author` agent. Do not require solution-architect for routine spec authoring.
102
117
 
118
+
119
+ **specMode (optional `pipeline.json` field):** `none` for spike/research; `generate` for `spec-gen` / `/spec-start`; `consume` default when INDEX exists. Echo top-level `specMode`. Brief `## Spec mode` wins on conflict.
120
+
121
+ Do **not** add a pipeline step for `spec-discovery`. Instruct analyst to load that skill only when the user/AC asks research-before-spec.
122
+
103
123
  ## Runtime initialization
104
124
 
105
125
  Return the routing receipt to the orchestrator. The orchestration runtime/hook exclusively initializes and updates `status.json`, `metrics.json`, attempt identities, and gate lifecycle; the router does not write those shared runtime files.
@@ -14,7 +14,7 @@ Routes intent **`spec-gen`** (or bootstrap) → **task-analyst** in **author mod
14
14
  3. Ensure `.cursor/team/tasks/<slug>/` exists (Write artifacts; not Shell mkdir).
15
15
  4. Write `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`.
16
16
  5. Write minimal `pipeline.json`: task-analyst → (optional stop) → feature-developer only if user asked implement-after. **No separate spec-author agent.**
17
- 6. Invoke **task-analyst** with: author mode; load **`product-specs`** + **`product-specs-authoring`** + skill **`spec-authoring`**; Bootstrap if `docs/specs/` absent, else Generate.
17
+ 6. Invoke **task-analyst** with: author mode; load **`product-specs`** + **`product-specs-authoring`** + skill **`spec-authoring`**; Bootstrap if `docs/specs/` absent, else Generate. Optional: if arguments/AC ask research-before-spec, also load skill **`spec-discovery`** (not default).
18
18
  7. Wait for analyst. **Do not** invoke feature-developer until human gate passes.
19
19
 
20
20
  ## Human gate
@@ -2,7 +2,7 @@
2
2
  "mcpServers": {
3
3
  "context7": {
4
4
  "command": "npx",
5
- "args": ["-y", "@upstash/context7-mcp"]
5
+ "args": ["-y", "@upstash/context7-mcp@4.0.2"]
6
6
  },
7
7
  "figma": {
8
8
  "url": "https://mcp.figma.com/mcp"
@@ -19,7 +19,7 @@
19
19
  ## Loading strategy
20
20
 
21
21
  - **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — base invariants only (**3**): `go-app-core`, `architecture-boundaries`, `code-quality-and-refactoring`
22
- - **On-demand / requestable** — `post-change-test`, `go-tooling`, `agent-team-intake`, `agent-team-orchestrator`, hexagonal domain/adapters, tests, feature-delivery-workflow, reference-features, product-specs, product-specs-authoring, `design-guidance`, `anti-sycophancy-discipline`, `technical-retro`
22
+ - **On-demand / requestable** — `post-change-test`, `go-tooling`, `agent-team-intake`, `agent-team-orchestrator`, hexagonal domain/adapters, tests, feature-delivery-workflow, reference-features, product-specs, product-specs-authoring, `design-guidance`, `mcp-usage`, `anti-sycophancy-discipline`, `technical-retro`
23
23
  - **Preset author meta** (globs `packages/ai-rules/presets/**`, never alwaysApply): `preset-layering`, `preset-twin-sync`, `preset-token-budget`, `preset-pr-checklist`, `preset-no-cross-stack-leakage`
24
24
  - **Skills** — long procedures (`feature-delivery`, `code-review`, `integration-testing`, …)
25
25
 
@@ -43,6 +43,7 @@ SoT prose: `packages/ai-rules/presets/_shared/core/**` (see `_shared/README.md`)
43
43
  | `quality/code-quality-and-refactoring.md` | `code-quality-and-refactoring.mdc` | embed | Stack notes: Go errors/`%w`, ports, `post-change-test` |
44
44
  | `quality/anti-sycophancy-discipline.md` | `anti-sycophancy-discipline.mdc` | embed | requestable full VERIFY/discipline set |
45
45
  | `quality/design-guidance.md` | `design-guidance.mdc` | embed | requestable smells/GoF |
46
+ | `quality/mcp-usage.md` | `mcp-usage.mdc` | embed | requestable Context7 + overlay MCP |
46
47
  | `agent-team/agent-team-orchestrator.md` | `agent-team-orchestrator.mdc` | lineage | Roles (`integration-test-*`); preset PR pointer |
47
48
  | `agent-team/agent-team-intake.md` | `agent-team-intake.mdc` | embed | thin alias |
48
49
  | `architecture/feature-delivery-workflow.md` | `feature-delivery-workflow.mdc` | lineage | Go hexagonal checklist (stack-native body; core = abstract SoT) |
@@ -19,6 +19,7 @@ Work request without `/task` — see **agent-team-intake** (when to suggest the
19
19
  | `/task-continue <slug>` | After human gate or pause |
20
20
  | `/feature-start <desc>` | Legacy: analyst-only start (no router) |
21
21
  | `/feature-continue <slug>` | Alias of task-continue |
22
+ | `/spec-start [desc]` | Generate/bootstrap `docs/specs` — router intent `spec-gen` → analyst author mode → human gate |
22
23
  | `/technical-retro [slug]` | Retro with agent team block |
23
24
 
24
25
  ## Roles (shared catalog)
@@ -11,7 +11,7 @@ alwaysApply: false
11
11
 
12
12
  Procedural rules for code generation and review. Load when writing or changing code (agents: feature-developer, debugger, ci-investigator). Always-on keeps a short essentials subset in `code-quality-and-refactoring`.
13
13
 
14
- 1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If you cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
14
+ 1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If that is not enough and Context7 MCP is available, load **`mcp-usage`** and query docs for the **installed major**. If you still cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
15
15
  2. **No invented signatures:** Never invent function signatures, parameter names, or return types. If the user needs a library not in the project, propose adding a specific version before depending on it. Silent stubs are worse than refusal.
16
16
  3. **Enumerate edge cases before validating:** When asked "is this correct?" or "does this work?", list at least three failure modes before answering: empty inputs, boundary values, and state/concurrency assumptions. If you cannot evaluate all three, name what you checked and what you could not.
17
17
  4. **Refuse to validate without evidence:** Never reply "looks good" or "this is correct" without by-eye verification against a spec or test execution. If no spec exists, ask for one or refuse to validate.
@@ -33,7 +33,7 @@ alwaysApply: true
33
33
 
34
34
  Essentials below. Full procedural set (~17 rules) → load **`anti-sycophancy-discipline`**.
35
35
 
36
- - Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
36
+ - Unverifiable third-party API → if Context7 is up, load **`mcp-usage`** and query the installed major; else mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
37
37
  - Before "is this correct?" — ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
38
38
  - Refactor without tests → propose characterization test; if declined, label `UNTESTED`.
39
39
  - Comments = WHY only when non-obvious; ban self-referential "added for issue Y".
@@ -15,7 +15,7 @@ Order of work:
15
15
  4. **Driving adapters** — HTTP/gRPC/CLI mapping DTOs.
16
16
  5. **Composition root** — wire in `cmd/` / `internal/app`.
17
17
  6. **Tests** — unit (domain/app) → integration (adapters) → optional e2e smoke.
18
- 7. **Gate** — `post-change-test` (+ `go-tooling`).
18
+ 7. **Gate** — `post-change-test` (+ `go-tooling`). When the current WP spans **more than one** layer or module, `implementation.md` includes a **Code Map** (3–8 annotated paths) and **Suggested Review Order** (`concern | path:line | ≤15 word note`). Omit both for a single-file or single-layer WP.
19
19
 
20
20
  ```mermaid
21
21
  flowchart LR
@@ -44,6 +44,7 @@ flowchart LR
44
44
  - Framework types in domain; SQL in use cases; DI inside handlers; skipping port interfaces “for speed”.
45
45
  - **Ubiquitous language:** Domain names/boundaries reflect the feature domain — do not mix transport/framework terms into domain without need.
46
46
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
47
+ - Do not mutate pipeline `status.json` / `metrics.json`; the orchestration hook is the single writer. Skills upsert the owned terminal receipt in `artifact-manifest.json`.
47
48
 
48
49
  ## Related
49
50
 
@@ -0,0 +1,98 @@
1
+ ---
2
+ description: When to call shipped Context7 and local overlay MCP — detect presence, use if the task fits, degrade.
3
+ alwaysApply: false
4
+ ---
5
+
6
+ <!-- shared-core: quality/mcp-usage.md -->
7
+
8
+ # MCP usage
9
+
10
+ Requestable protocol for **shipped** and **local-overlay** MCP servers. Agents load this stem via one-liner wiring — do not copy tool schemas into prompts; discover them at runtime.
11
+
12
+ Does not replace Figma mockup-review (that checklist stays on `mockup-review`). Does not add pipeline agents or required handoff stems.
13
+
14
+ ## Presence (runtime catalog is SoT)
15
+
16
+ 1. Inspect the **session MCP catalog** (server names + `serverStatus`). Project `mcp.json` / `.mcp.json` is a hint, not proof the server is up (user-level and plugin servers never appear there).
17
+ 2. Treat `error`, `needsAuth`, and `loading` as **unavailable**. Authenticate only when this task needs that server.
18
+ 3. **Discover tool schemas before calling.** Never invent tool names or arguments from memory.
19
+ 4. Match overlay servers by **documented aliases** or exact catalog ids. Prefer a ready `plugin-*` id over an unknown similarly named server; if several match, ask rather than guessing.
20
+ 5. If two servers expose the same product (plugin + project entry), use the **ready** one; do not call both.
21
+
22
+ ## Classes
23
+
24
+ | Class | Who adds it | Policy |
25
+ |-------|-------------|--------|
26
+ | **Shipped** | Preset `mcp.json` | Assume it should be there; call when the task fits; degrade if down (do not block unless noted below) |
27
+ | **Local overlay** | Consumer project or user MCP | Use only when present **and** the task fits. Never a required pipeline step |
28
+
29
+ Shipped in every preset: **Context7** (library docs). Other shipped servers are stack-specific — see adapter **Stack notes**.
30
+
31
+ ## Context7 (shipped)
32
+
33
+ **When to call** (after lockfile / manifest + sibling files still do not confirm the symbol):
34
+
35
+ - Third-party API that would otherwise get `// VERIFY: lib.symbol @ version`
36
+ - Version-sensitive framework or SDK APIs
37
+ - Migrations / major upgrades
38
+ - Library is in the lockfile but the signature is unclear
39
+
40
+ **When not to call:** repo public API; a sibling file already imports the symbol; a trivial call already in this module.
41
+
42
+ **Flow:**
43
+
44
+ 1. Discover server `context7`.
45
+ 2. Resolve a library id, then query docs (read the live schema; typical names `resolve-library-id` then `query-docs`).
46
+ 3. Put the **installed major** from the project manifest into the query.
47
+ 4. Cap: **≤3 doc queries per question**.
48
+ 5. Source priority: lockfile / sibling code **>** Context7 **>** training data. If docs disagree with the installed major, keep the installed API.
49
+ 6. If Context7 is down: `// VERIFY` (or stack equivalent) and say MCP was unavailable. **Do not block** the task.
50
+
51
+ ## Local overlay protocol
52
+
53
+ If a matching server is ready and a **task signal** fires → discover and use. Otherwise continue from files / native tools (`gh`, repo docs, source).
54
+
55
+ Absence of an overlay is **not** `BLOCKED` unless the user required that MCP as source of truth.
56
+
57
+ ### Observability (Sentry, Datadog, similar)
58
+
59
+ **Signal:** production error, event/trace id, APM / latency, pasted dashboard or issue URL.
60
+
61
+ Use the **first ready** observability MCP. Do not invent metrics or stack traces. Do not require two observability servers.
62
+
63
+ ### Tickets (Linear, Jira, Notion, similar)
64
+
65
+ **Signal:** ticket/page URL in the prompt or brief, or an explicit “pull from \<tracker\>”.
66
+
67
+ Read-only by default. Task-folder artifacts (`brief.md`, `decomposition.md`) remain SoT — do not replace them with a tracker page. Write back to the tracker **only** if the user asked.
68
+
69
+ ### Component-library overlay
70
+
71
+ **Signal:** UI component public API, stories, controls, or explicit component-docs MCP.
72
+
73
+ If such a server is ready, use it for documented props/variants instead of inventing them. If it is down, read story/source files. **Block** only when the user required that MCP as SoT.
74
+
75
+ Usual aliases and runtime needs live in frontend **Stack notes**. Do not ship this server in preset `mcp.json`.
76
+
77
+ ### GitHub MCP
78
+
79
+ Native `gh` / git remain SoT for PRs and checks. A GitHub MCP may be used when present; do not require it.
80
+
81
+ ## Figma
82
+
83
+ Policy is stack-class-specific — see adapter **Stack notes**. If a Figma **plugin** and a project `figma` server are both present, use the ready one and do not duplicate calls.
84
+
85
+ ## Forbidden
86
+
87
+ - Secrets in `mcp.json` / `.mcp.json`
88
+ - New pipeline agents or required handoffs for overlay MCP
89
+ - Treating overlay absence as blocked (except user-required SoT)
90
+ - Tracker/admin write tools without an explicit ask
91
+ - Calling overlay MCP “just in case” on unrelated tasks
92
+
93
+ ## Stack notes
94
+
95
+ - Shipped besides Context7: optional Figma for ad-hoc design context — **not** a mockup-review pipeline (this preset never schedules `mockup-reviewer`).
96
+ - Do **not** require Storybook, Playwright, or Chrome DevTools MCP.
97
+ - Observability and ticket overlays still apply when present.
98
+ - `init` **merges** `mcpServers`: preset keys update; extra local servers are kept.
@@ -23,6 +23,7 @@ Ban leakage of stack-specific names, paths, and handoff stems across presets.
23
23
  - `go` / `java` / `php-hexagonal` / `php-laravel` / `mcp-ts` must not ship Playwright, XCUITest, Android instrumentation agents, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
24
24
  - `mcp-ts` must not ship Go tool commands (`go test`, `go vet`, `golangci-lint`) or `integration-test-*` agents as required delivery gates.
25
25
  - Shared core must not embed stack paths (`app/src/**`, `Features/**`, `playwright`, `xcodebuild`).
26
+ - Storybook / Chrome DevTools MCP must **not** be required handoffs or agent stems (`storybook-reviewer`) on backend or mobile stacks. Frontend overlay mentions in `MCP.md` / `mcp-usage` Stack notes are OK.
26
27
 
27
28
  ## Forbidden in ios-swift hooks/agents (FAIL)
28
29
 
@@ -11,6 +11,8 @@ alwaysApply: false
11
11
 
12
12
  Load when **Generate** or **Bootstrap** is requested (`/spec-start`, router `spec-gen`, brief AC, or analyst author mode). Discovery-only work stays on **`product-specs`**.
13
13
 
14
+ **Optional prefix:** when the user or AC asks **research-before-spec**, load skill **`spec-discovery`** first (subset of methods; **claim-ledger** mandatory). Not the default `/task` consume path and not a new pipeline step.
15
+
14
16
  ## Modes
15
17
 
16
18
  1. **Consume** — default; never invent INDEX/specs (see `product-specs`).
@@ -84,7 +86,7 @@ Compliant = valid frontmatter + all required headings present (non-empty prose o
84
86
 
85
87
  ## Templates & assets
86
88
 
87
- **Package SoT:** `packages/ai-rules/presets/_shared/assets/docs-specs/` (`INDEX.md` stub, `_templates/page.md`, `_templates/feature.md`; optional `schemas/frontmatter-v1.schema.json`).
89
+ **Package SoT:** `packages/ai-rules/presets/_shared/assets/docs-specs/` (`INDEX.md` stub, `_templates/page.md`, `_templates/feature.md`; `schemas/frontmatter-v1.schema.json` is a documentation artifact — the checker does not evaluate it).
88
90
 
89
91
  **CLI `init`:** when consumer `docs/specs/` is **absent**, copy INDEX stub + `_templates/*` (idempotent; **never overwrite** existing INDEX). When the tree already exists, skip seed entirely.
90
92
 
@@ -94,7 +96,7 @@ Compliant = valid frontmatter + all required headings present (non-empty prose o
94
96
 
95
97
  | Role | Responsibility |
96
98
  |------|----------------|
97
- | **task-analyst** | Primary author (Generate + Bootstrap); INDEX bootstrap; brief **Related specs** + **Spec gaps / generation requested**; loads this stem + skill `spec-authoring` |
99
+ | **task-analyst** | Primary author (Generate + Bootstrap); INDEX bootstrap; brief **Related specs** + **Spec gaps / generation requested**; loads this stem + skill `spec-authoring`; optional skill `spec-discovery` when research-before-spec |
98
100
  | **tech-writer** | Post-delivery sync where present; never invent product behavior without AC/code source |
99
101
  | **feature-developer** | Consumes approved specs as SoT; mechanical INDEX/frontmatter fixes only on renames |
100
102
  | **mcp-ts** | No tech-writer — author + post-sync via **task-analyst** only |
@@ -113,8 +115,8 @@ Block handoff via `open_questions` until fixed:
113
115
 
114
116
  - `product-specs` — discovery / consume
115
117
  - Skill `spec-authoring` — procedural checklist
116
- - Optional consumer script `scripts/check-product-specs.sh` (WARN default; `--strict` FAIL)
117
-
118
+ - Skill `spec-discovery` opt-in research-before-spec (not default)
119
+ - Optional consumer script `scripts/check-product-specs.sh` (ships in the npm package; WARN default; `--strict` FAIL). Bash checks INDEX links, required frontmatter keys, and body headings — it does **not** evaluate `frontmatter-v1.schema.json`
118
120
 
119
121
  ## Stack notes
120
122
 
@@ -13,6 +13,8 @@ Product page/feature **behavior** specs live under the consumer repo `docs/specs
13
13
 
14
14
  **Authoring** (Generate / Bootstrap modes, INDEX/frontmatter v1, body checklist, greenfield, conflict precedence) → load **`product-specs-authoring`** when generation is requested (`/spec-start`, brief AC, or router `spec-gen`).
15
15
 
16
+ **Pipeline `specMode`:** `consume` (this stem) · `generate` (authoring stem) · `none` (spike/research — skip INDEX row requirement; do not invent a dummy INDEX). Primary field: `brief.md` `## Spec mode`; optional `pipeline.json` `specMode`.
17
+
16
18
  ## Modes (summary)
17
19
 
18
20
  | Mode | When | Behavior |
@@ -20,19 +22,21 @@ Product page/feature **behavior** specs live under the consumer repo `docs/specs
20
22
  | **Consume** (default) | INDEX exists or globs hit `docs/specs/**` without generate intent | Discover via INDEX; soft-fail on miss; **never invent** INDEX/specs |
21
23
  | **Generate** | Explicit generate intent / AC / `/spec-start` with existing tree | Create/update page/feature specs + INDEX from stated sources |
22
24
  | **Bootstrap** | Explicit bootstrap / `/spec-start` when tree absent | Create INDEX + templates + first domain spec |
25
+ | **None** (`specMode: none`) | Spike / research / preset-only | Skip INDEX requirement and author mode; no dummy INDEX row |
23
26
 
24
27
  Greenfield: agents may create INDEX/specs **only** on explicit intent, AC, or `/spec-start`. Missing INDEX alone does **not** authorize inventing the tree.
25
28
 
26
29
  ## Presence policy
27
30
 
31
+ - If `specMode` is **`none`** → do **not** require an INDEX row; continue from brief/AC. Do not invent INDEX.
28
32
  - If `docs/specs/INDEX.md` is **missing** → the tree is **optional** (greenfield OK for *consume*). Continue with code/brief discovery; do not invent an INDEX solely because this stem loaded.
29
- - If INDEX **exists** → it is the **required discovery path** for work that touches a listed page, feature, route, or alias.
33
+ - If INDEX **exists** and `specMode` is not `none` → it is the **required discovery path** for work that touches a listed page, feature, route, or alias.
30
34
 
31
35
  ## Discovery algorithm
32
36
 
33
- 1. Always start at `docs/specs/INDEX.md` when present.
37
+ 1. Always start at `docs/specs/INDEX.md` when present (skip when `specMode: none`).
34
38
  2. Resolve the entry by: route, stable `id`, PageName / alias, or domain folder.
35
- 3. Read the linked page spec (and optional domain `feature.md` when the INDEX or page Related links it).
39
+ 3. Read the **linked page** spec and, when INDEX or page Related links it, the optional domain `feature.md`. Do **not** dump the whole `docs/specs/**` tree into the prompt locator = those linked files.
36
40
 
37
41
  ## Miss policy (INDEX present, row or file missing)
38
42
 
@@ -54,10 +58,10 @@ Same-changeset INDEX updates, frontmatter v1, required body headings, templates,
54
58
  ## Related
55
59
 
56
60
  - `product-specs-authoring` — generation modes, contracts, self-check.
61
+ - Skill `spec-discovery` — opt-in research-before-spec (author mode only; not default consume).
57
62
  - `reference-features` — code structure mirror (how to layout files), not product behavior.
58
63
  - Consumer `.ai/context/**` when present — review/domain glossary; cross-link, do not replace.
59
64
 
60
-
61
65
  ## Stack notes
62
66
 
63
67
  - `routes`: HTTP paths. `ui` / `store`: usually `[]` (or handler labels). `e2e`: integration/contract test paths.
@@ -1,5 +1,5 @@
1
1
  # Skills (preset go)
2
2
 
3
- 8 skills: `feature-delivery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`, `write-adr`.
3
+ 10 skills: `feature-delivery`, `spec-authoring`, `spec-discovery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`, `write-adr`.
4
4
 
5
5
  No `playwright-e2e` / `xcuitest-e2e` / `react-performance`.
@@ -9,3 +9,10 @@ description: Investigates failing CI checks on PRs and branches — go test, vet
9
9
  2. Reproduce locally with the same commands.
10
10
  3. Minimal fix; for ai-rules preset PRs run `yarn check:preset-structure`.
11
11
  4. Do not treat Playwright/xcodebuild/`lint:js` as default Go gates.
12
+
13
+ ## MCP usage
14
+
15
+ Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
16
+
17
+ If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
18
+
@@ -20,6 +20,13 @@ description: Reviews pull requests and branch diffs for Go hexagonal services us
20
20
 
21
21
  Never require iOS/Next-only gates (XCUITest, Playwright, `lint:js`).
22
22
 
23
+ ## Receiving review feedback
24
+
25
+ <!-- shared-core: review/receiving-code-review.md -->
26
+
27
+ When **implementing** review comments (not when issuing them): verify each item against the codebase before changing code; do not perform agreement (`You're absolutely right!`). Unclear items → ask, do not guess.
28
+
23
29
  ## Design guidance
24
30
 
25
31
  - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
32
+ For agent team tasks, write the review artifact and upsert the owned terminal receipt (`completed` or `changes_requested`); do not mutate `status.json`.