@cbartens/bkit 5.5.1 → 6.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (425) hide show
  1. package/.bkit/README.md +167 -154
  2. package/.bkit/core/.agents/context.md +95 -29
  3. package/.bkit/core/.agents/docs.md +18 -15
  4. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-gateguard.cjs +1 -0
  5. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +6 -5
  6. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-readguard.cjs +1 -0
  7. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-rules.cjs +65 -0
  8. package/.bkit/core/.agents/rules.md +112 -102
  9. package/.bkit/core/.agents/skills.md +63 -15
  10. package/.bkit/core/.bkit/README.md +167 -154
  11. package/.bkit/core/.bkit/authoring.md +747 -0
  12. package/.bkit/core/.bkit/cli.md +407 -0
  13. package/.bkit/core/.bkit/cloud.md +283 -195
  14. package/.bkit/core/.bkit/comparison.md +45 -43
  15. package/.bkit/core/.bkit/install.md +166 -95
  16. package/.bkit/core/.bkit/jsonl.md +339 -196
  17. package/.bkit/core/.bkit/pipeline.md +142 -145
  18. package/.bkit/core/.bkit/prompts.md +295 -264
  19. package/.bkit/core/.bkit/providers.md +460 -277
  20. package/.bkit/core/.bkit/router.md +69 -0
  21. package/.bkit/core/.bkit/templates.md +530 -256
  22. package/.bkit/core/.bkit/trackers.md +116 -65
  23. package/.bkit/core/.bkit/workflows.md +742 -618
  24. package/.bkit/core/.claude/hooks/bkit-gateguard.cjs +2 -2
  25. package/.bkit/core/.claude/hooks/bkit-guardrails.cjs +3 -3
  26. package/.bkit/core/.claude/hooks/bkit-preflight.sh +45 -14
  27. package/.bkit/core/.codex/hooks/bkit-guardrails.cjs +3 -3
  28. package/.bkit/core/.codex/hooks/bkit-rules.cjs +57 -0
  29. package/.bkit/core/.cursor/hooks/bkit-guardrails.cjs +7 -7
  30. package/.bkit/core/.cursor/hooks/bkit-preflight.sh +47 -12
  31. package/.bkit/core/.opencode/plugin/bkit-rules.js +89 -0
  32. package/.bkit/core/AGENTS.md +6 -80
  33. package/.bkit/core/docs/templates/bkit-audit-accessibility.md +128 -130
  34. package/.bkit/core/docs/templates/bkit-audit-adoption.md +104 -94
  35. package/.bkit/core/docs/templates/bkit-audit-agents.md +96 -98
  36. package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +100 -103
  37. package/.bkit/core/docs/templates/bkit-audit-analytics.md +141 -107
  38. package/.bkit/core/docs/templates/bkit-audit-annotations.md +99 -97
  39. package/.bkit/core/docs/templates/bkit-audit-app-performance.md +122 -121
  40. package/.bkit/core/docs/templates/bkit-audit-app-store.md +158 -101
  41. package/.bkit/core/docs/templates/bkit-audit-architecture.md +114 -96
  42. package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +76 -97
  43. package/.bkit/core/docs/templates/bkit-audit-config.md +123 -101
  44. package/.bkit/core/docs/templates/bkit-audit-cost.md +86 -99
  45. package/.bkit/core/docs/templates/bkit-audit-coverage.md +76 -93
  46. package/.bkit/core/docs/templates/bkit-audit-database.md +102 -95
  47. package/.bkit/core/docs/templates/bkit-audit-dead-code.md +165 -108
  48. package/.bkit/core/docs/templates/bkit-audit-deferrals.md +115 -109
  49. package/.bkit/core/docs/templates/bkit-audit-dependencies.md +265 -113
  50. package/.bkit/core/docs/templates/bkit-audit-documentation.md +119 -118
  51. package/.bkit/core/docs/templates/bkit-audit-duplication.md +140 -111
  52. package/.bkit/core/docs/templates/bkit-audit-failures.md +111 -106
  53. package/.bkit/core/docs/templates/bkit-audit-flakes.md +100 -99
  54. package/.bkit/core/docs/templates/bkit-audit-gates.md +107 -103
  55. package/.bkit/core/docs/templates/bkit-audit-issues.md +105 -105
  56. package/.bkit/core/docs/templates/bkit-audit-llm.md +134 -85
  57. package/.bkit/core/docs/templates/bkit-audit-logs.md +124 -125
  58. package/.bkit/core/docs/templates/bkit-audit-models.md +99 -78
  59. package/.bkit/core/docs/templates/bkit-audit-privacy.md +56 -76
  60. package/.bkit/core/docs/templates/bkit-audit-prompts.md +63 -78
  61. package/.bkit/core/docs/templates/bkit-audit-red-team.md +125 -93
  62. package/.bkit/core/docs/templates/bkit-audit-reliability.md +97 -96
  63. package/.bkit/core/docs/templates/bkit-audit-repo.md +170 -98
  64. package/.bkit/core/docs/templates/bkit-audit-security.md +207 -121
  65. package/.bkit/core/docs/templates/bkit-audit-slop.md +78 -95
  66. package/.bkit/core/docs/templates/bkit-audit-testing.md +163 -139
  67. package/.bkit/core/docs/templates/bkit-audit-usability.md +114 -96
  68. package/.bkit/core/docs/templates/bkit-plan.md +158 -281
  69. package/.bkit/core/engine/checks/after/auth.ts +40 -37
  70. package/.bkit/core/engine/checks/after/ci-yml.ts +104 -31
  71. package/.bkit/core/engine/checks/after/github.ts +95 -17
  72. package/.bkit/core/engine/checks/after/index.ts +21 -8
  73. package/.bkit/core/engine/checks/after/suppression.ts +8 -5
  74. package/.bkit/core/engine/checks/after/tools.ts +125 -123
  75. package/.bkit/core/engine/checks/before/context-fetch.ts +227 -33
  76. package/.bkit/core/engine/checks/before/env.ts +3 -3
  77. package/.bkit/core/engine/checks/before/files.ts +5 -4
  78. package/.bkit/core/engine/checks/before/index.ts +25 -1
  79. package/.bkit/core/engine/checks/before/repo.ts +208 -2
  80. package/.bkit/core/engine/checks/status-holes.ts +916 -123
  81. package/.bkit/core/engine/checks/tips/catalogue.ts +82 -20
  82. package/.bkit/core/engine/checks/tips/detect.ts +66 -0
  83. package/.bkit/core/engine/checks/tips/index.ts +52 -11
  84. package/.bkit/core/engine/cli.ts +251 -130
  85. package/.bkit/core/engine/commands/analysis.ts +282 -199
  86. package/.bkit/core/engine/commands/ci/ci.ts +363 -29
  87. package/.bkit/core/engine/commands/ci/pins.ts +172 -0
  88. package/.bkit/core/engine/commands/ci/push-gate.ts +223 -0
  89. package/.bkit/core/engine/commands/comply.ts +77 -103
  90. package/.bkit/core/engine/commands/install/doctor.ts +2 -2
  91. package/.bkit/core/engine/commands/install/install.ts +57 -18
  92. package/.bkit/core/engine/commands/install/uninstall.ts +86 -55
  93. package/.bkit/core/engine/commands/install/upgrade.ts +32 -15
  94. package/.bkit/core/engine/commands/land.ts +139 -18
  95. package/.bkit/core/engine/commands/lib.ts +381 -22
  96. package/.bkit/core/engine/commands/registry.ts +10 -2
  97. package/.bkit/core/engine/commands/setup/setup.ts +8 -7
  98. package/.bkit/core/engine/commands/stats.ts +260 -0
  99. package/.bkit/core/engine/commands/tips.ts +10 -5
  100. package/.bkit/core/engine/commands/workflow/branches.ts +2215 -176
  101. package/.bkit/core/engine/commands/workflow/challenge.ts +748 -0
  102. package/.bkit/core/engine/commands/workflow/completeness.ts +109 -0
  103. package/.bkit/core/engine/commands/workflow/context.ts +1249 -47
  104. package/.bkit/core/engine/commands/workflow/counters.ts +483 -95
  105. package/.bkit/core/engine/commands/workflow/decisions.ts +585 -0
  106. package/.bkit/core/engine/commands/workflow/disk.ts +238 -56
  107. package/.bkit/core/engine/commands/workflow/fids.ts +811 -33
  108. package/.bkit/core/engine/commands/workflow/issues.ts +413 -64
  109. package/.bkit/core/engine/commands/workflow/ledgers.ts +1333 -36
  110. package/.bkit/core/engine/commands/workflow/locks.ts +28 -2
  111. package/.bkit/core/engine/commands/workflow/plan-blocks.ts +691 -0
  112. package/.bkit/core/engine/commands/workflow/plan-versions.ts +21 -0
  113. package/.bkit/core/engine/commands/workflow/plans.ts +257 -0
  114. package/.bkit/core/engine/commands/workflow/prs.ts +178 -33
  115. package/.bkit/core/engine/commands/workflow/repo.ts +66 -8
  116. package/.bkit/core/engine/commands/workflow/roadmap.ts +72 -22
  117. package/.bkit/core/engine/commands/workflow/run-facts.ts +492 -0
  118. package/.bkit/core/engine/commands/workflow/runs.ts +827 -79
  119. package/.bkit/core/engine/commands/workflow/runtime.ts +25 -1
  120. package/.bkit/core/engine/commands/workflow/skills.ts +1 -0
  121. package/.bkit/core/engine/commands/workflow/status.ts +329 -33
  122. package/.bkit/core/engine/commands/workflow/step-table.ts +381 -0
  123. package/.bkit/core/engine/commands/workflow/steps.ts +841 -105
  124. package/.bkit/core/engine/commands/workflow/summary-findings.ts +177 -0
  125. package/.bkit/core/engine/commands/workflow/summary.ts +544 -0
  126. package/.bkit/core/engine/commands/workflow/tasks.ts +409 -0
  127. package/.bkit/core/engine/commands/workflow/test-blocks.ts +254 -0
  128. package/.bkit/core/engine/commands/workflow/tests-changed.ts +201 -0
  129. package/.bkit/core/engine/commands/workflow/tests.ts +2124 -330
  130. package/.bkit/core/engine/commands/workflow/tracker.ts +1195 -0
  131. package/.bkit/core/engine/commands/workflow/workflows.ts +1197 -235
  132. package/.bkit/core/engine/commands/workflow/worktrees.ts +543 -24
  133. package/.bkit/core/engine/install/cloud-env.ts +251 -121
  134. package/.bkit/core/engine/install/context-ci-workflow.ts +102 -0
  135. package/.bkit/core/engine/install/manifest.ts +67 -17
  136. package/.bkit/core/engine/install/modules/antigravity.ts +3 -2
  137. package/.bkit/core/engine/install/modules/cloud.ts +24 -16
  138. package/.bkit/core/engine/install/modules/codex.ts +15 -2
  139. package/.bkit/core/engine/install/modules/core.ts +1196 -45
  140. package/.bkit/core/engine/install/modules/cursor.ts +6 -6
  141. package/.bkit/core/engine/install/modules/opencode.ts +18 -6
  142. package/.bkit/core/engine/install/template-notes.ts +130 -0
  143. package/.bkit/core/engine/install/version-file.ts +9 -4
  144. package/.bkit/core/engine/install/write.ts +5 -0
  145. package/.bkit/core/engine/ledgers/compact.ts +124 -0
  146. package/.bkit/core/engine/ledgers/journal.ts +291 -0
  147. package/.bkit/core/engine/ledgers/migrate.ts +92 -0
  148. package/.bkit/core/engine/ledgers/status.ts +249 -21
  149. package/.bkit/core/engine/ledgers/telemetry.ts +1397 -253
  150. package/.bkit/core/engine/render/hosts.ts +118 -14
  151. package/.bkit/core/engine/render/models.ts +12 -0
  152. package/.bkit/core/engine/shared/bkit-latest.ts +26 -4
  153. package/.bkit/core/engine/shared/branches.ts +4 -1
  154. package/.bkit/core/engine/shared/dep-updater.ts +60 -0
  155. package/.bkit/core/engine/shared/egress.ts +8 -1
  156. package/.bkit/core/engine/shared/json.ts +25 -7
  157. package/.bkit/core/engine/shared/package-manager.ts +9 -0
  158. package/.bkit/core/engine/shared/settings.ts +243 -31
  159. package/.bkit/core/engine/shared/text.ts +361 -0
  160. package/.bkit/core/engine/shared/timeouts.ts +2 -0
  161. package/.bkit/core/engine/tools/cli-doc.ts +111 -0
  162. package/.bkit/core/engine/tools/grammar-density.ts +215 -0
  163. package/.bkit/core/engine/tools/instructions-sources.ts +832 -0
  164. package/.bkit/core/engine/tools/instructions.ts +1802 -0
  165. package/.bkit/core/hooks/antigravity-hook.js +25 -10
  166. package/.bkit/core/hooks/gateguard-engine.js +54 -29
  167. package/.bkit/core/hooks/guardrails-shell.js +4 -5
  168. package/.bkit/core/hooks/guardrails-tiers.js +10 -4
  169. package/.bkit/core/hooks/preflight-linear.sh +9 -9
  170. package/.bkit/core/hooks/preflight-rules.sh +8 -0
  171. package/.bkit/core/hooks/readguard-engine.js +29 -10
  172. package/.bkit/core/hooks/session-rules-advisory.js +61 -0
  173. package/.bkit/core/prompts/bkit-audit-generate.md +202 -94
  174. package/.bkit/core/prompts/bkit-build-challenge-1.md +76 -34
  175. package/.bkit/core/prompts/bkit-build-challenge-2.md +85 -38
  176. package/.bkit/core/prompts/bkit-build-install-skills.md +50 -28
  177. package/.bkit/core/prompts/bkit-build-plan-convert.md +85 -0
  178. package/.bkit/core/prompts/bkit-build-plan-current.md +59 -36
  179. package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +101 -36
  180. package/.bkit/core/prompts/bkit-build-plan-tasks.md +149 -0
  181. package/.bkit/core/prompts/bkit-build-plan-tests.md +120 -0
  182. package/.bkit/core/prompts/bkit-build-plan-verify.md +104 -43
  183. package/.bkit/core/prompts/bkit-debug-abort-handover.md +47 -32
  184. package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +109 -57
  185. package/.bkit/core/prompts/bkit-debug-failure-remediate.md +65 -39
  186. package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +53 -31
  187. package/.bkit/core/prompts/bkit-debug-failure-soak.md +65 -34
  188. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +46 -31
  189. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +45 -31
  190. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +43 -30
  191. package/.bkit/core/prompts/bkit-design-generate.md +80 -46
  192. package/.bkit/core/prompts/bkit-design-organise.md +83 -32
  193. package/.bkit/core/prompts/bkit-design-review-1.md +70 -50
  194. package/.bkit/core/prompts/bkit-design-review-2.md +65 -46
  195. package/.bkit/core/prompts/bkit-design-spike.md +64 -40
  196. package/.bkit/core/prompts/bkit-design-update.md +53 -28
  197. package/.bkit/core/prompts/bkit-plan-generate.md +101 -29
  198. package/.bkit/core/prompts/bkit-plan-review-1.md +78 -41
  199. package/.bkit/core/prompts/bkit-plan-review-2.md +78 -35
  200. package/.bkit/core/prompts/bkit-plan-scope-check.md +116 -0
  201. package/.bkit/core/prompts/bkit-plan-update.md +86 -31
  202. package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +94 -50
  203. package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +91 -41
  204. package/.bkit/core/prompts/bkit-ship-update-docs.md +45 -24
  205. package/.bkit/core/prompts/bkit-utility-compress-markdown.md +65 -49
  206. package/.bkit/core/prompts/bkit-utility-update-decisions.md +87 -42
  207. package/.bkit/core/prompts/bkit-utility-update-deferrals.md +81 -37
  208. package/.bkit/core/prompts/bkit-utility-update-documentation.md +43 -25
  209. package/.bkit/core/prompts/bkit-utility-update-failures.md +84 -37
  210. package/.bkit/core/prompts/bkit-utility-update-knowledge.md +88 -42
  211. package/.bkit/core/prompts/bkit-utility-update-roadmap.md +92 -39
  212. package/.bkit/core/prompts/bkit-utility-update-tracker.md +159 -60
  213. package/.bkit/core/workflows/bkit-auto.md +89 -58
  214. package/.bkit/core/workflows/bkit-build.md +967 -517
  215. package/.bkit/core/workflows/bkit-debug.md +555 -387
  216. package/.bkit/core/workflows/bkit-design.md +319 -283
  217. package/.bkit/core/workflows/bkit-plan.md +319 -342
  218. package/.bkit/core/workflows/bkit-ship.md +525 -328
  219. package/.bkit/shared/.agents/plugins/bkit/hooks.json +10 -0
  220. package/.bkit/shared/.bkit/.env.example +2 -2
  221. package/.bkit/shared/.claude/bkit-cloud.md +12 -10
  222. package/.bkit/shared/.claude/settings.json +14 -0
  223. package/.bkit/shared/.codex/bkit-cloud.md +98 -0
  224. package/.bkit/shared/.codex/hooks.json +20 -0
  225. package/.bkit/shared/.cursor/bkit-cloud.md +3 -3
  226. package/.bkit/shared/.cursor/mcp.json +1 -1
  227. package/.bkit/shared/.cursor/rules/bkit-rules.mdc +1 -1
  228. package/.bkit/shared/.gitattributes +1 -1
  229. package/.bkit/shared/.mcp.json +1 -1
  230. package/.bkit/shared/.opencode/opencode.json +12 -1
  231. package/.bkit/shared/CLAUDE.md +6 -2
  232. package/.bkit/shared/GEMINI.md +5 -2
  233. package/.bkit/shared/docs/architecture.md +4 -7
  234. package/.bkit/shared/docs/data-schema.md +4 -7
  235. package/.bkit/shared/docs/deployments.md +241 -168
  236. package/.bkit/shared/docs/design.md +11 -12
  237. package/.bkit/shared/docs/noise.md +8 -7
  238. package/.bkit/shared/docs/observability.md +5 -8
  239. package/.bkit/shared/docs/security.md +35 -17
  240. package/.bkit/shared/docs/setup.md +29 -18
  241. package/.bkit/shared/docs/technology.md +3 -6
  242. package/.bkit/shared/docs/testing.md +289 -174
  243. package/.bkit/shared/gitignore +6 -2
  244. package/.bkit/templates/.claude/hooks/bkit-cloud-bootstrap.sh +15 -16
  245. package/.bkit/templates/.cursor/Dockerfile +12 -8
  246. package/.bkit/templates/.cursor/environment.json +1 -1
  247. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +10 -8
  248. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +45 -12
  249. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +3 -3
  250. package/.bkit/templates/.github/renovate.json5 +34 -6
  251. package/.bkit/templates/.github/workflows/bkit-ci.yml +54 -51
  252. package/.bkit/templates/.github/workflows/bkit-cloud.yml +34 -33
  253. package/.bkit/templates/.github/workflows/bkit-health.yml +97 -0
  254. package/.bkit/templates/.github/workflows/bkit-renovate.yml +5 -4
  255. package/.bkit/templates/.github/workflows/bkit-trivy.yml +5 -4
  256. package/.bkit/templates/.husky/pre-commit +2 -2
  257. package/.bkit/templates/.husky/pre-push +96 -36
  258. package/.bkit/templates/.prettierignore +6 -0
  259. package/.bkit/templates/.vale.ini +27 -27
  260. package/.bkit/templates/context/bkit-cloudrun.md +23 -15
  261. package/.bkit/templates/context/bkit-expo.md +70 -52
  262. package/.bkit/templates/context/bkit-github.md +93 -56
  263. package/.bkit/templates/context/bkit-inngest.md +21 -15
  264. package/.bkit/templates/context/bkit-maestro.md +22 -16
  265. package/.bkit/templates/context/bkit-playwright.md +23 -17
  266. package/.bkit/templates/context/bkit-resend.md +12 -10
  267. package/.bkit/templates/context/bkit-sentry.md +30 -20
  268. package/.bkit/templates/context/bkit-serena.md +8 -7
  269. package/.bkit/templates/context/bkit-stripe.md +14 -13
  270. package/.bkit/templates/context/bkit-supabase.md +16 -13
  271. package/.bkit/templates/context/bkit-tavily.md +14 -11
  272. package/.bkit/templates/context/bkit-vercel.md +27 -18
  273. package/.bkit/templates/docs/capabilities.md +15 -14
  274. package/.bkit/templates/scripts/ci/{check-accepted-divergences.mjs → bkit-check-accepted-divergences.mjs} +6 -3
  275. package/.bkit/templates/scripts/ci/{check-accepted-divergences.test.mjs → bkit-check-accepted-divergences.test.mjs} +3 -3
  276. package/.bkit/templates/scripts/ci/{check-capstone.mjs → bkit-check-capstone.mjs} +2 -2
  277. package/.bkit/templates/scripts/ci/{check-capstone.test.mjs → bkit-check-capstone.test.mjs} +4 -4
  278. package/.bkit/templates/scripts/ci/{check-dependency-audit.mjs → bkit-check-dependency-audit.mjs} +103 -18
  279. package/.bkit/templates/scripts/ci/{check-dependency-audit.test.mjs → bkit-check-dependency-audit.test.mjs} +31 -3
  280. package/.bkit/templates/scripts/ci/bkit-machine-lock.sh +387 -0
  281. package/.bkit/templates/scripts/ci/bkit-test-awake.mjs +75 -0
  282. package/.bkit/templates/scripts/ci/bkit-test-awake.test.mjs +160 -0
  283. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.mjs → bkit-resolve-push-base.mjs} +3 -3
  284. package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.test.mjs → bkit-resolve-push-base.test.mjs} +4 -4
  285. package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +10 -2
  286. package/.bkit/templates/scripts/graphify/bkit-graph-drift.py +1 -1
  287. package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +3 -3
  288. package/.bkit/templates/scripts/graphify/bkit-graph-embed.py +63 -0
  289. package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +2 -2
  290. package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +69 -18
  291. package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -3
  292. package/.bkit/templates/scripts/graphify/bkit-graph-surface.py +1 -1
  293. package/.bkit/templates/scripts/graphify/bkit-graphify-graphml.py +1 -1
  294. package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +197 -126
  295. package/.bkit/templates/scripts/graphify/bkit-graphify.sh +64 -41
  296. package/.bkit/templates/scripts/slop/bkit-slop-type-suppression.mjs +23 -7
  297. package/.bkit/templates/slop-scan.config.json +9 -2
  298. package/CHANGELOG.md +231 -0
  299. package/README.md +278 -89
  300. package/dist/checks/after/auth.js +36 -33
  301. package/dist/checks/after/ci-yml.js +91 -30
  302. package/dist/checks/after/github.js +91 -17
  303. package/dist/checks/after/index.js +22 -11
  304. package/dist/checks/after/suppression.js +8 -5
  305. package/dist/checks/after/tools.js +111 -114
  306. package/dist/checks/before/context-fetch.js +218 -33
  307. package/dist/checks/before/env.js +3 -3
  308. package/dist/checks/before/files.js +5 -3
  309. package/dist/checks/before/index.js +20 -3
  310. package/dist/checks/before/repo.js +197 -2
  311. package/dist/checks/status-holes.js +739 -114
  312. package/dist/checks/tips/catalogue.js +70 -19
  313. package/dist/checks/tips/detect.js +62 -0
  314. package/dist/checks/tips/index.js +51 -9
  315. package/dist/cli.js +234 -124
  316. package/dist/commands/analysis.js +174 -141
  317. package/dist/commands/ci/ci.js +302 -25
  318. package/dist/commands/ci/pins.js +142 -0
  319. package/dist/commands/ci/push-gate.js +194 -0
  320. package/dist/commands/comply.js +54 -91
  321. package/dist/commands/install/doctor.js +2 -2
  322. package/dist/commands/install/install.js +50 -19
  323. package/dist/commands/install/uninstall.js +82 -55
  324. package/dist/commands/install/upgrade.js +21 -11
  325. package/dist/commands/land.js +137 -17
  326. package/dist/commands/lib.js +295 -21
  327. package/dist/commands/registry.js +10 -2
  328. package/dist/commands/setup/setup.js +8 -7
  329. package/dist/commands/stats.js +175 -0
  330. package/dist/commands/tips.js +7 -3
  331. package/dist/commands/workflow/branches.js +1873 -152
  332. package/dist/commands/workflow/challenge.js +609 -0
  333. package/dist/commands/workflow/completeness.js +97 -0
  334. package/dist/commands/workflow/context.js +1045 -46
  335. package/dist/commands/workflow/counters.js +385 -86
  336. package/dist/commands/workflow/decisions.js +484 -0
  337. package/dist/commands/workflow/disk.js +214 -56
  338. package/dist/commands/workflow/fids.js +706 -33
  339. package/dist/commands/workflow/issues.js +349 -59
  340. package/dist/commands/workflow/ledgers.js +1123 -37
  341. package/dist/commands/workflow/locks.js +26 -2
  342. package/dist/commands/workflow/plan-blocks.js +501 -0
  343. package/dist/commands/workflow/plan-versions.js +22 -0
  344. package/dist/commands/workflow/plans.js +205 -0
  345. package/dist/commands/workflow/prs.js +154 -35
  346. package/dist/commands/workflow/repo.js +58 -8
  347. package/dist/commands/workflow/roadmap.js +58 -23
  348. package/dist/commands/workflow/run-facts.js +421 -0
  349. package/dist/commands/workflow/runs.js +670 -72
  350. package/dist/commands/workflow/runtime.js +15 -1
  351. package/dist/commands/workflow/skills.js +1 -0
  352. package/dist/commands/workflow/status.js +282 -34
  353. package/dist/commands/workflow/step-table.js +308 -0
  354. package/dist/commands/workflow/steps.js +703 -96
  355. package/dist/commands/workflow/summary-findings.js +117 -0
  356. package/dist/commands/workflow/summary.js +388 -0
  357. package/dist/commands/workflow/tasks.js +378 -0
  358. package/dist/commands/workflow/test-blocks.js +231 -0
  359. package/dist/commands/workflow/tests-changed.js +172 -0
  360. package/dist/commands/workflow/tests.js +1695 -305
  361. package/dist/commands/workflow/tracker.js +983 -0
  362. package/dist/commands/workflow/workflows.js +1014 -222
  363. package/dist/commands/workflow/worktrees.js +432 -26
  364. package/dist/install/cloud-env.js +233 -99
  365. package/dist/install/context-ci-workflow.js +85 -0
  366. package/dist/install/manifest.js +64 -17
  367. package/dist/install/modules/antigravity.js +3 -2
  368. package/dist/install/modules/cloud.js +25 -16
  369. package/dist/install/modules/codex.js +12 -2
  370. package/dist/install/modules/core.js +1090 -48
  371. package/dist/install/modules/cursor.js +6 -6
  372. package/dist/install/modules/opencode.js +13 -7
  373. package/dist/install/template-notes.js +116 -0
  374. package/dist/install/version-file.js +9 -4
  375. package/dist/ledgers/compact.js +87 -0
  376. package/dist/ledgers/journal.js +233 -0
  377. package/dist/ledgers/migrate.js +81 -0
  378. package/dist/ledgers/status.js +176 -13
  379. package/dist/ledgers/telemetry.js +1010 -125
  380. package/dist/render/hosts.js +104 -14
  381. package/dist/render/models.js +12 -0
  382. package/dist/shared/bkit-latest.js +26 -4
  383. package/dist/shared/branches.js +3 -1
  384. package/dist/shared/dep-updater.js +49 -0
  385. package/dist/shared/egress.js +8 -1
  386. package/dist/shared/json.js +20 -7
  387. package/dist/shared/package-manager.js +6 -0
  388. package/dist/shared/settings.js +181 -24
  389. package/dist/shared/text.js +333 -0
  390. package/dist/shared/timeouts.js +2 -0
  391. package/dist/tools/cli-doc.js +97 -0
  392. package/dist/tools/grammar-density.js +183 -0
  393. package/dist/tools/instructions-sources.js +720 -0
  394. package/dist/tools/instructions.js +1623 -0
  395. package/package.json +156 -51
  396. package/.bkit/core/.bkit/lite.md +0 -73
  397. package/.bkit/core/engine/commands/harvest.ts +0 -459
  398. package/.bkit/core/engine/commands/workflow/workstreams.ts +0 -166
  399. package/.bkit/core/engine/tools/wording.ts +0 -748
  400. package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +0 -69
  401. package/.bkit/core/prompts/bkit-build-challenge-remediate.md +0 -71
  402. package/.bkit/core/prompts/bkit-build-challenge-tests.md +0 -74
  403. package/.bkit/core/prompts/bkit-build-plan-execute.md +0 -76
  404. package/.bkit/core/prompts/bkit-build-summary.md +0 -94
  405. package/.bkit/core/prompts/bkit-debug-summary.md +0 -96
  406. package/.bkit/core/prompts/bkit-design-summary.md +0 -107
  407. package/.bkit/core/prompts/bkit-plan-complexity-check.md +0 -67
  408. package/.bkit/core/prompts/bkit-plan-complexity-split.md +0 -88
  409. package/.bkit/core/prompts/bkit-plan-review-3.md +0 -93
  410. package/.bkit/core/prompts/bkit-plan-scope-check-1.md +0 -85
  411. package/.bkit/core/prompts/bkit-plan-scope-check-2.md +0 -85
  412. package/.bkit/core/prompts/bkit-plan-summary.md +0 -107
  413. package/.bkit/core/prompts/bkit-ship-summary.md +0 -78
  414. package/.bkit/templates/scripts/ci/bkit-local-stack-lock.sh +0 -194
  415. package/dist/commands/harvest.js +0 -353
  416. package/dist/commands/workflow/workstreams.js +0 -143
  417. package/dist/tools/wording.js +0 -680
  418. /package/.bkit/templates/.vale/styles/{House → Bkit}/Filler.yml +0 -0
  419. /package/.bkit/templates/.vale/styles/{House → Bkit}/Hedging.yml +0 -0
  420. /package/.bkit/templates/.vale/styles/{House → Bkit}/LLMSlop.yml +0 -0
  421. /package/.bkit/templates/.vale/styles/{House → Bkit}/Verbose.yml +0 -0
  422. /package/.bkit/templates/scripts/ci/{accepted-advisories.json → bkit-accepted-advisories.json} +0 -0
  423. /package/.bkit/templates/scripts/ci/{accepted-divergences.json → bkit-accepted-divergences.json} +0 -0
  424. /package/.bkit/templates/scripts/launchd/{launchd.env.example → bkit-launchd.env.example} +0 -0
  425. /package/.bkit/templates/scripts/launchd/{ai.bkit.launchd.plist → bkit-launchd.plist} +0 -0
@@ -1,41 +1,40 @@
1
- <!-- Note: Reports live at `docs/audits/{YYYYMM}/{slug}.md`. `{YYYYMM}` = UTC month of this run. `{slug}` = template basename without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Never overwrite. The report is stamped with a `bkit:anchor` block recording the audited commit (`baseSha`) and branch (`baseRef`); never hand-author or edit it. `@bkit-audit-generate` fills this template. -->
2
-
3
1
  <!-- bkit:start -->
4
2
 
5
3
  {{BKIT_MANAGED_MARKER}}
6
4
 
5
+ <!-- Note: @bkit-audit-generate fills this template. The report lives at `docs/audits/{YYYYMM}/{slug}.md`, where `{YYYYMM}` is the UTC month of the run and `{slug}` is this file's name without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md`, where `{TIMESTAMP}` is the output of `date -u +%Y%m%dT%H%M%SZ`. NEVER overwrite an earlier report. The report is stamped with a `bkit:anchor` block that records the audited commit (`baseSha`) and branch (`baseRef`). NEVER write or edit that block by hand. -->
6
+
7
7
  # Red Team Audit
8
8
 
9
9
  > [!CAUTION]
10
- > **Purpose:** Active adversarial exploitation of a non-production deployment: one hostile request per probe, the request and response kept, then cleaned up.
10
+ > **Purpose:** Active adversarial exploitation of a non-production deployment: one hostile request per probe, with the request and response kept, then cleanup.
11
11
  >
12
12
  > **Rules:**
13
13
  >
14
- > - Read-only audit; never edit code, config, or data.
15
- > - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
16
- > - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
17
- > - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
18
- > - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
19
- > - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
20
- > - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
21
- > - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
22
- > - Non-production deployment only. NEVER production, the release branch, or a third party's own platform beyond calls the app already makes.
23
- > - Synthetic identities only; creating and deleting them is the only data write, and they are deleted before the report finishes. One request per probe. No load, volume fuzzing, or spend past a single cap. Stop at proof — do not pivot.
24
- > - never copy a working token or a personal-data value into the report. Record the route, the input shape, and the response.
14
+ > - Probe a non-production deployment only.
15
+ > - NEVER probe production, the release branch, or a third party's own platform beyond the calls the app already makes.
16
+ > - Use synthetic identities only.
17
+ > - Creating and deleting those identities is the only data write, and they are deleted before the report finishes.
18
+ > - Send one request per probe.
19
+ > - Send no load, no volume fuzzing, and no spend past a single cap.
20
+ > - Stop at proof, and do not pivot.
21
+ > - NEVER copy a working token into the report.
22
+ > - NEVER copy a personal-data value into the report.
23
+ > - Record the route, the input shape and the response.
25
24
 
26
25
  ## Universal Instructions
27
26
 
28
27
  ### Context & Goals
29
28
 
30
- Three shapes do not show up in a source read: row-security denial looks like empty result; middleware checks the route file does not show; prompt injection shows only when the model runs. Target failure: **a control that holds in the source and fails on a request** — e.g. mixed tenant-id list clamped to caller's rows, revoked token still accepted, message makes the model delete items it does not mention. Static suspicions from `bkit-audit-security` and `bkit-audit-llm`; this audit sends the request.
29
+ Three kinds of failure do not show up in a source read. A row-security denial looks like an empty result. A middleware check is not visible in the route file. A prompt injection shows only when the model runs. The failure this audit targets is a control that holds in the source and fails on a request. Examples: a mixed tenant-id list is clamped to the caller's rows instead of refused, a revoked token is still accepted, or a message makes the model delete items it does not mention. The static suspicions come from `bkit-audit-security` and `bkit-audit-llm`, and this audit sends the request.
31
30
 
32
- **Applies when:** non-production deployment can be called, and the system has auth, tenancy, or a public free-text model surface. None → one `N/A` row with evidence, never "clean".
31
+ **Applies when:** a non-production deployment can be called, and the system has auth, tenancy, or a public free-text model surface. **If** it has none → write one `N/A` row with its evidence, and never report the surface as "clean".
33
32
 
34
- **Cadence:** once before launch, then quarterly. Extra pass after any change to authentication, a route that takes an id, the inbound pipeline, or a machine-client tool.
33
+ **Cadence:** Run once before launch, then once a quarter. Run an extra pass after any change to authentication, a route that takes an id, the inbound pipeline, or a machine-client tool.
35
34
 
36
- **Anchor Standards:** record version and date read. Newer version → `Standards` step reads what changed.
35
+ **Anchor Standards:**
37
36
 
38
- - OWASP Web Security Testing Guide (e.g. WSTG v4.2; record if a newer stable release exists).
37
+ - OWASP Web Security Testing Guide (e.g., WSTG v4.2; record if a newer stable release exists).
39
38
  - Penetration Testing Execution Standard (PTES): pre-engagement, intelligence gathering, threat modelling, vulnerability analysis, exploitation, post-exploitation, reporting.
40
39
  - When a probe drives a model: OWASP GenAI Red Teaming Guide, OWASP AI Testing Guide, MITRE ATLAS.
41
40
  - OWASP Mobile Application Security Testing Guide (MASTG), when the native build is in scope.
@@ -43,17 +42,20 @@ Three shapes do not show up in a source read: row-security denial looks like emp
43
42
 
44
43
  ### Scope
45
44
 
46
- - Written in-list and out-list for this run, and what each platform's testing page allows.
47
- - Attack-surface diff since the previous report. Everything new gets at least one probe.
48
- - Retest of every earlier break whose fix has landed.
49
- - Cross-tenant reads through the app and, separately, through the data API with the client public key.
50
- - Acting above a role. A removed member trying every way back in.
51
- - Authentication, session end, off-site redirects.
52
- - Hostile inbound content: unauthorised writes, leaks, internal fetches, impersonation, caps.
53
- - Machine-client tool misuse.
54
- - Injection at render, search, and webhook boundaries. Rate-limit and cost caps, one crossing each.
55
- - Off-topic use of public model surfaces.
56
- - Cleanup of every identity this run created.
45
+ - Write the in-list and the out-list for this run, and what each platform's testing page allows.
46
+ - Diff the attack surface against the previous report, and give everything new at least one probe.
47
+ - Retest every earlier break whose fix has landed.
48
+ - Probe cross-tenant reads through the app.
49
+ - Probe cross-tenant reads separately through the data API with the client public key.
50
+ - Probe acting above a role.
51
+ - Probe every way a removed member could get back in.
52
+ - Probe authentication, session end and off-site redirects.
53
+ - Probe hostile inbound content: unauthorised writes, leaks, internal fetches, impersonation and caps.
54
+ - Probe machine-client tool misuse.
55
+ - Probe injection at the render, search and webhook boundaries.
56
+ - Cross each rate-limit and cost cap once.
57
+ - Probe off-topic use of public model surfaces.
58
+ - Clean up every identity this run created.
57
59
 
58
60
  ### Out of Scope
59
61
 
@@ -69,77 +71,107 @@ Three shapes do not show up in a source read: row-security denial looks like emp
69
71
 
70
72
  ### Verdicts
71
73
 
72
- One per probe, on the `Probes` row.
74
+ Each probe gets one verdict, on its `Probes` row.
73
75
 
74
- - **HELD:** control did what it should. Held probe = result, not blank. No test proves it → `bkit-audit-testing`. Not a finding.
75
- - **BROKE:** control failed = finding. Record blast radius by reasoning, not by pivoting.
76
- - **INCONCLUSIVE:** blocked, skipped, or no clear answer. Say why. Stays in `Probes` — skipped check reads like passed. `BROKE` without kept response → `INCONCLUSIVE` until a later run reproduces.
77
- - **FIXED** / **STILL BROKE:** retest of earlier `BROKE` only, with fix commit.
78
- - **OTHER:** fits none. Say why. Same `OTHER` on 2 runs → propose new verdict in `Process Improvements`.
76
+ - **HELD:** the control did what it should. A held probe is a result, not a blank. **If** no test proves it → route it to `bkit-audit-testing`. It is not a finding.
77
+ - **BROKE:** the control failed, and that is a finding. Record the blast radius by reasoning, not by pivoting.
78
+ - **INCONCLUSIVE:** the probe was blocked, skipped, or gave no clear answer. Say why. It stays in `Probes`, because a skipped check otherwise reads as passed. **If** a `BROKE` has no kept response → mark it `INCONCLUSIVE` until a later run reproduces it.
79
+ - **FIXED** / **STILL BROKE:** use these only for a retest of an earlier `BROKE`, with the fix commit.
80
+ - **OTHER:** it fits no other verdict. Say why. **If** the same `OTHER` shows up on 2 runs → propose a new verdict in `Process Improvements`.
79
81
 
80
82
  ### Pre-Flight / Dependencies
81
83
 
82
- **Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
83
-
84
- **Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
85
-
86
84
  #### Core
87
85
 
88
- Always verify.
89
-
90
- - [ ] **Permissions:** Before Step 1 — one cheap read-only call per tool this run uses (every item below, every rule under `Project Instructions` `Permissions`), e.g. `gh run list --limit 1`, one MCP read, one anchor-standard fetch. Blocked / denied (here or in any step) → record call verbatim and narrow allow rule clearing it (e.g. `Bash(gh run list *)`) in `Not Checked`, `Process Improvements`, and `Project Instructions` `Permissions`; run every step the remaining tools allow; work needing blocked call → `Not Checked`. never stop the run for a blocked call; never retry or reword a blocked call to get past it.
91
- - [ ] **Target:** Steps 2–13 — non-production deployment of this commit, resolved by commit SHA, confirmed serving. Fallback: none. Probes stay `INCONCLUSIVE`. NEVER point them at production.
92
- - [ ] **Identities:** Steps 2, 5–12, 15 — create and delete synthetic users and tenants, guarded so a non-synthetic identity cannot be deleted. Fallback: none. Do not probe with real accounts.
93
- - [ ] **Web:** Steps 2, 14 — each platform's penetration-testing page, and anchor standards. Fallback: policy unread → do not send probes; record why.
86
+ - [ ] **Permissions:** every blocked call is recorded.
87
+ - [ ] **Target:** Steps 2-13 — a non-production deployment of this commit, resolved by commit SHA and confirmed serving. Fallback: none, so the probes stay `INCONCLUSIVE`. NEVER point them at production.
88
+ - [ ] **Identities:** Steps 2, 5-12, 15 — create and delete synthetic users and tenants, with a guard so that a non-synthetic identity cannot be deleted. Fallback: none. Do not probe with real accounts.
89
+ - [ ] **Web:** Steps 2, 14 — read each platform's penetration-testing page and the anchor standards. Fallback: **If** a platform's policy is unread → send no probes, and record why.
94
90
 
95
91
  #### Conditional
96
92
 
97
- Verify only when applicable.
98
-
99
- - [ ] **Data API:** Client public key plus a user token can call the data API directly → Step 6 — e.g. PostgREST, Storage, Realtime. Fallback: app routes only; direct path `Not Checked`.
100
- - [ ] **Inbound Mail:** The synthetic tenant has an inbound address → Step 10. Fallback: skip; `Not Checked`.
101
- - [ ] **Machine Client:** A token-gated tool endpoint exists → Steps 2, 11. Fallback: skip with evidence.
102
- - [ ] **Native Build:** This run includes the native client → Step 8 — cached data and sync on a device or emulator. Fallback: web only; device path `Not Checked`.
103
- - [ ] **Model Spend:** A probe drives a model → Steps 10, 13 — budget for one crossing of one cap. Fallback: do not send the cost probe; `INCONCLUSIVE`.
93
+ - [ ] **Data API:** **If** the client public key plus a user token can call the data API directly → Step 6 — e.g., PostgREST, Storage, Realtime. Fallback: probe through the app routes only, and mark the direct path `Not Checked`.
94
+ - [ ] **Inbound Mail:** **If** the synthetic tenant has an inbound address → Step 10. Fallback: skip the step, and mark it `Not Checked`.
95
+ - [ ] **Machine Client:** **If** a token-gated tool endpoint exists → Steps 2, 11. Fallback: skip with evidence.
96
+ - [ ] **Native Build:** **If** this run includes the native client → Step 8 — cached data and sync on a device or emulator. Fallback: test the web only, and mark the device path `Not Checked`.
97
+ - [ ] **Model Spend:** **If** a probe drives a model → Steps 10, 13 — a budget for one crossing of one cap. Fallback: do not send the cost probe, and mark it `INCONCLUSIVE`.
104
98
 
105
99
  ### 🔒 Gate 1: Prerequisites Check
106
100
 
107
- **Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
108
-
109
- - [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
110
- - [ ] **Gate 1 - Verified:** All Core items checked. All applicable Conditional items checked.
101
+ - [ ] **Gaps named:** every missing item names its fallback and its `Not Checked` entry.
102
+ - [ ] **Gate 1 — Verified:** every item above, every Core item and every applicable Conditional item is checked.
111
103
 
112
104
  ### Probe Steps
113
105
 
114
- - [ ] **Step 1 — Previous Run:** Audited commit = this report's `bkit:anchor` `baseSha`. Read newest prior report for this slug under `docs/audits/`; its commit = its `bkit:anchor` `baseSha`, else the HEAD its `Previous Run` recorded. Count findings fixed / still open; age of oldest open. Open after 2 runs → re-raise with age. **Done when:** closure rate in `Previous Run`, or run marked baseline.
115
- - [ ] **Step 2 — Engage:** Record commit and non-production URL deployed for it (the deployment the live lane resolves for that SHA, not a branch alias that may be stale). Confirm serving. Write scope in `Scope`. **In:** non-production web URL (e.g. preview deploy, staging), API host, machine-client endpoint, inbound mail domain, data API via client public key, background-job serve endpoint, native build if tested. **Out:** production, release branch, persistent demo tenant, every third party's own platform, anything not on in-list. Read current penetration-testing page of each platform probes touch (app host, database, native vendor if in scope). Record what they allow and plan tier. Page forbids probe → do not send; `INCONCLUSIVE`. Create two synthetic tenants, attacker, and victim, each with roles the product distinguishes. Issue machine-client token for each owner where product has one, on plan the feature allows. Seed victim with few records, one recurring record, attachment. Do not touch persistent demo tenant. Read newest `bkit-audit-security` and `bkit-audit-llm` reports. Every finding they could not prove → probe; model audit's prompt-only rules → probe. Every trust boundary threat model names → ≥1 probe. No threat model → say so in `Scope`. Before destructive probe, confirm no other live test holds target database. Record window. Do not wait for named approver. Later probe degrades target, touches non-synthetic data, or reaches third party → stop remaining probes; record stop in `Scope`. **Done when:** `Scope` holds URL, commit, in-list, out-list, platform rules, plan tier, identities (no tokens), suspicion list. **Probe row** (every later probe): request with tokens redacted, response status, relevant body, verdict. `BROKE` adds blast radius by reasoning, not pivoting.
116
- - [ ] **Step 3 — Surface:** List attack surface at this commit: routes, server actions, machine-client tools, webhooks, response headers of each in-scope origin. Diff vs previous report's list. Everything new → ≥1 probe. **Done when:** `Surface` holds list and diff.
117
- - [ ] **Step 4 — Retest:** Re-run every earlier `BROKE` whose fix landed, from recorded reproduction. `FIXED` or `STILL BROKE`, with fix commit. Confirm regression test prior run named exists; if not → `bkit-audit-testing`. **Done when:** `Retests` row per prior break, or `none`.
118
- - [ ] **Step 5 — Cross-Tenant:** As attacker, request victim's records by id on every route that takes one: items, attachments, download URLs, members, invitations, machine-client read tools. Mixed own-and-foreign id list must be refused, not clamped to attacker's rows. Expected: denial or not-found; no victim field in any response part, including errors. **Done when:** `Probes` row per route, shape as Step 2.
119
- - [ ] **Step 6 — Direct API:** Step 5 goes through app; attacker can skip. With attacker's token and client public key, ask data API for victim's tenant: each tenant-scoped table, privileged routines, GraphQL if enabled, file-storage list and download, realtime subscribe. Expected: no victim row, object, or event. Denial looks like empty result → send same request once as victim to show it would have returned data. **Done when:** `Probes` row per surface, including victim-control request, or skip with evidence direct API not exposed.
120
- - [ ] **Step 7 — Roles:** Inside attacker tenant, low role tries what only higher role may do: invite, remove member, change plan, issue machine-client token, delete record not theirs, delete tenant. Check against role matrix. **Done when:** `Probes` row per operation.
121
- - [ ] **Step 8 — Removed:** Realistic attacker = former tenant member. Remove attacker's second member, then try every way back: web session, native cached data and sync, machine-client token they issued, invitation links they sent, signed attachment URLs they were given, capability URL (calendar feed or equivalent), mail to tenant address. Expected: every path fails on next request; mail from removed member gets no more trust than stranger. **Done when:** `Probes` row per path.
122
- - [ ] **Step 9 — Authentication:** Expired token and revoked one. Revoked machine token fails on next call — no grace period unless product records one. Token for plan excluding feature → refused. Cookie-authenticated write with no `Origin`, or foreign one. Redirect parameters pointing off-site. Sign-out-all ends every other session. **Done when:** `Probes` row per case.
123
- - [ ] **Step 10 — Inbound:** Mail to synthetic tenant inbound address, from attacker address, trying to make model: delete or change records message does not mention; leak other records into reply; fetch internal address (`http://169.254.169.254/`, localhost, private ranges); claim member (address or display name) from domain failing or lacking SPF and DKIM; exceed link and attachment caps. Payload corpus e.g. promptfoo, garak — record which. On a shared inbound provider, use the environment tag the project documents so the message cannot land in production. Expected: only records message genuinely describes are written; nothing else changes; no internal fetch; every cap fires. Check action log for what was written. Cost probe crosses one limit, once. **Done when:** `Probes` row per attempt, with action-log evidence, or `INCONCLUSIVE` where model spend unavailable.
124
- - [ ] **Step 11 — Tools:** With attacker's token, as client that ignores rules: set fields allow-list excludes; pass victim's ids; change recurring record without required scope; send oversized arguments; repeat create to test idempotency key. **Done when:** `Probes` row per case, or skip with evidence no machine-client tools.
125
- - [ ] **Step 12 — Boundaries:** Script and markup in text fields; check render on web, native client, reply. Injection through search query and filters reaching search routine. Webhook endpoints: no signature = denial; wrong signature = same denial plus error log. Rate limits: documented thresholds fire, then stop. **Done when:** `Probes` row per boundary.
126
- - [ ] **Step 13 — Off-Topic:** Per public free-text model surface (`bkit-audit-llm` `Job Scope`; none there → find from `Surface`), as an anonymous or synthetic visitor, one ask per probe: general coding (e.g. "write a Python function that…"), homework, essay, off-topic ask wrapped in an on-topic frame (e.g. "for my trip, write a script that…"); then one greeting as control. Expected: redirect per the surface's stated job, no off-topic answer; greeting gets a normal reply. Off-topic answered → `BROKE`; record what was meant to bound it (prompt, grounding gate, classifier). **Done when:** `Probes` row per surface × ask, or skip with evidence no public free-text model surface.
127
- - [ ] **Step 14 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per WSTG category (INFO, CONF, IDNT, ATHN, ATHZ, SESS, INPV, ERRH, CRYP, BUSL, CLNT, APIT), and per ATLAS tactic a model probe touched → checked (name step) / not applicable (why) / finding. Per bkit anchor (doc section, rule, or issue shape): one row → followed (name step or evidence) / not applicable (why) / finding; departure with no recorded reason (e.g. `docs/decisions.jsonl` row, accepted-divergence entry) = finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
128
- - [ ] **Step 15 — Anything Else:** (a) Everything changed since previous report's commit touching attack surface (routes, server actions, machine-client tools, webhooks, response headers, inbound handling, what client public key can reach; Step 3 diff = starting list) → one-line verdict each. (b) Bounded ~30 min pass: what senior penetration tester flags that no step asks; read since previous run (incidents, `bkit-audit-logs` reports, new `docs/failures.jsonl` rows, vendor status incidents) — what would no step catch? Probes these passes send follow rules, use identities made for it, go in `Probes`. Then delete every identity this run created with guarded delete (reaps tenant it would strand); confirm orphan sweep finds nothing left. Record where full request/response evidence is kept, for how long, redaction applied. **Done when:** `Beyond the Steps` holds both passes, or `none`; `Cleanup` confirms every identity this run created is gone. Class seen on 2 runs → propose step in `Process Improvements`. `Expected` names where finding goes, recommends safer fix. This run does not file; the audit agent writes `docs/failures.jsonl` rows: `BROKE` → plan from this report, `docs/failures.jsonl` row, regression test (ideally deployed boundary) so `bkit-audit-testing` keeps it fixed; `HELD` with no test → `bkit-audit-testing`; model result → `bkit-audit-llm`, against finding it tested; `STILL BROKE` → original finding, with retest and fix commit; `INCONCLUSIVE` → next run's Step 2 suspicion list, with what blocked; `OTHER` → report, second run proposes verdict; vulnerability in database product itself, not project's use → vendor per that vendor's testing page, plus this report; stop condition → remaining probes stopped, stop recorded in `Scope`.
106
+ - [ ] **Step 1 — Previous Run:** **Done when:** `Previous Run` holds the closure rate, or the run is marked baseline.
107
+ - [ ] **Step 2 — Engage:** Record the commit and the non-production URL deployed for it.
108
+ - Use the deployment the live lane resolves for that SHA, not a branch alias, which may be stale.
109
+ - Confirm it is serving.
110
+ - Write the scope in `Scope`:
111
+ - The in-list covers: the non-production web URL (e.g., preview deploy, staging), the API host, the machine-client endpoint, the inbound mail domain, the data API via the client public key, the background-job serve endpoint, and the native build if it is tested.
112
+ - The out-list covers: production, the release branch, the persistent demo tenant, every third party's own platform, and anything not on the in-list.
113
+ - Read the current penetration-testing page of each platform the probes touch: the app host, the database, and the native vendor when the native build is in scope.
114
+ - Record what each allows and the plan tier.
115
+ - **If** a page forbids a probe → do not send it, and mark it `INCONCLUSIVE`.
116
+ - Create two synthetic tenants, attacker and victim, each with the roles the product distinguishes.
117
+ - Issue a machine-client token for each owner where the product has one, on a plan the feature allows.
118
+ - Seed the victim with a few records, one recurring record and an attachment.
119
+ - Do not touch the persistent demo tenant.
120
+ - Read the newest `bkit-audit-security` and `bkit-audit-llm` reports.
121
+ - Give each finding they could not prove a probe.
122
+ - Give each of the model audit's prompt-only rules a probe.
123
+ - Give each trust boundary the threat model names at least one probe.
124
+ - **If** there is no threat model → say so in `Scope`.
125
+ - Before a destructive probe, confirm that no other live test holds the target database, and record the window. Do not wait for a named approver.
126
+ - **If** a later probe degrades the target, touches non-synthetic data, or reaches a third party → stop the remaining probes, and record the stop in `Scope`.
127
+ - Each later probe gets a `Probes` row with: the request with tokens redacted, the response status, the relevant body and the verdict. A `BROKE` row adds the blast radius by reasoning, not by pivoting.
128
+
129
+ **Done when:** `Scope` holds the URL, the commit, the in-list, the out-list, the platform rules, the plan tier, the identities (no tokens) and the suspicion list.
130
+
131
+ - [ ] **Step 3 — Surface:** List the attack surface at this commit: routes, server actions, machine-client tools, webhooks, and the response headers of each in-scope origin. Diff it against the previous report's list. Give everything new at least one probe. **Done when:** `Surface` holds the list and the diff.
132
+ - [ ] **Step 4 — Retest:** Re-run every earlier `BROKE` whose fix has landed, from its recorded reproduction. Mark it `FIXED` or `STILL BROKE`, with the fix commit. Confirm that the regression test the prior run named exists. **If** it does not → route it to `bkit-audit-testing`. **Done when:** `Retests` has a row per prior break, or says `none`.
133
+ - [ ] **Step 5 — Cross-Tenant:** As the attacker, request the victim's records by id on every route that takes one: items, attachments, download URLs, members, invitations and machine-client read tools. A mixed list of own and foreign ids must be refused, not clamped to the attacker's rows. Expected: denial or not-found, and no victim field in any part of the response, errors included. **Done when:** `Probes` has a row per route, in the Step 2 row shape.
134
+ - [ ] **Step 6 — Direct API:** Step 5 goes through the app, and an attacker can skip the app. With the attacker's token and the client public key, ask the data API for the victim's tenant: each tenant-scoped table, privileged routines, GraphQL if enabled, file-storage list and download, and realtime subscribe. Expected: no victim row, object or event. **If** a denial looks like an empty result → send the same request once as the victim, to show it would have returned data. **Done when:** `Probes` has a row per surface, including the victim-control request, or the step is skipped with evidence that the direct API is not exposed.
135
+ - [ ] **Step 7 — Roles:** Inside the attacker tenant, have the low role try what only a higher role may do: invite, remove a member, change the plan, issue a machine-client token, delete a record that is not theirs, and delete the tenant. Check each against the role matrix. **Done when:** `Probes` has a row per operation.
136
+ - [ ] **Step 8 — Removed:** The realistic attacker is a former tenant member. Remove the attacker's second member, then try every way back in: the web session, native cached data and sync, a machine-client token they issued, invitation links they sent, signed attachment URLs they were given, a capability URL (a calendar feed or equivalent), and mail to the tenant address. Expected: every path fails on the next request, and mail from a removed member gets no more trust than a stranger's. **Done when:** `Probes` has a row per path.
137
+ - [ ] **Step 9 — Authentication:** Probe an expired token and a revoked one. A revoked machine token must fail on the next call, with no grace period unless the product records one. A token for a plan that excludes the feature must be refused. Probe a cookie-authenticated write with no `Origin`, and one with a foreign `Origin`. Probe redirect parameters that point off-site. Check that sign-out-all ends every other session. **Done when:** `Probes` has a row per case.
138
+ - [ ] **Step 10 — Inbound:** Send mail to the synthetic tenant's inbound address, from the attacker's address, trying to make the model: delete or change records the message does not mention; leak other records into the reply; fetch an internal address (`http://169.254.169.254/`, localhost, private ranges); claim to be a member (by address or display name) from a domain that fails or lacks SPF and DKIM; and exceed the link and attachment caps. Use a payload corpus (e.g., promptfoo, garak), and record which. On a shared inbound provider, use the environment tag the project documents, so the message cannot land in production. Expected: only the records the message genuinely describes are written, nothing else changes, no internal fetch happens, and every cap fires. Check the action log for what was written. The cost probe crosses one limit, once. **Done when:** `Probes` has a row per attempt, with action-log evidence, or `INCONCLUSIVE` where model spend is unavailable.
139
+ - [ ] **Step 11 — Tools:** With the attacker's token, act as a client that ignores the rules: set fields the allow-list excludes, pass the victim's ids, change a recurring record without the required scope, send oversized arguments, and repeat a create to test the idempotency key. **Done when:** `Probes` has a row per case, or the step is skipped with evidence that there are no machine-client tools.
140
+ - [ ] **Step 12 — Boundaries:** Put script and markup in text fields, and check how they render on the web, in the native client and in a reply. Send injection through the search query and the filters that reach the search routine. Webhook endpoints: no signature must get a denial, and a wrong signature must get the same denial plus an error log. Rate limits: the documented thresholds must fire, then stop. **Done when:** `Probes` has a row per boundary.
141
+ - [ ] **Step 13 — Off-Topic:** For each public free-text model surface (from `bkit-audit-llm` `Job Scope`, or from `Surface` when that report lists none), act as an anonymous or synthetic visitor and send one ask per probe: general coding (e.g., "write a Python function that…"), homework, an essay, and an off-topic ask wrapped in an on-topic frame (e.g., "for my trip, write a script that…"). Then send one greeting as a control. Expected: a redirect per the surface's stated job and no off-topic answer, while the greeting gets a normal reply. **If** an off-topic ask is answered → mark it `BROKE`, and record what was meant to bound it (prompt, grounding gate, classifier). **Done when:** `Probes` has a row per surface x ask, or the step is skipped with evidence that there is no public free-text model surface.
142
+ - [ ] **Step 14 — Standards:** Confirm the current version of each anchor standard, and read what changed since the previous report's version. Give `Standards Coverage` one row per WSTG category (INFO, CONF, IDNT, ATHN, ATHZ, SESS, INPV, ERRH, CRYP, BUSL, CLNT, APIT), and one per ATLAS tactic a model probe touched, each marked checked (naming the step), not applicable (saying why) or finding. Give each bkit anchor (a doc section, rule or issue shape) one row, marked followed (with the step or evidence), not applicable (saying why) or finding. A departure with no recorded reason (e.g., a `docs/decisions.jsonl` row or an accepted-divergence entry) is a finding. Mark each recommended practice the project does not apply as adopt (with a proposed step), reject (saying why) or not applicable. **Done when:** no row is empty.
143
+ - [ ] **Step 15 — Anything Else:** (a) Give a one-line verdict on each change since the previous report's commit that touches the attack surface: routes, server actions, machine-client tools, webhooks, response headers, inbound handling, and what the client public key can reach. The Step 3 diff is the starting list.
144
+ - (b) In a bounded pass of about 30 minutes, note what a senior penetration tester would flag that no step asks about. Read what happened since the previous run (incidents, `bkit-audit-logs` reports, new `docs/failures.jsonl` rows, vendor status incidents), and ask what no step would catch.
145
+ - Probes these passes send follow the Rules, use identities made for this run, and go in `Probes`.
146
+ - Then delete every identity this run created with the guarded delete, which also reaps any tenant it would strand.
147
+ - Confirm that the orphan sweep finds nothing left.
148
+ - Record where the full request and response evidence is kept, for how long, and the redaction applied.
149
+ - `Expected` names where the finding goes, and recommends the safer fix.
150
+ - This run files nothing. It does write the `docs/failures.jsonl` rows.
151
+ - Route each result as follows:
152
+ - `BROKE` → a plan from this report, a `docs/failures.jsonl` row, and a regression test (ideally at the deployed boundary) so that `bkit-audit-testing` keeps it fixed.
153
+ - `HELD` with no test → `bkit-audit-testing`.
154
+ - A model result → `bkit-audit-llm`, against the finding it tested.
155
+ - `STILL BROKE` → the original finding, with the retest and the fix commit.
156
+ - `INCONCLUSIVE` → the next run's Step 2 suspicion list, with what blocked it.
157
+ - `OTHER` → this report, and a second run proposes a verdict.
158
+ - A vulnerability in the database product itself, not in the project's use of it → the vendor, per that vendor's testing page, plus this report.
159
+ - A stop condition → the remaining probes stop, and the stop is recorded in `Scope`.
160
+
161
+ **Done when:** `Beyond the Steps` holds both passes, or says `none`. `Cleanup` confirms that every identity this run created is gone. **If** one class of issue is seen on 2 runs → propose a step for it in `Process Improvements`.
129
162
 
130
163
  ### 🔒 Gate 2: Probes Check
131
164
 
132
- **Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
133
-
134
- - [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
135
- - [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
136
- - [ ] **Target:** no probe against production, the release branch, a third-party platform, or a non-synthetic identity.
137
- - [ ] **Cleanup:** every identity this run created is deleted; no token value in the report.
138
- - [ ] **Gate 2 - Verified:** Every checkbox above independently verified and checked off.
165
+ - [ ] **Steps complete:** every step is `[x]`, or skipped with evidence that its surface is absent.
166
+ - [ ] **Evidence:** every finding cites evidence someone can check again, and the tool that produced it.
167
+ - [ ] **Target:** no probe was sent to production, the release branch, a third-party platform, or a non-synthetic identity.
168
+ - [ ] **Cleanup:** every identity this run created is deleted.
169
+ - [ ] **No tokens:** no token value appears in the report.
170
+ - [ ] **Gate 2 — Verified:** every item above holds.
139
171
 
140
172
  ## Findings
141
173
 
142
- `HELD` probe stays in `Probes`. Every `BROKE` is finding, shares probe ID. `Expected` carries WSTG id, CWE, likelihood and impact rationale. Model finding also names OWASP Top 10 for LLM / agentic applications category and MITRE ATLAS technique — vocabulary `bkit-audit-llm` uses.
174
+ A `HELD` probe stays in `Probes`. Every `BROKE` is a finding, and shares its probe ID. `Expected` carries the WSTG id, the CWE, and the reasoning for likelihood and impact. A model finding also names its OWASP Top 10 for LLM / agentic applications category and its MITRE ATLAS technique, the vocabulary `bkit-audit-llm` uses.
143
175
 
144
176
  <!-- prettier-ignore -->
145
177
  | Severity | Use |
@@ -149,14 +181,14 @@ Verify only when applicable.
149
181
  | `MEDIUM` | A mixed id list is clamped instead of refused; a rate limit or size cap does not fire; markup renders unsanitised on one surface; a public model surface answers an off-topic ask |
150
182
  | `LOW` | Status differs from expected, and the response exposes no data and grants no action |
151
183
 
152
- Scale per `.bkit/jsonl.md` § Severity. Within a severity: cross-tenant first. Break on non-production target keeps severity it would have in production.
184
+ Within a severity, list cross-tenant findings first. A break on the non-production target keeps the severity it would have in production.
153
185
 
154
186
  <!-- prettier-ignore -->
155
187
  | ID | Severity | Verdict | Location | Evidence | Expected |
156
188
  | --- | --- | --- | --- | --- | --- |
157
189
  | PENDING | PENDING | PENDING | PENDING | PENDING | PENDING |
158
190
 
159
- Empty and clean → one row `None`.
191
+ **If** the run finds nothing → write one row: `None`.
160
192
 
161
193
  ## Report
162
194
 
@@ -217,17 +249,17 @@ PENDING
217
249
 
218
250
  ### 🔒 Gate 3: Report Check
219
251
 
220
- **Checkpoint.** Verify and check `[x]` all boxes below, then stop.
221
-
222
- - [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
223
- - [ ] **Summary:** names count per severity and probe counts (`HELD` / `BROKE` / `INCONCLUSIVE`).
224
- - [ ] **Cleanup:** states that every identity this run created is deleted, and where redacted evidence is kept.
225
- - [ ] **Writes:** only this report and template `Project Instructions` changed; throwaway worktrees / remote targets removed.
226
- - [ ] **Process Improvements:** `Universal` = proposed step changes, template untouched; `Project` = edits applied below `bkit:end`; each `none` if empty.
227
- - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
228
- - [ ] **Gate 3 - Verified:** Every checkbox above independently verified and checked off.
229
-
230
- > `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
252
+ - [ ] **No placeholders:** no `PENDING` is left.
253
+ - [ ] **Summary:** `Summary` gives the count per severity.
254
+ - [ ] **Probe counts:** `Summary` gives the probe counts (`HELD` / `BROKE` / `INCONCLUSIVE`).
255
+ - [ ] **Cleanup stated:** `Cleanup` states that every identity this run created is deleted.
256
+ - [ ] **Evidence kept:** `Cleanup` states where the redacted evidence is kept.
257
+ - [ ] **Writes:** this run changed only this report, the template's `Project Instructions` and its own `docs/failures.jsonl` rows.
258
+ - [ ] **Throwaways removed:** every throwaway worktree or remote target is removed.
259
+ - [ ] **Process Improvements:** `Universal` and `Project` are both filled.
260
+ - [ ] **Suggested Issues:** every `MEDIUM`+ finding ID is in exactly one `Suggested Issues` row.
261
+ - [ ] **Next Step:** every `Suggested Issues` row has a `Next Step`.
262
+ - [ ] **Gate 3 — Verified:** every item above holds.
231
263
 
232
264
  <!-- bkit:end -->
233
265