@cbartens/bkit 5.2.4 → 5.4.0

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 (271) hide show
  1. package/.bkit/README.md +27 -11
  2. package/.bkit/core/.agents/context.md +1 -1
  3. package/.bkit/core/.agents/docs.md +1 -1
  4. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +1 -1
  5. package/.bkit/core/.agents/rules.md +18 -1
  6. package/.bkit/core/.bkit/README.md +26 -10
  7. package/.bkit/core/.bkit/cloud.md +40 -39
  8. package/.bkit/core/.bkit/comparison.md +68 -345
  9. package/.bkit/core/.bkit/install.md +16 -9
  10. package/.bkit/core/.bkit/lite.md +73 -0
  11. package/.bkit/core/.bkit/pipeline.md +346 -0
  12. package/.bkit/core/.bkit/prompts.md +90 -74
  13. package/.bkit/core/.bkit/providers.md +42 -23
  14. package/.bkit/core/.bkit/templates.md +138 -19
  15. package/.bkit/core/.bkit/trackers.md +49 -4
  16. package/.bkit/core/.bkit/workflows.md +144 -123
  17. package/.bkit/core/.claude/hooks/bkit-guardrails.cjs +1 -1
  18. package/.bkit/core/.codex/hooks/bkit-guardrails.cjs +7 -4
  19. package/.bkit/core/.cursor/hooks/bkit-guardrails.cjs +8 -5
  20. package/.bkit/core/docs/templates/bkit-audit-accessibility.md +3 -2
  21. package/.bkit/core/docs/templates/bkit-audit-adoption.md +2 -2
  22. package/.bkit/core/docs/templates/bkit-audit-agents.md +1 -1
  23. package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +1 -1
  24. package/.bkit/core/docs/templates/bkit-audit-analytics.md +1 -1
  25. package/.bkit/core/docs/templates/bkit-audit-annotations.md +1 -1
  26. package/.bkit/core/docs/templates/bkit-audit-app-performance.md +1 -1
  27. package/.bkit/core/docs/templates/bkit-audit-app-store.md +1 -1
  28. package/.bkit/core/docs/templates/bkit-audit-architecture.md +1 -1
  29. package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +4 -2
  30. package/.bkit/core/docs/templates/bkit-audit-config.md +3 -2
  31. package/.bkit/core/docs/templates/bkit-audit-cost.md +3 -2
  32. package/.bkit/core/docs/templates/bkit-audit-coverage.md +1 -1
  33. package/.bkit/core/docs/templates/bkit-audit-database.md +3 -2
  34. package/.bkit/core/docs/templates/bkit-audit-dead-code.md +5 -5
  35. package/.bkit/core/docs/templates/bkit-audit-deferrals.md +1 -1
  36. package/.bkit/core/docs/templates/bkit-audit-dependencies.md +26 -21
  37. package/.bkit/core/docs/templates/bkit-audit-documentation.md +1 -1
  38. package/.bkit/core/docs/templates/bkit-audit-duplication.md +2 -2
  39. package/.bkit/core/docs/templates/bkit-audit-failures.md +1 -1
  40. package/.bkit/core/docs/templates/bkit-audit-flakes.md +3 -2
  41. package/.bkit/core/docs/templates/bkit-audit-gates.md +5 -2
  42. package/.bkit/core/docs/templates/bkit-audit-issues.md +3 -2
  43. package/.bkit/core/docs/templates/bkit-audit-llm.md +22 -15
  44. package/.bkit/core/docs/templates/bkit-audit-logs.md +10 -6
  45. package/.bkit/core/docs/templates/bkit-audit-models.md +1 -1
  46. package/.bkit/core/docs/templates/bkit-audit-privacy.md +1 -1
  47. package/.bkit/core/docs/templates/bkit-audit-prompts.md +7 -7
  48. package/.bkit/core/docs/templates/bkit-audit-red-team.md +12 -9
  49. package/.bkit/core/docs/templates/bkit-audit-reliability.md +3 -2
  50. package/.bkit/core/docs/templates/bkit-audit-repo.md +1 -1
  51. package/.bkit/core/docs/templates/bkit-audit-security.md +14 -12
  52. package/.bkit/core/docs/templates/bkit-audit-slop.md +1 -1
  53. package/.bkit/core/docs/templates/bkit-audit-testing.md +10 -8
  54. package/.bkit/core/docs/templates/bkit-audit-usability.md +1 -1
  55. package/.bkit/core/docs/templates/bkit-plan.md +8 -6
  56. package/.bkit/core/engine/checks/after/auth.ts +9 -9
  57. package/.bkit/core/engine/checks/after/ci-yml.ts +14 -12
  58. package/.bkit/core/engine/checks/after/github.ts +29 -120
  59. package/.bkit/core/engine/checks/after/index.ts +2 -2
  60. package/.bkit/core/engine/checks/after/managed.ts +8 -28
  61. package/.bkit/core/engine/checks/after/tools.ts +3 -15
  62. package/.bkit/core/engine/checks/before/context-fetch.ts +1 -21
  63. package/.bkit/core/engine/checks/before/index.ts +7 -43
  64. package/.bkit/core/engine/checks/before/mcp.ts +17 -8
  65. package/.bkit/core/engine/checks/before/repo.ts +9 -12
  66. package/.bkit/core/engine/checks/status-holes.ts +4 -6
  67. package/.bkit/core/engine/checks/tips/catalogue.ts +76 -24
  68. package/.bkit/core/engine/checks/tips/detect.ts +45 -2
  69. package/.bkit/core/engine/checks/tips/index.ts +77 -26
  70. package/.bkit/core/engine/cli.ts +57 -27
  71. package/.bkit/core/engine/commands/analysis.ts +36 -26
  72. package/.bkit/core/engine/commands/comply.ts +42 -32
  73. package/.bkit/core/engine/commands/harvest.ts +12 -12
  74. package/.bkit/core/engine/commands/install/doctor.ts +57 -28
  75. package/.bkit/core/engine/commands/install/install.ts +73 -130
  76. package/.bkit/core/engine/commands/install/uninstall.ts +191 -33
  77. package/.bkit/core/engine/commands/install/upgrade.ts +49 -43
  78. package/.bkit/core/engine/commands/land.ts +156 -0
  79. package/.bkit/core/engine/commands/lib.ts +45 -18
  80. package/.bkit/core/engine/commands/registry.ts +2 -0
  81. package/.bkit/core/engine/commands/tips.ts +12 -5
  82. package/.bkit/core/engine/commands/workflow/branches.ts +386 -286
  83. package/.bkit/core/engine/commands/workflow/counters.ts +21 -12
  84. package/.bkit/core/engine/commands/workflow/disk.ts +556 -0
  85. package/.bkit/core/engine/commands/workflow/fids.ts +46 -0
  86. package/.bkit/core/engine/commands/workflow/issues.ts +73 -28
  87. package/.bkit/core/engine/commands/workflow/ledgers.ts +3 -1
  88. package/.bkit/core/engine/commands/workflow/locks.ts +38 -152
  89. package/.bkit/core/engine/commands/workflow/prs.ts +15 -4
  90. package/.bkit/core/engine/commands/workflow/repo.ts +2 -2
  91. package/.bkit/core/engine/commands/workflow/roadmap.ts +49 -53
  92. package/.bkit/core/engine/commands/workflow/runs.ts +8 -7
  93. package/.bkit/core/engine/commands/workflow/runtime.ts +3 -2
  94. package/.bkit/core/engine/commands/workflow/status.ts +33 -11
  95. package/.bkit/core/engine/commands/workflow/steps.ts +25 -15
  96. package/.bkit/core/engine/commands/workflow/tests.ts +17 -5
  97. package/.bkit/core/engine/commands/workflow/workflows.ts +436 -267
  98. package/.bkit/core/engine/commands/workflow/workstreams.ts +4 -2
  99. package/.bkit/core/engine/commands/workflow/worktrees.ts +24 -6
  100. package/.bkit/core/engine/install/cloud-env.ts +10 -31
  101. package/.bkit/core/engine/install/manifest.ts +14 -7
  102. package/.bkit/core/engine/install/modules/antigravity.ts +15 -26
  103. package/.bkit/core/engine/install/modules/claude.ts +20 -28
  104. package/.bkit/core/engine/install/modules/cloud.ts +5 -2
  105. package/.bkit/core/engine/install/modules/codex.ts +15 -29
  106. package/.bkit/core/engine/install/modules/core.ts +106 -70
  107. package/.bkit/core/engine/install/modules/cursor.ts +6 -20
  108. package/.bkit/core/engine/install/modules/index.ts +7 -1
  109. package/.bkit/core/engine/install/modules/opencode.ts +48 -70
  110. package/.bkit/core/engine/install/network-allowlist.ts +73 -0
  111. package/.bkit/core/engine/install/placeholders.ts +16 -35
  112. package/.bkit/core/engine/install/write.ts +59 -12
  113. package/.bkit/core/engine/ledgers/telemetry.ts +6 -4
  114. package/.bkit/core/engine/render/hosts.ts +47 -67
  115. package/.bkit/core/engine/render/models.ts +29 -11
  116. package/.bkit/core/engine/shared/branches.ts +13 -0
  117. package/.bkit/core/engine/shared/egress.ts +3 -3
  118. package/.bkit/core/engine/shared/json.ts +18 -1
  119. package/.bkit/core/engine/shared/package-json.ts +63 -0
  120. package/.bkit/core/engine/shared/package-roots.ts +0 -10
  121. package/.bkit/core/engine/shared/protected-paths.ts +5 -130
  122. package/.bkit/core/engine/shared/settings.ts +44 -0
  123. package/.bkit/core/engine/shared/timeouts.ts +8 -7
  124. package/.bkit/core/hooks/antigravity-hook.js +1 -0
  125. package/.bkit/core/hooks/guardrails-shell.js +186 -40
  126. package/.bkit/core/hooks/guardrails-tiers.js +5 -78
  127. package/.bkit/core/prompts/bkit-audit-generate.md +103 -7
  128. package/.bkit/core/prompts/bkit-build-challenge-1.md +1 -1
  129. package/.bkit/core/prompts/bkit-build-challenge-2.md +1 -1
  130. package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +1 -1
  131. package/.bkit/core/prompts/bkit-build-challenge-remediate.md +1 -1
  132. package/.bkit/core/prompts/bkit-build-challenge-tests.md +1 -1
  133. package/.bkit/core/prompts/bkit-build-install-skills.md +1 -1
  134. package/.bkit/core/prompts/bkit-build-plan-current.md +1 -1
  135. package/.bkit/core/prompts/bkit-build-plan-execute.md +4 -4
  136. package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +1 -1
  137. package/.bkit/core/prompts/bkit-build-plan-verify.md +2 -2
  138. package/.bkit/core/prompts/bkit-debug-abort-handover.md +1 -1
  139. package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +1 -1
  140. package/.bkit/core/prompts/bkit-debug-failure-remediate.md +1 -1
  141. package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +78 -0
  142. package/.bkit/core/prompts/bkit-debug-failure-soak.md +1 -1
  143. package/.bkit/core/prompts/bkit-debug-summary.md +3 -3
  144. package/.bkit/core/prompts/bkit-design-spike.md +1 -1
  145. package/.bkit/core/prompts/bkit-design-summary.md +2 -2
  146. package/.bkit/core/prompts/bkit-design-update.md +1 -1
  147. package/.bkit/core/prompts/bkit-plan-complexity-check.md +1 -1
  148. package/.bkit/core/prompts/bkit-plan-generate.md +1 -1
  149. package/.bkit/core/prompts/bkit-plan-scope-check-1.md +1 -1
  150. package/.bkit/core/prompts/bkit-plan-scope-check-2.md +1 -1
  151. package/.bkit/core/prompts/bkit-plan-summary.md +1 -1
  152. package/.bkit/core/prompts/bkit-plan-update.md +1 -1
  153. package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +1 -1
  154. package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +1 -1
  155. package/.bkit/core/prompts/bkit-ship-update-docs.md +1 -1
  156. package/.bkit/core/prompts/bkit-utility-update-decisions.md +9 -2
  157. package/.bkit/core/prompts/bkit-utility-update-deferrals.md +9 -2
  158. package/.bkit/core/prompts/bkit-utility-update-documentation.md +2 -1
  159. package/.bkit/core/prompts/bkit-utility-update-failures.md +9 -2
  160. package/.bkit/core/prompts/bkit-utility-update-knowledge.md +9 -2
  161. package/.bkit/core/prompts/bkit-utility-update-roadmap.md +11 -4
  162. package/.bkit/core/workflows/bkit-auto.md +2 -2
  163. package/.bkit/core/workflows/bkit-build.md +10 -10
  164. package/.bkit/core/workflows/bkit-debug.md +80 -44
  165. package/.bkit/core/workflows/bkit-design.md +22 -13
  166. package/.bkit/core/workflows/bkit-plan.md +33 -16
  167. package/.bkit/core/workflows/bkit-ship.md +87 -98
  168. package/.bkit/shared/.claude/bkit-cloud.md +58 -25
  169. package/.bkit/shared/.claude/settings.json +19 -0
  170. package/.bkit/shared/.cursor/mcp.json +2 -1
  171. package/.bkit/shared/.opencode/opencode.json +19 -1
  172. package/.bkit/shared/docs/deployments.md +49 -29
  173. package/.bkit/shared/docs/security.md +8 -6
  174. package/.bkit/shared/docs/testing.md +9 -5
  175. package/.bkit/shared/gitignore +1 -2
  176. package/.bkit/templates/.cursor/Dockerfile +30 -16
  177. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +78 -0
  178. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +91 -0
  179. package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +56 -0
  180. package/.bkit/templates/.github/renovate.json5 +91 -12
  181. package/.bkit/templates/.github/workflows/bkit-ci.yml +73 -55
  182. package/.bkit/templates/.github/workflows/bkit-cloud.yml +3 -1
  183. package/.bkit/templates/.github/workflows/bkit-renovate.yml +8 -1
  184. package/.bkit/templates/.github/workflows/bkit-trivy.yml +67 -0
  185. package/.bkit/templates/.husky/pre-commit +6 -0
  186. package/.bkit/templates/.husky/pre-push +15 -3
  187. package/.bkit/templates/.lintstagedrc.json +5 -1
  188. package/.bkit/templates/.oxlintrc.json +21 -0
  189. package/.bkit/templates/docs/capabilities.md +1 -1
  190. package/.bkit/templates/scripts/ci/check-capstone.mjs +176 -0
  191. package/.bkit/templates/scripts/ci/check-capstone.test.mjs +311 -0
  192. package/.bkit/templates/scripts/cleanup/bkit-disk-prune.machine.mjs +197 -0
  193. package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +164 -0
  194. package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +2 -2
  195. package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +43 -20
  196. package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +33 -11
  197. package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -2
  198. package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +5 -5
  199. package/.bkit/templates/scripts/graphify/bkit-graphify.sh +79 -19
  200. package/CHANGELOG.md +98 -3
  201. package/README.md +252 -122
  202. package/dist/checks/after/auth.js +10 -11
  203. package/dist/checks/after/ci-yml.js +11 -14
  204. package/dist/checks/after/github.js +32 -125
  205. package/dist/checks/after/index.js +3 -2
  206. package/dist/checks/after/managed.js +8 -24
  207. package/dist/checks/after/tools.js +3 -16
  208. package/dist/checks/before/context-fetch.js +1 -21
  209. package/dist/checks/before/index.js +6 -42
  210. package/dist/checks/before/mcp.js +14 -9
  211. package/dist/checks/before/repo.js +8 -11
  212. package/dist/checks/status-holes.js +5 -7
  213. package/dist/checks/tips/catalogue.js +65 -18
  214. package/dist/checks/tips/detect.js +41 -2
  215. package/dist/checks/tips/index.js +61 -25
  216. package/dist/cli.js +52 -26
  217. package/dist/commands/analysis.js +21 -5
  218. package/dist/commands/comply.js +40 -31
  219. package/dist/commands/harvest.js +12 -13
  220. package/dist/commands/install/doctor.js +55 -23
  221. package/dist/commands/install/install.js +72 -122
  222. package/dist/commands/install/uninstall.js +165 -31
  223. package/dist/commands/install/upgrade.js +46 -39
  224. package/dist/commands/land.js +129 -0
  225. package/dist/commands/lib.js +41 -16
  226. package/dist/commands/registry.js +2 -0
  227. package/dist/commands/tips.js +10 -3
  228. package/dist/commands/workflow/branches.js +303 -248
  229. package/dist/commands/workflow/counters.js +17 -7
  230. package/dist/commands/workflow/disk.js +452 -0
  231. package/dist/commands/workflow/fids.js +39 -0
  232. package/dist/commands/workflow/issues.js +63 -27
  233. package/dist/commands/workflow/ledgers.js +3 -1
  234. package/dist/commands/workflow/locks.js +35 -130
  235. package/dist/commands/workflow/prs.js +8 -5
  236. package/dist/commands/workflow/repo.js +2 -2
  237. package/dist/commands/workflow/roadmap.js +50 -57
  238. package/dist/commands/workflow/runs.js +5 -5
  239. package/dist/commands/workflow/runtime.js +3 -2
  240. package/dist/commands/workflow/status.js +32 -12
  241. package/dist/commands/workflow/steps.js +19 -11
  242. package/dist/commands/workflow/tests.js +16 -3
  243. package/dist/commands/workflow/workflows.js +390 -249
  244. package/dist/commands/workflow/workstreams.js +4 -2
  245. package/dist/commands/workflow/worktrees.js +15 -6
  246. package/dist/install/cloud-env.js +10 -23
  247. package/dist/install/manifest.js +14 -7
  248. package/dist/install/modules/antigravity.js +15 -26
  249. package/dist/install/modules/claude.js +17 -21
  250. package/dist/install/modules/cloud.js +6 -2
  251. package/dist/install/modules/codex.js +15 -29
  252. package/dist/install/modules/core.js +95 -63
  253. package/dist/install/modules/cursor.js +6 -9
  254. package/dist/install/modules/index.js +6 -1
  255. package/dist/install/modules/opencode.js +41 -72
  256. package/dist/install/network-allowlist.js +62 -0
  257. package/dist/install/placeholders.js +16 -35
  258. package/dist/install/write.js +55 -15
  259. package/dist/ledgers/telemetry.js +5 -4
  260. package/dist/render/hosts.js +30 -55
  261. package/dist/render/models.js +20 -9
  262. package/dist/shared/branches.js +11 -0
  263. package/dist/shared/egress.js +0 -2
  264. package/dist/shared/json.js +14 -0
  265. package/dist/shared/package-json.js +61 -0
  266. package/dist/shared/package-roots.js +0 -8
  267. package/dist/shared/protected-paths.js +5 -122
  268. package/dist/shared/settings.js +23 -1
  269. package/dist/shared/timeouts.js +8 -7
  270. package/package.json +21 -17
  271. package/.bkit/core/.agents/shortcuts.md +0 -73
@@ -41,7 +41,7 @@
41
41
  - **Banned shapes:** a parenthetical explaining why a clause exists, an inline comment justifying behaviour, a note on what a previous version did.
42
42
  - **Cross-prompt alignment:** Check for shared instructions and change in all prompts using them. Rules binding every agent live once in `.agents/rules.md` § `Universal Rules` — reached via the `**Rules:**` EXECUTION PROTOCOL bullet, never copied per prompt.
43
43
  - **Shared wording:** sentences shared by 5+ prompts live in `.bkit/wording.md`; change them there, move the old wording to the clause's `retired` block, run `pnpm wording:sync`. never hand-edit one copy.
44
- - **Self-contained:** every prompt must stand alone; inline all instructions; no file references. Exceptions: `.agents/rules.md`, `.agents/docs.md`, `.agents/shortcuts.md`, `*.jsonl` ledgers, supplied templates (plan, audit) — those carry their own rules.
44
+ - **Self-contained:** every prompt must stand alone; inline all instructions; no file references. Exceptions: `.agents/rules.md`, `.agents/docs.md`, `.bkit/lite.md`, `*.jsonl` ledgers, supplied templates (plan, audit) — those carry their own rules.
45
45
  - **Template owns its rules:** prompt filling or auditing a supplied template names the section + ONLY what template lacks (input handling, carry-forward, ledger writes, severity it assigns); never restate template rules. Agent that does not read the template → inline.
46
46
  - **Removal = delete:** drop instruction outright; never leave removal explanations.
47
47
  - **Enforced elsewhere:** step numbers by `.bkit/core/engine/audits/repo/shipped-docs-refs.test.ts`, the managed-version marker by `.bkit/core/engine/audits/workflows/prompt-notation.test.ts`, shared sentences, the `**Rules:**` bullet, and the `.agents/rules.md` group headings by `.bkit/core/engine/tools/wording.test.ts` — the GateGuard advisory omits them because a test is the gate.
@@ -124,7 +124,7 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
124
124
  | `model` | Explicit Claude model pin per the effort mapping table above. Locks the model independent of the orchestrator's session default — without it, subagents inherit user's Claude Code default and `xhigh` thinking depth + 1M context disappear if the user runs Sonnet. | Brittle by version (must update on every model rev), but explicit and discoverable. Never use family alias (`opus` / `sonnet`) — they don't lock context-window variant. |
125
125
  | `tools` | Minimum capability sandbox. Enforced on Claude (native). Cursor: `bkit install` T3 transform passes the field through verbatim, but Cursor CLI 2026.10.01 does not enforce it (measured: a `tools: [Read]` subagent still has `Shell`, `Write`, `StrReplace`, and every MCP tool via `CallDynamicTool`). Removing `Edit`/`Bash` makes an agent provably non-mutating on Claude only. | Add `WebFetch`/`WebSearch` only for genuine ecosystem research (`bkit-design-review-1/2`) or to pin a probe against vendor docs before running it (`bkit-design-spike`). |
126
126
  | `permissionMode: acceptEdits` | End-to-end runs of `/design`/`/plan`/`/build`/`/debug`/`/ship` would break if mid-workflow prompt blocked an agent. Bash auto-approve surface lives in `.claude/settings.json` (`workflows.md` § Permissions) | Never deviate inside the pipeline; one-off ad-hoc invocations may use stricter modes. |
127
- | `maxTurns` | Pure runaway-loop safety cap, not a workload budget. 4 tiers (S=50 / M=100 / L=150 / XL=300). Hitting the cap means the agent is definitely stuck (tight retry loop, infinite re-read pattern, etc.), not "tight on a complex run." | Cap by **tier** (see § `maxTurns` calibration). Per-agent assignment in § Models. |
127
+ | `maxTurns` | Pure runaway-loop safety cap, not a workload budget. 4 tiers (S=50 / M=100 / L=200 / XL=400). Hitting the cap means the agent is definitely stuck (tight retry loop, infinite re-read pattern, etc.), not "tight on a complex run." | Cap by **tier** (see § `maxTurns` calibration). Per-agent assignment in § Models. |
128
128
 
129
129
  ### Effort tiers
130
130
 
@@ -133,7 +133,7 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
133
133
  | --- | --- | --- |
134
134
  | `low` | Pure synthesis with no verdict riding on it. | (none currently) |
135
135
  | `medium` | Single-shot writers, scope audits, skill curators, fix executors with clear input. Some `medium`-effort agents pin opus (depth-sensitive lens) — see Models table footnote. | `bkit-debug-abort-handover`, `bkit-plan-complexity-check`, `bkit-plan-scope-check-1`, `bkit-plan-scope-check-2`, `bkit-plan-review-2`, `bkit-design-brainstorm-ideate-2`, `bkit-design-review-2`, `bkit-build-install-skills`, `bkit-utility-compress-markdown`, `bkit-utility-update-documentation` |
136
- | `high` | Adversarial review, parallel-fan-out high-effort slots, observability instrumentation, feasibility research, ledger / roadmap judgement against the codebase. Also phase-verdict summaries (`*-summary`, haiku model) and source modifiers with test loops (sonnet model). | `*-summary`, `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-build-challenge-tests`, `bkit-debug-failure-remediate`, `bkit-ship-conflict-resolve`, `bkit-build-plan-verify`, `bkit-build-plan-current`, `bkit-build-challenge-1`, `bkit-build-challenge-2`, `bkit-design-brainstorm-ideate-1`, `bkit-design-brainstorm-ideate-3`, `bkit-design-organise`, `bkit-design-review-1`, `bkit-design-spike`, `bkit-plan-review-1`, `bkit-plan-review-3`, `bkit-plan-complexity-split`, `bkit-ship-update-docs`, `bkit-ship-deferred-sweep`, `bkit-utility-update-deferrals`, `bkit-utility-update-failures`, `bkit-utility-update-decisions`, `bkit-utility-update-knowledge`, `bkit-utility-update-roadmap` |
136
+ | `high` | Adversarial review, parallel-fan-out high-effort slots, observability instrumentation, feasibility research, ledger / roadmap judgement against the codebase. Also phase-verdict summaries (`*-summary`, haiku model) and source modifiers with test loops (sonnet model). | `*-summary`, `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-build-challenge-tests`, `bkit-debug-failure-reproduce`, `bkit-debug-failure-remediate`, `bkit-ship-conflict-resolve`, `bkit-build-plan-verify`, `bkit-build-plan-current`, `bkit-build-challenge-1`, `bkit-build-challenge-2`, `bkit-design-brainstorm-ideate-1`, `bkit-design-brainstorm-ideate-3`, `bkit-design-organise`, `bkit-design-review-1`, `bkit-design-spike`, `bkit-plan-review-1`, `bkit-plan-review-3`, `bkit-plan-complexity-split`, `bkit-ship-update-docs`, `bkit-ship-deferred-sweep`, `bkit-utility-update-deferrals`, `bkit-utility-update-failures`, `bkit-utility-update-decisions`, `bkit-utility-update-knowledge`, `bkit-utility-update-roadmap` |
137
137
  | `xhigh` | Top-of-pipeline synthesizers and highest-leverage adversarial / diagnostic agents — depth here compounds downstream. Model-gated (Opus-only on current models); pin `model: opus` if dispatched from a Sonnet orchestrator. | `bkit-design-generate`, `bkit-plan-generate`, `bkit-plan-update`, `bkit-design-update`, `bkit-audit-generate`, `bkit-build-challenge-reconcile`, `bkit-debug-failure-diagnose`, `bkit-debug-failure-soak` |
138
138
  | `max` | Reserved — only if `xhigh` proves insufficient on a recurring failure mode. Costliest tier; one-shot orchestrator-level work only. Lazy-escalate from `xhigh` based on observed truncation, never preemptively. | (none currently) |
139
139
 
@@ -148,11 +148,12 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
148
148
  | Stub-replace + log-append reviewer | `Read, Grep, Glob, Write, Edit, Bash` | `bkit-build-challenge-1`, `bkit-build-challenge-2`, `bkit-build-plan-verify`, `bkit-build-plan-current`, `bkit-ship-deferred-sweep` |
149
149
  | Doc rewriter (cp + Edit) | `Read, Grep, Glob, Edit, Bash` | `bkit-design-update`, `bkit-plan-update`, `bkit-build-challenge-reconcile` |
150
150
  | Doc writer (with shell) | `Read, Grep, Glob, Write, Edit, Bash` | `bkit-design-organise`, `bkit-ship-update-docs` |
151
- | Source modifier (with test gate) | `Read, Grep, Glob, Write, Edit, Bash` | `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-build-challenge-tests`, `bkit-debug-failure-remediate`, `bkit-ship-conflict-resolve` |
151
+ | Source modifier (with test gate) | `Read, Grep, Glob, Write, Edit, Bash` | `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-build-challenge-tests`, `bkit-debug-failure-reproduce`, `bkit-debug-failure-remediate`, `bkit-ship-conflict-resolve` |
152
152
  | Skill-installer / Bash-only utility | `Read, Grep, Glob, Bash` | `bkit-build-install-skills` |
153
153
  | Tracker reader (read-only MCP) | `Read, Grep, Glob, Write, Edit, Bash` + per tracker: github `mcp__github__list_issues, mcp__github__issue_read`; linear `mcp__linear__list_issues, mcp__linear__get_issue`; none — | `bkit-utility-update-roadmap` |
154
154
  | Ledger updater | `Read, Grep, Glob, Write, Edit, Bash` | `bkit-utility-update-decisions`, `bkit-utility-update-deferrals`, `bkit-utility-update-failures`, `bkit-utility-update-knowledge` |
155
- | Investigator (web access) | `Read, Grep, Glob, Write, Edit, Bash, WebFetch, WebSearch` | `bkit-design-review-1`, `bkit-design-review-2`, `bkit-design-spike`, `bkit-debug-failure-diagnose`, `bkit-debug-failure-soak`, `bkit-audit-generate` |
155
+ | Investigator (web access) | `Read, Grep, Glob, Write, Edit, Bash, WebFetch, WebSearch` | `bkit-design-review-1`, `bkit-design-review-2`, `bkit-design-spike`, `bkit-debug-failure-diagnose`, `bkit-debug-failure-soak` |
156
+ | Investigator + tracker comment | `Read, Grep, Glob, Write, Edit, Bash, WebFetch, WebSearch` + per tracker: github `mcp__github__add_issue_comment`; linear `mcp__linear__save_comment`; none — | `bkit-audit-generate` |
156
157
 
157
158
  **Language-server lookups.** Every agent carrying `Grep` except `bkit-utility-compress-markdown` and `bkit-build-install-skills` (neither reads source) also lists `mcp__serena__*` directly after `Glob`. A Claude Code subagent with a `tools:` list reaches an MCP tool only when the list names it; an entry for an unwired server is dropped silently and the agent still starts (probed Claude Code 2.1.295 + Serena 1.7.0: explicit names, `mcp__serena__*`, and bare `mcp__serena` all grant; omitted → none). Wildcard grants every tool Serena advertises, so the template `.serena/project.yml` `excluded_tools` list is what keeps Serena lookup-only — Serena edits bypass GateGuard (`Edit|Write|MultiEdit` matcher). Measured with that template: `claude-code` and `ide` contexts advertise lookups only; `codex` advertises the excluded tools but refuses each call. Product-named only here — the template ships with bkit (`.bkit/templates.md` § Serena); prompt bodies and the `.agents/rules.md` `Language server first` / `Code reads` rules stay capability-worded. Codex ignores `tools:`, so a wired server is reachable regardless. Cursor passes the entry through verbatim and ignores `tools:`, so a wired server is reachable regardless (probed Cursor CLI 2026.10.01; with the template `.serena/project.yml`, `--context ide` offers lookups only). OpenCode respells `mcp__<server>__<tool>` as `<server>_<tool>` (its MCP tool ids) in its `tools` map → `serena_*`.
158
159
 
@@ -162,15 +163,15 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
162
163
 
163
164
  `maxTurns` = max **agent turns** (assistant messages); each turn may emit multiple parallel tool calls. **Runaway-loop safety cap, not workload budget.** Runtime bounded by universal 3600s step timeout (`workflows.md` § Execution Protocol).
164
165
 
165
- **Same philosophy as timeout:** 3600s ~2x typical 30 min runtime — hit means something wrong. `maxTurns` tiers are S=50 / M=100 / L=150 / XL=300, per-agent in § Models:
166
+ **Same philosophy as timeout:** 3600s ~2x typical 30 min runtime — hit means something wrong. `maxTurns` tiers are S=50 / M=100 / L=200 / XL=400, per-agent in § Models:
166
167
 
167
168
  <!-- prettier-ignore -->
168
169
  | Tier | Cap | Typical work | Use for | Examples |
169
170
  | --- | --- | --- | --- | --- |
170
- | **S** | **50** | 3-10 turns | Pure synthesizers, scope checks, single-pass utilities, install / cleanup, summary writers. | `*-summary`, `bkit-debug-abort-handover`, `bkit-plan-complexity-check`, `bkit-plan-scope-check-*`, `bkit-build-install-skills` |
171
- | **M** | **100** | 5-25 turns | Reviewers, doc writers, multi-doc, web investigators, surgical-edit appliers, single-pass source modifiers (no test loop). | `bkit-design-brainstorm-ideate-*`, `bkit-design-review-*`, `bkit-design-spike`, `bkit-design-generate`, `bkit-design-organise`, `bkit-design-update`, `bkit-plan-review-*`, `bkit-plan-generate`, `bkit-plan-update`, `bkit-plan-complexity-split`, `bkit-build-challenge-1`, `bkit-build-challenge-2`, `bkit-build-challenge-reconcile`, `bkit-build-challenge-tests`, `bkit-build-plan-verify`, `bkit-debug-failure-diagnose`, `bkit-ship-update-docs`, `bkit-ship-deferred-sweep`, `bkit-utility-update-*`, `bkit-utility-compress-markdown` |
172
- | **L** | **150** | 30-60 turns | Source modifiers with test loops, plan executor — iterative edit→`pnpm bkit:gate:static-unit`→edit cycles. | `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-debug-failure-remediate`, `bkit-debug-failure-soak`, `bkit-ship-conflict-resolve` |
173
- | **XL** | **300** | 60-180 turns | Whole-surface sweeps: every probe step of one audit template against repo and live systems. | `bkit-audit-generate` |
171
+ | **S** | **50** | 3-10 turns | Pure synthesizers reading 1-3 run artifacts and writing one verdict. | `*-summary` |
172
+ | **M** | **100** | 5-25 turns | Reviewers and generators reading a few docs and writing one, scope / complexity checks, single-pass utilities, install, handover writers. | `bkit-design-brainstorm-ideate-*`, `bkit-design-review-*`, `bkit-design-generate`, `bkit-design-organise`, `bkit-plan-review-*`, `bkit-plan-complexity-check`, `bkit-plan-complexity-split`, `bkit-plan-scope-check-*`, `bkit-build-install-skills`, `bkit-debug-abort-handover`, `bkit-utility-compress-markdown` |
173
+ | **L** | **200** | 30-60 turns | Source modifiers with test loops, plan executor — iterative edit→`pnpm bkit:gate:static-unit`→edit cycles; probe-code runners; investigators sweeping a diff, its callers or the codebase; whole-doc rewriters; per-cycle doc sync. | `bkit-build-plan-execute`, `bkit-build-plan-gaps-remediate`, `bkit-build-challenge-remediate`, `bkit-debug-failure-remediate`, `bkit-debug-failure-soak`, `bkit-ship-conflict-resolve`, `bkit-design-spike`, `bkit-build-challenge-1`, `bkit-build-challenge-2`, `bkit-build-challenge-reconcile`, `bkit-build-challenge-tests`, `bkit-build-plan-verify`, `bkit-build-plan-current`, `bkit-debug-failure-reproduce`, `bkit-debug-failure-diagnose`, `bkit-ship-deferred-sweep`, `bkit-plan-generate`, `bkit-plan-update`, `bkit-design-update`, `bkit-ship-update-docs` |
174
+ | **XL** | **400** | 60-180 turns | Whole-surface sweeps: every probe step of one audit template against repo and live systems; every row of a jsonl ledger, the roadmap board or the doc catalog re-checked against code, docs and tracker. | `bkit-audit-generate`, `bkit-utility-update-*` |
174
175
 
175
176
  **Tier assignment is canonical** — per-agent rows in § Models. Cap hit at any tier → agent stuck (retry loop, infinite re-read) — orchestrator verdict-validation retry handles partial recovery.
176
177
 
@@ -178,7 +179,7 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
178
179
 
179
180
  Canonical per-agent metadata — **single source of truth for model per agent**. **Keyed on PROVIDER, not host** — a model ID belongs to the gateway serving it → shared provider = one column, never two; table never grows as hosts x providers. Columns: `Anthropic` (Claude Code's pinned provider — locked ID, session-independent), `Cursor` (Cursor's pinned provider; cross-family diversity), `OpenAI` (Codex), `Google` (Antigravity), one per opencode provider (`OpenRouter`, `Ollama`, …). `bkit install --opencode=<provider>` reads the matching column; every allowlisted provider ships one.
180
181
 
181
- **Cells = BARE provider-scoped model ID** (`kimi-k2.7-code`, `moonshotai/kimi-k3`) — never a provider prefix. Host-format prefixes are added at render by `formatModelPin`, which also maps key `opencode-zen` → opencode's own id `opencode`. A prefixed cell (`opencode/kimi-k2.7-code`) double-prefixes.
182
+ **Cells = BARE provider-scoped model ID** (`deepseek-v4.1-flash`, `moonshotai/kimi-k3`) — never a provider prefix. Host-format prefixes are added at render by `formatModelPin`, which also maps key `opencode-zen` → opencode's own id `opencode`. A prefixed cell (`opencode/deepseek-v4.1-flash`) double-prefixes.
182
183
 
183
184
  > **`OpenAI` column — PROVISIONAL, not parity-proven.** Every other gateway column = live catalog probe + per-model tool-calling smoke. `OpenAI` cells mapped from documented role only (`gpt-6-astra` deep reasoning, `gpt-5.6-terra` balanced default). Haiku cells are board-picked: `gpt-6-luna` (LiveBench 51.2; `gpt-5.6-luna` measures 48.4), 2026-10-09, existence via models.dev only — no OpenAI key to probe. Re-pin from a real probe before relying on them. `gpt-5.4` / `gpt-5.4-mini` retired 2026-08-31.
184
185
 
@@ -186,63 +187,64 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
186
187
 
187
188
  > **Context-window note:** Claude Code `model:` is the API ID. `claude-opus-5-5` and `claude-sonnet-5-5` are 1M context. Haiku pins `claude-haiku-5-5` (1M context). xhigh agents pin `claude-opus-5-5`.
188
189
  >
189
- > **opencode model IDs:** Per-provider column; full provider-prefixed ID (`<provider>/<model-id>`, e.g. `openrouter/moonshotai/kimi-k3`, `ollama/kimi-k2.7-code`). `bkit install --opencode=<provider>` installs column verbatim. Allowlisted: `openrouter`, `ollama`, `opencode-zen` + `opencode-go` (both `BKIT_OPENCODE_API_KEY`). **All four ship curated columns below.** Zen: models.dev id `opencode/<id>`; Go: `opencode-go/<id>`. Both gateways = built-ins (apiKey only). **`/zen/v1/models` REST probe cannot see Go-only models — models.dev is source of truth.** See `.bkit/providers.md` § Models.
190
+ > **opencode model IDs:** Per-provider column; full provider-prefixed ID (`<provider>/<model-id>`, e.g. `openrouter/moonshotai/kimi-k3`, `ollama/deepseek-v4.1-flash`). `bkit install --opencode=<provider>` installs column verbatim. Allowlisted: `openrouter`, `ollama`, `opencode-zen` + `opencode-go` (both `BKIT_OPENCODE_API_KEY`). **All four ship curated columns below.** Zen: models.dev id `opencode/<id>`; Go: `opencode-go/<id>`. Both gateways = built-ins (apiKey only). **`/zen/v1/models` REST probe cannot see Go-only models — models.dev is source of truth.** See `.bkit/providers.md` § Models.
190
191
  >
191
192
  > **Columns target scores, not tiers.** opencode columns do **not** mirror the Claude ladder: each cell is the cheapest model reaching that tier's target on the parity board (`providers.md` § Selecting pins); chain-of-thought reasoner for convergent agents (risk / diagnosis lens). Per-row columns; any cell re-pinnable.
192
193
  >
193
- > **Per-tier quality targets; cheapest sufficient pin.** Tier cells are not the same rung of each provider's ladder — each is the **cheapest model that reaches that tier's Claude score** on LiveBench Agentic Coding (opus target **65.2**, sonnet target **59.4**, haiku target **~51** — `claude-haiku-5-5` 51.4 at `xhigh`, run at `high`; opus and sonnet targets stay the `claude-opus-5` / `claude-sonnet-5` scores because LiveBench's 5.5 rows land level (opus) or don't read cleanly (sonnet) — `providers.md` § Agentic-coding parity board; process in § Selecting pins). Two consequences pull opposite ways: a provider whose ceiling sits under the sonnet target **collapses opus+sonnet onto that ceiling** (spreading them buys nothing and costs quality on the sonnet half), while **haiku cells stay cheap** because a low-cost model already clears the haiku bar. **Claude is never a pin on an opencode column** — those columns exist to carry work when the Claude quota is spent, so a Claude model there defeats the purpose regardless of score. **opus** → `openrouter` `deepseek-v4.1-flash` (77.3); `ollama` `kimi-k2.7-code` (45.7); `opencode-zen` `deepseek-v4.1-flash` (77.3 — re-pinned from `kimi-k2.7-code` because 2.0 rejects a `variant:` the model does not expose, and `kimi-k2.7-code` exposes none; Zen bills V4.1 Flash at $0.30/$1.20, so this cell costs more than the old one); `opencode-go` `deepseek-v4-pro` (42.6). **sonnet** → `openrouter` same `deepseek-v4.1-flash` (clears 59.4); every other provider's ceiling sits under the sonnet target, so opus+sonnet stay collapsed there. **haiku** → `openrouter` + `opencode-zen` `glm-5.3-flash` (56.8); `ollama` + `opencode-go` `deepseek-v4.1-flash` (77.3 — cheaper than GLM on those two); `OpenAI` `gpt-6-luna` (51.2). **convergent** → `openrouter` `kimi-k3` (62.2); `deepseek-v4-pro` on `ollama` + both gateways (the undated `deepseek-v4-pro` slug is frozen on the 0423 snapshot at 42.6). **gpt-oss pinned nowhere** — `gpt-oss-120b` measures **~10 est**, below every tier target including haiku. **`ollama` subscription:** every tier needs a **paid plan** (`kimi-k2.7-code` / `deepseek-v4-pro` / `deepseek-v4.1-flash`); the free `qwen3.5:397b` / `gpt-oss:20b` are unmeasured or far below target — free-tier users re-pin in § Model Overrides and accept unverified quality. **`opencode-go`** carries no `gemini-*` (it lists `gpt-6-luna`, `gpt-5.6-luna` and `claude-haiku-5-5`; Claude is still never pinned); its DeepSeek models need the workspace privacy setting on "Global regions"; prefer Go 5h window pins. Re-pin via § Model Overrides or models.dev / provider `/v1/models` (`providers.md`).
194
+ > **Per-tier quality targets; cheapest sufficient pin.** Tier cells are not the same rung of each provider's ladder — each is the **cheapest model that reaches that tier's Claude score** on LiveBench Agentic Coding (opus target **65.2**, sonnet target **59.4**, haiku target **~51** — `claude-haiku-5-5` 51.4 at `xhigh`, run at `high`; opus and sonnet targets stay the `claude-opus-5` / `claude-sonnet-5` scores because LiveBench's 5.5 rows land level (opus) or don't read cleanly (sonnet) — `providers.md` § Agentic-coding parity board; process in § Selecting pins). Two consequences pull opposite ways: a provider whose ceiling sits under the sonnet target **collapses opus+sonnet onto that ceiling** (spreading them buys nothing and costs quality on the sonnet half), while **haiku cells stay cheap** because a low-cost model already clears the haiku bar. **Claude is never a pin on an opencode column** — those columns exist to carry work when the Claude quota is spent, so a Claude model there defeats the purpose regardless of score. **opus** → `openrouter` `deepseek-v4.1-flash` (77.3); `ollama` `deepseek-v4.1-flash` (77.3); `opencode-zen` `deepseek-v4.1-flash` (77.3 — re-pinned from `kimi-k2.7-code` because 2.0 rejects a `variant:` the model does not expose, and `kimi-k2.7-code` exposes none; Zen bills V4.1 Flash at $0.30/$1.20, so this cell costs more than the old one); `opencode-go` `deepseek-v4.1-flash` (77.3). **sonnet** → same `deepseek-v4.1-flash` on every opencode column (clears 59.4). **haiku** → `openrouter` + `opencode-zen` `glm-5.3-flash` (56.8); `ollama` + `opencode-go` `deepseek-v4.1-flash` (77.3 — cheaper than GLM on those two); `OpenAI` `gpt-6-luna` (51.2). **convergent** → `kimi-k3` (62.2) on every opencode column; on both gateways it bills $3/$15 per Mtok, the column's most expensive pin. **gpt-oss pinned nowhere** — `gpt-oss-120b` measures **~10 est**, below every tier target including haiku. **`ollama` subscription:** every tier needs a **paid plan** (`deepseek-v4.1-flash` / `kimi-k3`); the free `qwen3.5:397b` / `gpt-oss:20b` are unmeasured or far below target — free-tier users re-pin in § Model Overrides and accept unverified quality. **`opencode-go`** carries no `gemini-*` (it lists `gpt-6-luna`, `gpt-5.6-luna` and `claude-haiku-5-5`; Claude is still never pinned); its DeepSeek models need the workspace privacy setting on "Global regions"; prefer Go 5h window pins. Re-pin via § Model Overrides or models.dev / provider `/v1/models` (`providers.md`).
194
195
 
195
196
  <!-- prettier-ignore -->
196
197
  | Prompt | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Google | Effort | Max Turns | Role |
197
198
  | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
198
- | `bkit-design-brainstorm-ideate-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 1 (pragmatic lens) |
199
- | `bkit-design-brainstorm-ideate-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | parallel slot 2 (optimal-tradeoff lens; Composer vs Grok siblings on Cursor; cross-tier on Claude) |
200
- | `bkit-design-brainstorm-ideate-3` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `deepseek-v4-pro` | `deepseek-v4-pro` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 3 (risk-premortem lens) |
201
- | `bkit-design-review-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | design review slot 1 (web search + feasibility analysis) |
202
- | `bkit-design-review-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | design review slot 2 (Composer vs Grok sibling on Cursor; cross-tier on Claude) |
203
- | `bkit-design-spike` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | settle review-named unknowns with throwaway probe code (conditional step) |
204
- | `bkit-design-update` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | merge review critiques into design (whole-doc rewrite — needs depth) |
205
- | `bkit-design-organise` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | decompose reviewed design into dependency-annotated workstreams; coverage self-verify + DAG cycle detection |
199
+ | `bkit-design-brainstorm-ideate-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 1 (pragmatic lens) |
200
+ | `bkit-design-brainstorm-ideate-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | parallel slot 2 (optimal-tradeoff lens; Composer vs Grok siblings on Cursor; cross-tier on Claude) |
201
+ | `bkit-design-brainstorm-ideate-3` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `kimi-k3` | `kimi-k3` | `kimi-k3` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 3 (risk-premortem lens) |
202
+ | `bkit-design-review-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | design review slot 1 (web search + feasibility analysis) |
203
+ | `bkit-design-review-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | design review slot 2 (Composer vs Grok sibling on Cursor; cross-tier on Claude) |
204
+ | `bkit-design-spike` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | settle review-named unknowns with throwaway probe code (conditional step) |
205
+ | `bkit-design-update` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | merge review critiques into design (whole-doc rewrite — needs depth) |
206
+ | `bkit-design-organise` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | decompose reviewed design into dependency-annotated workstreams; coverage self-verify + DAG cycle detection |
206
207
  | `bkit-design-summary` | `claude-haiku-5-5` | `composer-2.5` | `z-ai/glm-5.3-flash` | `deepseek-v4.1-flash` | `glm-5.3-flash` | `deepseek-v4.1-flash` | `gpt-6-luna` | `gemini-3.8-flash` | `high` | 50 | summary writer |
207
- | `bkit-design-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | generate design from brainstorms (top-of-pipeline synthesizer; whole-doc rewrite) |
208
- | `bkit-plan-complexity-check` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 50 | complexity check |
209
- | `bkit-plan-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | plan draft generator (top-of-pipeline synthesizer) |
210
- | `bkit-audit-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 300 | audit report from one template (top-of-pipeline synthesizer) |
211
- | `bkit-plan-review-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | review slot 1 (tightness + design-coverage) |
212
- | `bkit-plan-review-2` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `medium` | 100 | review slot 2 (dependency-correctness + design-coverage; depth-sensitive lens — both opus) |
213
- | `bkit-plan-review-3` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `deepseek-v4-pro` | `deepseek-v4-pro` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | review slot 3 (regression-risk + design-coverage) |
214
- | `bkit-plan-scope-check-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `medium` | 50 | scope audit slot 1 (mechanical audit — medium effort) |
215
- | `bkit-plan-scope-check-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 50 | scope audit slot 2 (Composer vs Grok sibling on Cursor) |
216
- | `bkit-plan-complexity-split` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | split large plan |
208
+ | `bkit-design-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | generate design from brainstorms (top-of-pipeline synthesizer; whole-doc rewrite) |
209
+ | `bkit-plan-complexity-check` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | complexity check |
210
+ | `bkit-plan-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | plan draft generator (top-of-pipeline synthesizer) |
211
+ | `bkit-audit-generate` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 400 | audit report from one template (top-of-pipeline synthesizer) |
212
+ | `bkit-plan-review-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | review slot 1 (tightness + design-coverage) |
213
+ | `bkit-plan-review-2` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `medium` | 100 | review slot 2 (dependency-correctness + design-coverage; depth-sensitive lens — both opus) |
214
+ | `bkit-plan-review-3` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `kimi-k3` | `kimi-k3` | `kimi-k3` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | review slot 3 (regression-risk + design-coverage) |
215
+ | `bkit-plan-scope-check-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `medium` | 100 | scope audit slot 1 (mechanical audit — medium effort) |
216
+ | `bkit-plan-scope-check-2` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | scope audit slot 2 (Composer vs Grok sibling on Cursor) |
217
+ | `bkit-plan-complexity-split` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | split large plan |
217
218
  | `bkit-plan-summary` | `claude-haiku-5-5` | `composer-2.5` | `z-ai/glm-5.3-flash` | `deepseek-v4.1-flash` | `glm-5.3-flash` | `deepseek-v4.1-flash` | `gpt-6-luna` | `gemini-3.8-flash` | `high` | 50 | summary writer |
218
- | `bkit-plan-update` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | merge review + scope critiques into plan (whole-doc rewrite — needs depth) |
219
- | `bkit-build-install-skills` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 50 | skill identifier |
220
- | `bkit-build-challenge-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 1 (bug-hunting lens) |
221
- | `bkit-build-challenge-2` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `deepseek-v4-pro` | `deepseek-v4-pro` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | parallel slot 2 (security lens; depth-sensitive — both opus) |
222
- | `bkit-build-challenge-reconcile` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | merge parallel challenge findings (whole-doc rewrite) |
223
- | `bkit-build-challenge-tests` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 100 | test generator (source modifier, no test loop) |
224
- | `bkit-build-plan-execute` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 150 | task executor (source modifier with test loop; ceiling — split if exceeded) |
225
- | `bkit-build-challenge-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 150 | fix challenge findings (source modifier with test loop) |
226
- | `bkit-build-plan-gaps-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 150 | fix verification gaps (source modifier with test loop) |
219
+ | `bkit-plan-update` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | merge review + scope critiques into plan (whole-doc rewrite — needs depth) |
220
+ | `bkit-build-install-skills` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | skill identifier |
221
+ | `bkit-build-challenge-1` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | parallel slot 1 (bug-hunting lens) |
222
+ | `bkit-build-challenge-2` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `kimi-k3` | `kimi-k3` | `kimi-k3` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | parallel slot 2 (security lens; depth-sensitive — both opus) |
223
+ | `bkit-build-challenge-reconcile` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | merge parallel challenge findings (whole-doc rewrite) |
224
+ | `bkit-build-challenge-tests` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | test generator (source modifier, no test loop) |
225
+ | `bkit-build-plan-execute` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | task executor (source modifier with test loop; ceiling — split if exceeded) |
226
+ | `bkit-build-challenge-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | fix challenge findings (source modifier with test loop) |
227
+ | `bkit-build-plan-gaps-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | fix verification gaps (source modifier with test loop) |
227
228
  | `bkit-build-summary` | `claude-haiku-5-5` | `composer-2.5` | `z-ai/glm-5.3-flash` | `deepseek-v4.1-flash` | `glm-5.3-flash` | `deepseek-v4.1-flash` | `gpt-6-luna` | `gemini-3.8-flash` | `high` | 50 | summary writer |
228
- | `bkit-build-plan-verify` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | verify impl vs plan |
229
- | `bkit-build-plan-current` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | judge plan vs changes landed since its base commit |
230
- | `bkit-debug-abort-handover` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 50 | handover writer |
231
- | `bkit-debug-failure-diagnose` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `deepseek-v4-pro` | `deepseek-v4-pro` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 100 | failure diagnosis (Final-strategy attempts especially benefit from depth before human handover) |
232
- | `bkit-debug-failure-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 150 | implement diagnosis fixes (source modifier with test loop) |
233
- | `bkit-debug-failure-soak` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `deepseek-v4-pro` | `deepseek-v4-pro` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 150 | soak fix — one accumulating-context instrument-or-fix step per iteration against the live boundary (orchestrator re-runs tests + loops) |
229
+ | `bkit-build-plan-verify` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | verify impl vs plan |
230
+ | `bkit-build-plan-current` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | judge plan vs changes landed since its base commit |
231
+ | `bkit-debug-abort-handover` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | handover writer |
232
+ | `bkit-debug-failure-reproduce` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | failing tests from a bug report, no fix; opus over the sonnet test-writer tier — an off-symptom test sends the fix loop after the wrong bug |
233
+ | `bkit-debug-failure-diagnose` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `kimi-k3` | `kimi-k3` | `kimi-k3` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | failure diagnosis (Final-strategy attempts especially benefit from depth before human handover) |
234
+ | `bkit-debug-failure-remediate` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | implement diagnosis fixes (source modifier with test loop) |
235
+ | `bkit-debug-failure-soak` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `moonshotai/kimi-k3` | `kimi-k3` | `kimi-k3` | `kimi-k3` | `gpt-6-astra` | `gemini-3.8-pro` | `xhigh` | 200 | soak fix — one accumulating-context instrument-or-fix step per iteration against the live boundary (orchestrator re-runs tests + loops) |
234
236
  | `bkit-debug-summary` | `claude-haiku-5-5` | `composer-2.5` | `z-ai/glm-5.3-flash` | `deepseek-v4.1-flash` | `glm-5.3-flash` | `deepseek-v4.1-flash` | `gpt-6-luna` | `gemini-3.8-flash` | `high` | 50 | summary writer |
235
237
  | `bkit-ship-summary` | `claude-haiku-5-5` | `composer-2.5` | `z-ai/glm-5.3-flash` | `deepseek-v4.1-flash` | `glm-5.3-flash` | `deepseek-v4.1-flash` | `gpt-6-luna` | `gemini-3.8-flash` | `high` | 50 | summary writer |
236
- | `bkit-ship-update-docs` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | sync cataloged docs (multi-doc writer) |
237
- | `bkit-ship-conflict-resolve` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 150 | mechanical rebase-conflict resolver (source modifier with test loop) |
238
- | `bkit-ship-deferred-sweep` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | pre-merge completeness gate — intended-vs-actual + declared-deferral resurface |
239
- | `bkit-utility-update-deferrals` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | deferrals update |
240
- | `bkit-utility-update-failures` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | failures update |
241
- | `bkit-utility-update-decisions` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | decisions update |
242
- | `bkit-utility-update-knowledge` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | knowledge update |
243
- | `bkit-utility-update-roadmap` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 100 | roadmap analysis |
244
- | `bkit-utility-compress-markdown` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | token-optimize markdown |
245
- | `bkit-utility-update-documentation` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `deepseek-v4.1-flash` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | doc sync (multi-doc writer) |
238
+ | `bkit-ship-update-docs` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | sync cataloged docs (multi-doc writer) |
239
+ | `bkit-ship-conflict-resolve` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `high` | 200 | mechanical rebase-conflict resolver (source modifier with test loop) |
240
+ | `bkit-ship-deferred-sweep` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 200 | pre-merge completeness gate — intended-vs-actual + declared-deferral resurface |
241
+ | `bkit-utility-update-deferrals` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 400 | deferrals update |
242
+ | `bkit-utility-update-failures` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 400 | failures update |
243
+ | `bkit-utility-update-decisions` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 400 | decisions update |
244
+ | `bkit-utility-update-knowledge` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 400 | knowledge update |
245
+ | `bkit-utility-update-roadmap` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | `high` | 400 | roadmap analysis |
246
+ | `bkit-utility-compress-markdown` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 100 | token-optimize markdown |
247
+ | `bkit-utility-update-documentation` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | `medium` | 400 | doc sync (multi-doc writer) |
246
248
 
247
249
  **Effort vs maxTurns vs model — three independent knobs:**
248
250
 
@@ -255,7 +257,7 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
255
257
 
256
258
  ### Live model-ID verification
257
259
 
258
- > **Verified against live provider APIs** (`providers.md` § Per-provider live model lookup). Last verification: 2026-10-09 (Claude; haiku cells of every column — existence only, no tool-call smoke: Ollama needs a paid plan, Zen balance zero, no Go subscription, no OpenAI key); 2026-10-06 (Cursor); 2026-09-16 (OpenRouter column); 2026-07-25 (remaining columns).
260
+ > **Verified against live provider APIs** (`providers.md` § Per-provider live model lookup). Last verification: 2026-10-19 (Ollama column — existence via `/api/tags`, no tool-call smoke: no Ollama key; OpenCode Zen + Go opus/sonnet/convergent — existence via models.dev); 2026-10-09 (Claude; haiku cells of every column — existence only, no tool-call smoke: Ollama needs a paid plan, Zen balance zero, no Go subscription, no OpenAI key); 2026-10-06 (Cursor); 2026-09-16 (OpenRouter column); 2026-07-25 (remaining columns).
259
261
  >
260
262
  > - **Claude** (`/v1/models`) — pins `claude-opus-5-5` / `claude-sonnet-5-5` / `claude-haiku-5-5`. Opus 5, Sonnet 5 and Haiku 4.5 remain listed; not pinned.
261
263
  > - **Cursor** (`/v0/models`) — **defaults = first-party pool only:** `cursor-grok-4.5-high` (depth / synthesizers / parallel diversity) + `composer-2.5` (volume / build+ship orchestrators). Catalog has **no** `cursor-grok-4.7` and **no** Opus 5.5 / Sonnet 5.5 IDs. API-pool IDs present and **not pinned**: `claude-opus-5-thinking-high`, `claude-sonnet-5-thinking-high`/`-xhigh`, `gpt-5.6-*`, `claude-fable-5-thinking-high`/`-xhigh`. Opt in via § Model Overrides.
@@ -264,12 +266,12 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
264
266
  > **OpenAI-compatible providers curated + tool-call-smoked** (`tools:` chat / completions round-trip per pin, confirming `tool_calls` — `/models` existence ≠ tool-calls):
265
267
  >
266
268
  > - **OpenRouter** (`/api/v1/models`, public) — `deepseek/deepseek-v4.1-flash` (opus+sonnet, 77.3, 16+ endpoints), `z-ai/glm-5.3-flash` (haiku, 56.8, 27 endpoints), `moonshotai/kimi-k3` (convergent, 62.2, 17 endpoints). All three auto-cache — `providers.md` § Selecting pins. (Tool-call smoke 403 `Key limit exceeded` — existence-verified; smoke deferred.)
267
- > - **Ollama** (`/v1/models`) — `kimi-k2.7-code` (opus+sonnet), `deepseek-v4.1-flash` (haiku, 2026-10-09), `deepseek-v4-pro` (convergent). Every tier needs a paid plan.
269
+ > - **Ollama** (`/v1/models`) — `deepseek-v4.1-flash` (opus+sonnet+haiku, 77.3), `kimi-k3` (convergent, 62.2). Every tier needs a paid plan. (Existence-verified via `/api/tags` 2026-10-19; smoke deferred.)
268
270
  >
269
271
  > **opencode gateways — TWO providers; catalogs from models.dev (not `/zen/v1/models`).** `/zen/v1/models` = Zen only; CANNOT see Go-only models — models.dev source of truth (`opencode` = Zen, `opencode-go` = Go).
270
272
  >
271
- > - **`opencode-zen`** (`https://opencode.ai/zen/v1`) — full gateway; `opencode/kimi-k2.7-code` (opus+sonnet), `glm-5.3-flash` (haiku), `deepseek-v4-pro` (convergent). `qwen3.6-plus` not pinned — strictly dominated (41.4 at $1.55/task vs k2.7-code's 45.7 at $0.39). models.dev validated (Zen balance zero; smoke on Go).
272
- > - **`opencode-go`** (`https://opencode.ai/zen/**go**/v1` — nested under `/zen/`) — open-weight budget plan. `deepseek-v4-pro` (opus+sonnet+convergent), `deepseek-v4.1-flash` (haiku). `minimax-m3` / `qwen3.7-plus` not pinned — v4-pro scores higher at a third of the cost (42.6 at $0.14 vs 40.7 at $0.42). Prefer Go 5h window pins. No `gemini-*`; never pin its `gpt-*` / `claude-*`.
273
+ > - **`opencode-zen`** (`https://opencode.ai/zen/v1`) — full gateway; `deepseek-v4.1-flash` (opus+sonnet), `glm-5.3-flash` (haiku), `kimi-k3` (convergent, 62.2). `kimi-k2.7-code` / `qwen3.6-plus` not pinned — dominated by V4.1 Flash (77.3 at $0.06/task vs 45.7 at $0.39 / 41.4 at $1.55). models.dev validated (Zen balance zero; smoke on Go).
274
+ > - **`opencode-go`** (`https://opencode.ai/zen/**go**/v1` — nested under `/zen/`) — open-weight budget plan. `deepseek-v4.1-flash` (opus+sonnet+haiku, 77.3), `kimi-k3` (convergent, 62.2 — $3/$15 per Mtok, the heaviest draw on the Go 5h window). `minimax-m3` / `qwen3.7-plus` not pinned — both score under V4.1 Flash at higher cost (40.7 at $0.42 for `minimax-m3`; `qwen3.7-plus` unmeasured). Prefer Go 5h window pins. No `gemini-*`; never pin its `gpt-*` / `claude-*`.
273
275
 
274
276
  ### Orchestrators (slash commands)
275
277
 
@@ -278,11 +280,11 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
278
280
  <!-- prettier-ignore -->
279
281
  | Orchestrator | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Google | Role |
280
282
  | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
281
- | `/design` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `kimi-k2.7-code` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | Synthesizes conflicting brainstorms; resolves design ambiguity. |
282
- | `/plan` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `kimi-k2.7-code` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | Decides single vs split; merges review (triplet) + scope-check (pair) critiques. |
283
- | `/debug` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `kimi-k2.7-code` | `deepseek-v4-pro` | `gpt-6-astra` | `gemini-3.8-pro` | Picks remediation path under uncertainty; Standard / Pivot / Final escalation. |
284
- | `/build` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `kimi-k2.7-code` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | Fixed pipeline: dispatch → verify → challenge → tests → summary. Subagents own the heavy reasoning (`bkit-build-challenge-1`/`-2`/`-reconcile`, `bkit-build-plan-verify` are `high`/`medium`/`xhigh` effort). |
285
- | `/ship` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `kimi-k2.7-code` | `kimi-k2.7-code` | `deepseek-v4-pro` | `gpt-5.6-terra` | `gemini-3.8-pro` | Mostly mechanical: merge + archive + parallel docs / summary. |
283
+ | `/design` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | Synthesizes conflicting brainstorms; resolves design ambiguity. |
284
+ | `/plan` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | Decides single vs split; merges review (triplet) + scope-check (pair) critiques. |
285
+ | `/debug` | `claude-opus-5-5` | `cursor-grok-4.5-high` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-6-astra` | `gemini-3.8-pro` | Picks remediation path under uncertainty; Standard / Pivot / Final escalation. |
286
+ | `/build` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | Fixed pipeline: dispatch → verify → challenge → tests → summary. Subagents own the heavy reasoning (`bkit-build-challenge-1`/`-2`/`-reconcile`, `bkit-build-plan-verify` are `high`/`medium`/`xhigh` effort). |
287
+ | `/ship` | `claude-sonnet-5-5` | `composer-2.5` | `deepseek/deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `deepseek-v4.1-flash` | `gpt-5.6-terra` | `gemini-3.8-pro` | Mostly mechanical: merge + archive + parallel docs / summary. |
286
288
 
287
289
  **Rule:** Opus where orchestrator resolves ambiguity; Sonnet for defined sequence. **If** Sonnet orchestrator skips Failure Path branches or mis-routes verify gaps → escalate Opus.
288
290
 
@@ -304,14 +306,14 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
304
306
  | `bkit-design-spike` | Conditional — runs only when `bkit-design-review-1` sets `Spike` = TRUE. Restates each unknown as a falsifiable claim, writes the smallest probe that could disprove it under `docs/plans/{YYYYMM}/logs/{FID}/spike/`, runs it, records captured output verbatim. Settles claims by evidence only — never infers a result from source reading, never simulates an unavailable service. PASS / CONCERNS / FAIL where FAIL = a design assumption is disproven (Step 8 revises against it) and CONCERNS = unsettleable this run (assumption carried forward unproven); per-claim `SETTLED` / `DISPROVEN` / `BLOCKED` stays in the body. Disproof needs evidence that an honest attempt failed — "could not get it working" is `BLOCKED`, never `DISPROVEN`, and no claim may be weakened or stubbed to make a probe pass. Probe code is throwaway and confined to the artifact tree; never touches tracked source or a repo manifest. |
305
307
  | `bkit-design-update` | Apply CRITICAL items and OPTIONAL items judged on merit from both reviews; whole-doc rewrite of design. Open questions a finding adds or rewords carry options, `Recommended` and `Default if unanswered`; untouched regions stay verbatim. |
306
308
  | `bkit-design-organise` | Decompose `design-v2-reviewed.md` into dependency-annotated workstreams (`WS-1`, `WS-2`, …); inline `Requires` per workstream; FAIL if cycles detected. `## Suggested Workstreams` is the suggestion. Workflow Step 11 posts that list on the parent issue. It never creates tracker issues. |
307
- | `bkit-design-summary` | Read-only verdict on design doc + spike. `Outstanding Questions` surfaces each open question with its options, `Recommended` and `Default if unanswered` verbatim from the artifact — never generated here, since a summary-only recommendation is discarded the moment `bkit-plan-generate` reads the artifact. Which option is right stays verdict-neutral; a question still left bare is a CONCERNS-level content issue — the backstop for a bare-question finding `bkit-design-update` skipped on merit. Unchecked human-confirmation gates never downgrade the verdict and land in `Action Items` on every verdict — gating that section on CONCERNS / FAIL left a PASS note nowhere to go. |
309
+ | `bkit-design-summary` | Read-only verdict on design doc + spike. `Outstanding Questions` surfaces each open question with its options, `Recommended` and `Default if unanswered` verbatim from the artifact — never generated here, since a summary-only recommendation is discarded the moment `bkit-plan-generate` reads the artifact. Which option is right stays verdict-neutral; a question still left bare is a CONCERNS-level content issue — the backstop for a bare-question finding `bkit-design-update` skipped on merit. Unchecked human-confirmation gates never downgrade the verdict and land in `Action Items` on every verdict — gating that section on CONCERNS / FAIL left a PASS note nowhere to go. With 2+ suggested workstreams it asks whether to file one issue each (shape per `.bkit/trackers.md` § Issue shapes, filed in `Requires` order so blocker numbers exist) and points `/bkit-plan` at the first root workstream's new issue, not the design issue, so each workstream gets its own smaller plan. |
308
310
 
309
311
  ## Plan Phase
310
312
 
311
313
  <!-- prettier-ignore -->
312
314
  | Agent | Scope |
313
315
  | --- | --- |
314
- | `bkit-plan-generate` | Read design and / or audit reports + template + docs → write new plan draft. Design absent and audits present is valid. Audit contract: if input includes audit-scope directives, plan covers only those findings; the rest of each report is context only, not backlog. Workstream contract: if input includes `**Workstream:**` directive, plan covers only that workstream's `## Scope` content unless stated otherwise; surface `**Requires:**` at top of plan. Process = one step per major template section in **dependency (authoring) order, not template document order** — derived sections (Breaking Changes, Supersession, Security, Docs, Rollback) follow Architecture rather than preceding it: Context → Acceptance Scenario → Derived Test Matrix → Open Questions → Pre-Flight → Alternatives → Data Schema → Reuse Inventory → Architecture (+ `decisions.jsonl`) → Breaking Changes → Supersession → Security → Docs → Rollback → Out of Scope → Suggested Scope Expansion → Agent Execution Runbook (pick tests from matrix only; each row → exactly one task; every task has `**Done when:**`) → Verification. Human-confirmation checkboxes stay unchecked at generate. Every `Open Questions & Assumptions` question carries 2-3 concrete options with trade-offs, a `Recommended` option and a `Default if unanswered` (design's answer carried forward where it has one); a bare question is not acceptable output. `Out of Scope` entries must be `Exempt` (genuinely-additive), else a runbook task. `Suggested Scope Expansion` filled per template (candidates, not tasks); no tracker / ledger scan here — surface overlaps come from the orchestrator Fetch Context step via `bkit-plan-review-1`. |
316
+ | `bkit-plan-generate` | Read design and / or audit reports + template + docs → write new plan draft. Design absent and audits present is valid. Neither present → the issue is the source: a change-shape issue's `Narrative`, `Success Criteria`, `Edge Cases`, matrix rows and tasks carry over verbatim (template § `Spec`). Audit contract: if input includes audit-scope directives, plan covers only those findings; the rest of each report is context only, not backlog. Workstream contract: if input includes `**Workstream:**` directive, plan covers only that workstream's `## Scope` content unless stated otherwise; surface `**Requires:**` at top of plan. Process = one step per major template section in **dependency (authoring) order, not template document order** — derived sections (Breaking Changes, Supersession, Security, Docs, Rollback) follow Architecture rather than preceding it: Context → Acceptance Scenario → Derived Test Matrix → Open Questions → Pre-Flight → Alternatives → Data Schema → Reuse Inventory → Architecture (+ `decisions.jsonl`) → Breaking Changes → Supersession → Security → Docs → Rollback → Out of Scope → Suggested Scope Expansion → Agent Execution Runbook (pick tests from matrix only; each row → exactly one task; every task has `**Done when:**`) → Verification. Human-confirmation checkboxes stay unchecked at generate. Every `Open Questions & Assumptions` question carries 2-3 concrete options with trade-offs, a `Recommended` option and a `Default if unanswered` (design's answer carried forward where it has one); a bare question is not acceptable output. `Out of Scope` entries must be `Exempt` (genuinely-additive), else a runbook task. `Suggested Scope Expansion` filled per template (candidates, not tasks); no tracker / ledger scan here — surface overlaps come from the orchestrator Fetch Context step via `bkit-plan-review-1`. |
315
317
  | `bkit-plan-review-1` | Read-only critique — tightness lens; effort slot 1 (`high`). Parallel with `-2` and `-3`. Missing or vague `**Done when:**` on any task → CRITICAL. `Blocking` out-of-scope deferral (in-scope work parked in `Out of Scope`) → CRITICAL. Audits `Open Questions & Assumptions` format — question missing options, `Recommended` or `Default if unanswered` → OPTIONAL (mirrors `bkit-design-review-2` on the design side). Surfaces `Suggested Scope Expansion` candidates from the `related-*.md` context. FAIL only for broken template structure (sections missing / reordered) — content gaps, drift included, are CRITICAL → CONCERNS so `bkit-plan-update` repairs them; `-2` shares the mapping. |
316
318
  | `bkit-plan-review-2` | Same scope — dependency-correctness lens; effort slot 2 (`medium` effort, opus model — depth-sensitive lens). Plans carry no dependency fields, so the graph is derived: what each task produces and consumes, read against runbook order (template: build order). A consumer before its producer, or a prerequisite no task produces and the repo lacks, is CRITICAL. Reading declared `Requires:` / `After:` fields instead found no edges on every real plan and passed unchecked. |
317
319
  | `bkit-plan-review-3` | Same scope — regression-risk lens; effort slot 3 (`high`). |
@@ -329,8 +331,8 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
329
331
  | --- | --- |
330
332
  | `bkit-build-plan-current` | Judge whether changes landed on `origin/dev` since the plan's `bkit:anchor` `baseSha` leave its tasks executable. Derives its own changed-path list from `BASE_SHA` (orchestrator-supplied via Context), intersects it against the paths each task depends on, and reads per-path diffs for the intersection only — no whole-range diff, no path outside it. Same output shape as `bkit-build-challenge-*`: header count + one append-only findings section. `Executable` tasks are not findings and are not logged; `Reword` / `Broken` are, and `Affected` = their count. PASS = no affected task; CONCERNS = any `Reword`; FAIL = any `Broken`. All three are advisory — build proceeds on every verdict and `@bkit-build-plan-execute` reads the findings as its currency input. Judges the plan against the codebase — the design doc is not an input and a superseded design is not a finding. Commit distance and elapsed time never carry the verdict. Does not revise the plan: remediation is a `/bkit-plan` re-run, never `bkit-plan-update` from build. |
331
333
  | `bkit-build-install-skills` | Identify and install relevant skills via `npx skills find`/`add`: quality-hurdle the source (official publisher, or 1000+ installs / 100+ stars), install one named skill per gap, report provenance. |
332
- | `bkit-build-plan-execute` | Execute plan tasks sequentially; per task naming `Test first` tests: tests + stubs first, then the red command the orchestrator supplies in Context (`bkit tests red`) once per test — never the task's code before every red is recorded; skipped for tasks logged `DONE — already landed`; refused as `passed` → `BLOCKED` (never undo code to force a red); other refusals → fix test / stub and re-run; `bkit:test:file` not declared → `red not enforced`; could not run → `BLOCKED` (`.bkit/workflows.md` § Test-first). Branches on the outcome the command prints, not its exit code; honours plan `Reuse Inventory` at the only point the decision can still be quietly discarded — `EXTEND` row modifies named artifact, never a parallel file; reusable artifact found mid-build folds in, never forks; reads each task's `**Done when:**` line as the completion criterion to satisfy; modify source; write stub artifact first then incremental `## Task Log` entries. No plan file → `build-input-*.md` is the plan; tasks = its requested outcomes; outcome as worded is the bar. Reads `build-plan-current.md` when present: findings are fact, plan is intent — `Reword` tasks build at the paths the report names as current, `Broken` tasks whose work already landed log `DONE — already landed`, the rest build the intent against current code. Never edits the plan file; tasks absent from the findings follow plan wording verbatim. Does not tick plan checkboxes (verify owns that). Does not write `docs/deferrals.jsonl` — a blocked task is a `BLOCKED` log line for verify to catch, not a deferral. |
333
- | `bkit-build-plan-verify` | Verify implementation vs plan; writes Plan Verification log. Ticks plan `[ ]`→`[x]` only when the task's `**Done when:**` criterion is satisfied in the codebase and the orchestrator's test-first audit report (`bkit tests green`) shows no gap for it — `not-green` fixable; `test-changed` / `red-mismatch` judged from the diff; `red-mismatch` for a planned test renamed or moved and passing now → no gap; `no-red` on an already-landed task (plan-currency `Broken` + execute `DONE — already landed`) → no gap; other `no-red` and the plan-defect kinds not fixable — a `BLOCKED` log line or a deferral row never discharges a task, so unfinished work routes to `@bkit-build-plan-gaps-remediate` in-loop instead of surfacing at ship. Missing `**Done when:**` on any plan-file task → FAIL (template structure broken; remediation cannot recover). No plan file → `build-input-*.md` is the plan, never created or ticked; outcome as worded is the bar, so missing `Done when` alone is not FAIL (the request was never reviewed). |
334
+ | `bkit-build-plan-execute` | Execute plan tasks sequentially; per task naming `Test first` tests: tests + stubs first, then the red command the orchestrator supplies in Context (`bkit tests red`) once per test — never the task's code before every red is recorded; skipped for tasks logged `DONE — already landed`; refused as `passed` → `BLOCKED` (never undo code to force a red); other refusals → fix test / stub and re-run; `bkit:test:file` not declared → `red not enforced`; could not run → `BLOCKED` (`.bkit/workflows.md` § Test-first). Branches on the outcome the command prints, not its exit code; honours plan `Reuse Inventory` at the only point the decision can still be quietly discarded — `EXTEND` row modifies named artifact, never a parallel file; reusable artifact found mid-build folds in, never forks; reads each task's `**Done when:**` line as the completion criterion to satisfy; modify source; write stub artifact first then incremental `## Task Log` entries. No plan file → `build-input-*.md` is the plan; tasks = its `**Task N:**` lines when present (reds recorded as for a plan, numbers kept), else its requested outcomes; outcome as worded is the bar when no `Done when` is written. Reads `build-plan-current.md` when present: findings are fact, plan is intent — `Reword` tasks build at the paths the report names as current, `Broken` tasks whose work already landed log `DONE — already landed`, the rest build the intent against current code. Never edits the plan file; tasks absent from the findings follow plan wording verbatim. Does not tick plan checkboxes (verify owns that). Does not write `docs/deferrals.jsonl` — a blocked task is a `BLOCKED` log line for verify to catch, not a deferral. |
335
+ | `bkit-build-plan-verify` | Verify implementation vs plan; writes Plan Verification log. Ticks plan `[ ]`→`[x]` only when the task's `**Done when:**` criterion is satisfied in the codebase and the orchestrator's test-first audit report (`bkit tests green`) shows no gap for it — `not-green` fixable; `test-changed` / `red-mismatch` judged from the diff; `red-mismatch` for a planned test renamed or moved and passing now → no gap; `no-red` on an already-landed task (plan-currency `Broken` + execute `DONE — already landed`) → no gap; other `no-red` and the plan-defect kinds not fixable — a `BLOCKED` log line or a deferral row never discharges a task, so unfinished work routes to `@bkit-build-plan-gaps-remediate` in-loop instead of surfacing at ship. Missing `**Done when:**` on any plan-file task → FAIL (template structure broken; remediation cannot recover). No plan file → `build-input-*.md` is the plan, never created or ticked; its `**Task N:**` lines, when present, are the tasks and `tests green --brief=` audits their reds; outcome as worded is the bar when no `Done when` is written, so missing `Done when` alone is not FAIL (the request was never reviewed). |
334
336
  | `bkit-build-plan-gaps-remediate` | Fix specific gaps from latest verify log + boundary gate log failures (red sub-plan boundary; that gate MUST pass too); Standard / Pivot / Final escalation. |
335
337
  | `bkit-build-challenge-1` | Adversarial review of `git diff origin/dev..HEAD` — bug-hunting lens; effort slot 1 (`high`). Parallel with `-2`. Writes findings, each tagged `class: mechanical\|architectural`. Never references sibling output (circular reasoning guard). |
336
338
  | `bkit-build-challenge-2` | Same as `-1` — security lens; effort slot 2 (`high` on Claude / opus — depth-sensitive; Grok on Cursor — first-party depth, same native pool as `-1`). |
@@ -346,9 +348,10 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
346
348
  <!-- prettier-ignore -->
347
349
  | Agent | Scope |
348
350
  | --- | --- |
351
+ | `bkit-debug-failure-reproduce` | Bug report, no failing test → co-located tests failing on the reported symptoms, lowest tier reaching it; no implementation changes. Max 3 rewrites / 3 paths; not reproduced → test changes removed, `Reproduced: NO`. `Mode: SOAK` → tests repeat the scenario until they fail reliably. Wired into `/bkit-debug` § Failure Reproduce on `[repro]` + first-attempt PASS; `YES` → Run Tests records the red, or passes with no fix → Summary (`CONCERNS`: `Reproduced: YES` with no remediate / soak log); `NO` → Summary. |
349
352
  | `bkit-debug-failure-diagnose` | Investigate test / CI failure → diagnosis log; no fixes. Standard / Pivot / Final by attempt. Folds `docs/knowledge.jsonl` by `key`, highest `ts` wins → reads only winning rows where `status` is `ACTIVE` or absent → cites matching entries in `## Prior Knowledge` → uses them to seed hypotheses. Output uses append-only ReAct `Hypothesis {N}` blocks; refuted hypotheses must remain. |
350
353
  | `bkit-debug-failure-remediate` | Apply diagnosis fix; lint / typecheck / test gate; may append `knowledge.jsonl`/`decisions.jsonl`. |
351
- | `bkit-debug-failure-soak` | One accumulating context across iterations (reads its prior `debug-failure-soak-*-log.md`); applies the single next instrument-or-fix step against the failing boundary; refuses to theorise; adds `[DEBUG-OBSERVE]` scaffolding and strips every marker before declaring a fix (no-leak). Wired into `/bkit-debug` § Step 7 (`DEBUG_MODE` = SOAK); the orchestrator re-runs the tests and loops it within `SOAK_ATTEMPT` (`MAX_SOAK_ATTEMPT`, reset to 0 on each SOAK entry). Flat append-only `DONE`/`BLOCKED` log. |
354
+ | `bkit-debug-failure-soak` | One accumulating context across iterations (reads its prior `debug-failure-soak-*-log.md`); applies the single next instrument-or-fix step against the failing boundary; refuses to theorise; adds `[DEBUG-OBSERVE]` scaffolding and strips every marker before declaring a fix (no-leak). Wired into `/bkit-debug` § Failure Remediate Soak (`DEBUG_MODE` = SOAK); the orchestrator re-runs the tests and loops it within `SOAK_ATTEMPT` (`MAX_SOAK_ATTEMPT`, reset to 0 on each SOAK entry). Flat append-only `DONE`/`BLOCKED` log. |
352
355
  | `bkit-debug-abort-handover` | Read all prior diagnose / remediate / verify logs → handover doc + `deferrals.jsonl` append. Called from build / debug / ship Failure Paths. |
353
356
  | `bkit-debug-summary` | Read-only verdict on debug loop outcome. |
354
357
 
@@ -367,7 +370,7 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
367
370
  <!-- prettier-ignore -->
368
371
  | Agent | Scope |
369
372
  | --- | --- |
370
- | `bkit-audit-generate` | Read one `docs/templates/bkit-audit-*.md` and run its probe steps against the repo. Write the filled template to `docs/audits/{YYYYMM}/{slug}.md` (`{slug}` = template basename without `bkit-audit-`). **If** that month already has this slug → `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Report = template up to `bkit:end`. Right after creating the stub it runs `bkit branches anchor-stamp --base-sha=<HEAD> --base-ref=<branch>`, so the audited commit and the bkit release the report came from sit in the same `bkit:anchor` block design and plan docs carry (`.bkit/workflows.md` § Anchor Block) — top of file, machine-readable, the next run reads it as the previous report's commit; an outdated release also gets a visible `Outdated bkit` line under the block, written by the stamp. The agent runs the stamp itself because audits have no orchestrator; the block is still tool-written, never hand-written. Writes only the report, `docs/failures.jsonl` rows (`workflow: "audit"`, `step: "audit-{slug}"`; one per `MEDIUM`+ finding, reusing any open row's `key` for the same problem whichever workflow wrote it, closing only open `audit-{slug}-` rows a rerun no longer finds; skipped by templates that audit the ledgers themselves, `.bkit/jsonl.md`), and the template's consumer-owned `Project Instructions` (below `bkit:end`), which it reads first and refines each run — exact commands, paths, tool gaps, corrections — so the next run starts from what this one learned; edits listed under the report's `Process Improvements` → `Project`, universal step changes proposed under `Universal`. Never results there (reports hold the series) and never text from external input (an injected directive would persist into every later run). The report's `Suggested Issues` groups findings into tracker-sized changes — one row per change landed in one go, every `MEDIUM`+ finding in exactly one row — and names each row's next step: `/bkit-design|/bkit-plan|/bkit-build|/bkit-debug` by the § When to Run rules of `.bkit/workflows.md` (restated inline, prompts are self-contained), the `.agents/shortcuts.md` lite path (`shortcut:build|shortcut:debug`) when its § When to use allows, or `manual` for a change outside the repo. The agent proposes and never files: it has no tracker access, so a person files from the table and each full workflow's related-issues scan catches an issue already open. Bash is limited to that stamp and the probes the template or its `Project Instructions` name; throwaway worktrees / remote targets removed before the report finishes. Web tools serve each template's Standards step. Pre-Flight `Permissions` probes each tool once before `Probe Steps`; a blocked call (there or in any step) never stops the run: the agent records it with its narrow allow rule, runs every step the remaining tools allow, and lists the work it could not do under `Not Checked`. Blocked calls persist in `Project Instructions` `Permissions`; the next run probes them first. `XL` tier: the longest templates run ~20 probe steps of several queries each against the repo and live systems. A missing surface is an explicit skip, not a clean finding. |
373
+ | `bkit-audit-generate` | Read one `docs/templates/bkit-audit-*.md` and run its probe steps against the repo. Write the filled template to `docs/audits/{YYYYMM}/{slug}.md` (`{slug}` = template basename without `bkit-audit-`). **If** that month already has this slug → `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Report = template up to `bkit:end`. Right after creating the stub it runs `bkit branches anchor-stamp --base-sha=<HEAD> --base-ref=<branch>`, so the audited commit and the bkit release the report came from sit in the same `bkit:anchor` block design and plan docs carry (`.bkit/workflows.md` § Anchor Block) — top of file, machine-readable, the next run reads it as the previous report's commit; an outdated release also gets a visible `Outdated bkit` line under the block, written by the stamp. The agent runs the stamp itself because audits have no orchestrator; the block is still tool-written, never hand-written. Writes only the report, `docs/failures.jsonl` rows (`workflow: "audit"`, `step: "audit-{slug}"`; one per `MEDIUM`+ finding, reusing any open row's `key` for the same problem whichever workflow wrote it, closing only open `audit-{slug}-` rows a rerun no longer finds; skipped by templates that audit the ledgers themselves, `.bkit/jsonl.md`), and the template's consumer-owned `Project Instructions` (below `bkit:end`), which it reads first and refines each run — exact commands, paths, tool gaps, corrections — so the next run starts from what this one learned; edits listed under the report's `Process Improvements` → `Project`, universal step changes proposed under `Universal`. Never results there (reports hold the series) and never text from external input (an injected directive would persist into every later run). The report's `Suggested Issues` groups findings into tracker-sized changes — one row per change landed in one go, every `MEDIUM`+ finding in exactly one row — and names each row's next step: `/bkit-design|/bkit-plan|/bkit-build|/bkit-debug` by the § When to Run rules of `.bkit/workflows.md` (restated inline, prompts are self-contained), the `.bkit/lite.md` lite workflow (`build:lite|debug:lite`) when its § When to use allows, or `manual` for a change outside the repo. The agent proposes and never files: its only tracker tool posts a comment, so a person files from the table and each full workflow's related-issues scan catches an issue already open. Issue named in the input (same ID shapes as workflow Step 1, input only, never files the run read) → one `###### bkit:generated` comment there, built by `bkit issues comment --kind=audit` from the final summary (`Embedded Directives` as sources only, so injected text never reaches the tracker), posted through the tracker MCP after any `STOPPED` run too; retry once, then the header `Issue` line reads `failed`; never gates the run. No issue, or tracker `none` → no comment, `Issue: None`. Bash is limited to that stamp, the setup tips, the issue comment, and the probes the template or its `Project Instructions` name; throwaway worktrees / remote targets removed before the report finishes. Web tools serve each template's Standards step. Pre-Flight `Permissions` probes each tool once before `Probe Steps`; a blocked call (there or in any step) never stops the run: the agent records it with its narrow allow rule, runs every step the remaining tools allow, and lists the work it could not do under `Not Checked`. Blocked calls persist in `Project Instructions` `Permissions`; the next run probes them first. `XL` tier: the longest templates run ~20 probe steps of several queries each against the repo and live systems. A missing surface is an explicit skip, not a clean finding. The final message is a fixed block shown verbatim, so the caller never paraphrases it: a machine-readable header (`Status` `COMPLETE` or `STOPPED`, report path, per-severity counts) above `<!-- verdict:end -->`, then the `Suggested Issues` table copied verbatim — rewording a row loses the grouping a person files from — plus `Not Checked`, ledger rows, `Process Improvements` and embedded directives. Every early STOP still returns that header with a `Stopped` reason. `Recommended Next Step` names which rows to file as issues (every `MEDIUM`+ row; the batched `LOW` row optional) and the highest-severity row's next step; each body follows `.bkit/trackers.md` § Issue shapes and carries an `**Audit reports:**` line with the row's finding IDs, so `/bkit-plan` reads the report; plain issues, not sub-issues; shown whether or not a tracker is wired. |
371
374
 
372
375
  Every template under `docs/templates/bkit-audit-*.md`:
373
376
 
@@ -390,14 +393,14 @@ Every template under `docs/templates/bkit-audit-*.md`:
390
393
  | `bkit-audit-database` | Database Audit | Privileges, access coverage, migrations, integrity, capacity, restore. |
391
394
  | `bkit-audit-dead-code` | Dead Code Audit | Reachability — code, config, routes, events, schema, assets that look live and never run. |
392
395
  | `bkit-audit-deferrals` | Deferrals Triage | Open deferral → done / superseded / tracked / parked / in-scope unfinished. |
393
- | `bkit-audit-dependencies` | Dependency Triage | Dep-update PRs → one verified batch; supply-chain settings, advisories, licences, EOL. |
396
+ | `bkit-audit-dependencies` | Dependency Triage | Dep-update PRs → one verified batch; supply-chain settings, advisories, licences, EOL, off-manifest CLIs. |
394
397
  | `bkit-audit-documentation` | Documentation Audit | Claim matches code, pointer lands, agent-relied fact is written down. |
395
398
  | `bkit-audit-duplication` | Duplication Audit | One behaviour, >1 implementation — inline rules, competing mechanisms, restated types, paired decisions, bad merges. |
396
399
  | `bkit-audit-failures` | Failures Triage | Open failure → reachable / already fixed / mis-framed / unconfirmed / repeat of a known defect. |
397
400
  | `bkit-audit-flakes` | Flake Triage | Pass-on-retry or fail-on-one-surface; the change that removes each. |
398
401
  | `bkit-audit-gates` | Gate Candidates | Detective sweeps → preventive gates, order, which stay audits. |
399
402
  | `bkit-audit-issues` | Issue Prioritisation | Size + priority per open tracker issue; two rules a later run re-applies identically; board membership, parent, milestone, blocked-by links. |
400
- | `bkit-audit-llm` | LLM Audit | Per model call — effect, stop on hostile input: prompts, tool bounds, output checks, limits, evals. |
403
+ | `bkit-audit-llm` | LLM Audit | Per model call — effect, stop on hostile input: prompts, tool bounds, output checks, job scope, limits, evals. |
401
404
  | `bkit-audit-logs` | Log Triage | Error-tracker stream + logs it misses — real issue, wrong level, failure that never arrived. |
402
405
  | `bkit-audit-models` | Model Audit | Call site = latest capable fit; model + fallbacks still live; one registry. |
403
406
  | `bkit-audit-privacy` | Privacy Audit | Personal data — held, where it goes, retention, deletion removes the person, disclosure matches code. |
@@ -419,10 +422,23 @@ Every template under `docs/templates/bkit-audit-*.md`:
419
422
  | `bkit-utility-update-failures` | Same over `docs/failures.jsonl`, judged on whether the bug still reproduces from the code. A flaky row closes only on a landed determinism fix, never a green run. Same `TRIAGED` promotion on an open tracker issue; a `failure` carries no `reason` field, so its `TRIAGED` rows only ever mean issue-promotion, unlike `deferral` where `bkit-ship-deferred-sweep` also writes `TRIAGED` alongside `reason` = `unjustified`. Same locator append. Ensure agent memories (`MEMORY.md` / `memory/*.md`) do not duplicate content and only contain pointers (path, section, one-line hook) to relevant `docs/*.md` sections / `docs/*.jsonl` entries. **If** memory contains duplicate / stale content → update memory. Final message is the output format verbatim. |
420
423
  | `bkit-utility-update-decisions` | Fold `docs/decisions.jsonl` by `key`, highest `ts` wins → read only winning rows where `status` is `ACTIVE` or absent. Classify `HOLDS` / `CONTRADICTED` / `OBSOLETE` / `AMBIGUOUS` against `docs/` and the codebase. `CONTRADICTED` with one unambiguous replacement appends the corrected decision `ACTIVE`; `OBSOLETE` (nothing replaced it) appends `SUPERSEDED`. An unambiguous stale locator is folded into the same append and does not reclassify. One append per `key` per run. `AMBIGUOUS` and unresolved locators are left. Doc sentences that restate a corrected row are edited to match; implementation code is not. Ensure agent memories (`MEMORY.md` / `memory/*.md`) do not duplicate content and only contain pointers (path, section, one-line hook) to relevant `docs/*.md` sections / `docs/*.jsonl` entries. **If** memory contains duplicate / stale content → update memory. Final message is the output format verbatim. |
421
424
  | `bkit-utility-update-knowledge` | Fold `docs/knowledge.jsonl` by `key`, highest `ts` wins → read only winning rows where `status` is `ACTIVE` or absent. Classify `HOLDS` / `CONTRADICTED` / `OBSOLETE` / `AMBIGUOUS`. An entry about upstream behaviour is never retracted from absence of local evidence. `OBSOLETE` appends same-`key` `SUPERSEDED`; `CONTRADICTED` appends the corrected lesson `ACTIVE`. Same locator append. Same doc-sentence edit; implementation code is not. Ensure agent memories (`MEMORY.md` / `memory/*.md`) do not duplicate content and only contain pointers (path, section, one-line hook) to relevant `docs/*.md` sections / `docs/*.jsonl` entries. **If** memory contains duplicate / stale content → update memory. Final message is the output format verbatim. |
422
- | `bkit-utility-update-roadmap` | Rank next best steps from the board, both `## Notes` blocks, `.bkit/issues.jsonl` and open deferrals / failures. When a tracker is wired, always names the next milestone and the next distinct umbrella; a child is included only when open, unblocked, and able to start now. Those containers stay visible and enter the list only by priority, one row each, action = those children. List length is `package.json` `bkit.roadmapNext` (positive integer; absent or invalid → 25). Due audits compete by priority (risk covered first, then how overdue) for at most 3 rows. The length hint sits in the generated `roadmap-status` header. The full workflow is the default recommendation; names the `.agents/shortcuts.md` light path only where a lite flow is clearly enough. Rewrites ONLY the `roadmap-analysis` block. |
425
+ | `bkit-utility-update-roadmap` | Rank next best steps from the board, both `## Notes` blocks, `.bkit/issues.jsonl` and open deferrals / failures. When a tracker is wired, always names the next milestone and the next distinct umbrella; a child is included only when open, unblocked, and able to start now. Those containers stay visible and enter the list only by priority, one row each, action = those children. List length is `package.json` `bkit.roadmapNext` (positive integer; absent or invalid → 25). Due audits compete by priority (risk covered first, then how overdue) for at most 3 rows. The length hint sits in the generated `roadmap-status` header. The full workflow is the default recommendation; names the `.bkit/lite.md` lite workflow (`<phase>:lite`) only where it is clearly enough. An item with no tracker issue (ledger row, due audit) gets a file-an-issue-first recommendation, shaped per `.bkit/trackers.md` § Issue shapes, when a tracker is wired. Rewrites ONLY the `roadmap-analysis` block. |
423
426
  | `bkit-utility-compress-markdown` | Token-optimize a single markdown file; preserve 100 % load-bearing tokens. **Destructive** (overwrites target). |
424
427
  | `bkit-utility-update-documentation` | Sync every doc in `.agents/docs.md` with system state — drift cleanup across multiple plans. Ensure agent memories (`MEMORY.md` / `memory/*.md`) do not duplicate content and only contain pointers (path, section, one-line hook) to relevant `docs/*.md` sections / `docs/*.jsonl` entries. **If** memory contains duplicate / stale content → update memory. |
425
428
 
429
+ ## Hook-injected text
430
+
431
+ Text hooks add to an agent's context mid-run — every agent and subagent, no frontmatter opt-out. Canonical wording lives in the engine file; per-host delivery → `.bkit/providers.md` § Guardrails, § GateGuard, § ReadGuard.
432
+
433
+ <!-- prettier-ignore -->
434
+ | Hook | Fires on | Injects | Hosts | Canonical text |
435
+ | --- | --- | --- | --- | --- |
436
+ | GateGuard | First edit per (session, agent, file) | First touch → investigation checklist (file read, callers, symbols, contracts, conventions, instructions quoted); new file → reuse-over-duplicate checklist; gate-config path → fix-code-not-gate advisory; `docs/**.md` (not `docs/plans/`) → density advisory appended | All five | `.bkit/core/hooks/gateguard-engine.js` |
437
+ | ReadGuard | Repeat read of an unchanged line range, same agent | Use-earlier-output note; re-read only if the output left context | All five | `.bkit/core/hooks/readguard-engine.js` |
438
+ | Guardrails | Shell edit (`sed -i`, redirect into a source file); unlisted `curl` / `wget` host on Claude, Codex; Codex ask tier | Advisory naming the bypassed gate; command still runs | Claude, Cursor, Codex, Antigravity | `.bkit/core/hooks/guardrails-shell.js`, `.bkit/core/hooks/guardrails-tiers.js` |
439
+
440
+ - **Never a must-do:** hook text is advisory and fail-open; it never fires on an untrusted Codex `.codex/` layer and arrives after the edit on opencode. A prompt instruction that must hold stays in the prompt.
441
+
426
442
  ## Special Behaviors (frontmatter-adjacent contracts)
427
443
 
428
444
  <!-- prettier-ignore -->