@cbartens/bkit 5.0.3 → 5.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (112) hide show
  1. package/.bkit/README.md +4 -4
  2. package/.bkit/core/.agents/docs.md +1 -0
  3. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-gateguard.cjs +104 -0
  4. package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +119 -0
  5. package/.bkit/core/.agents/rules.md +2 -2
  6. package/.bkit/core/.agents/shortcuts.md +73 -0
  7. package/.bkit/core/.agents/skills.md +5 -3
  8. package/.bkit/core/.bkit/README.md +3 -3
  9. package/.bkit/core/.bkit/comparison.md +2 -2
  10. package/.bkit/core/.bkit/install.md +5 -3
  11. package/.bkit/core/.bkit/prompts.md +69 -68
  12. package/.bkit/core/.bkit/providers.md +28 -10
  13. package/.bkit/core/.bkit/templates.md +4 -2
  14. package/.bkit/core/.bkit/workflows.md +6 -6
  15. package/.bkit/core/AGENTS.md +11 -0
  16. package/.bkit/core/engine/checks/after/managed.ts +4 -1
  17. package/.bkit/core/engine/cli.ts +25 -9
  18. package/.bkit/core/engine/commands/install/check.ts +2 -0
  19. package/.bkit/core/engine/commands/install/doctor.ts +9 -0
  20. package/.bkit/core/engine/commands/install/install.ts +20 -0
  21. package/.bkit/core/engine/commands/install/uninstall.ts +30 -19
  22. package/.bkit/core/engine/commands/install/upgrade.ts +17 -2
  23. package/.bkit/core/engine/commands/workflow/prs.ts +20 -2
  24. package/.bkit/core/engine/commands/workflow/runs.ts +26 -3
  25. package/.bkit/core/engine/install/manifest.ts +38 -2
  26. package/.bkit/core/engine/install/modules/antigravity.ts +265 -0
  27. package/.bkit/core/engine/install/modules/codex.ts +3 -0
  28. package/.bkit/core/engine/install/modules/core.ts +7 -1
  29. package/.bkit/core/engine/install/modules/index.ts +33 -6
  30. package/.bkit/core/engine/render/hosts.ts +174 -1
  31. package/.bkit/core/engine/render/models.ts +10 -0
  32. package/.bkit/core/prompts/bkit-audit-generate.md +1 -1
  33. package/.bkit/core/prompts/bkit-build-challenge-1.md +1 -1
  34. package/.bkit/core/prompts/bkit-build-challenge-2.md +1 -1
  35. package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +1 -1
  36. package/.bkit/core/prompts/bkit-build-challenge-remediate.md +1 -1
  37. package/.bkit/core/prompts/bkit-build-challenge-tests.md +1 -1
  38. package/.bkit/core/prompts/bkit-build-install-skills.md +6 -5
  39. package/.bkit/core/prompts/bkit-build-plan-current.md +1 -1
  40. package/.bkit/core/prompts/bkit-build-plan-execute.md +1 -1
  41. package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +1 -1
  42. package/.bkit/core/prompts/bkit-build-plan-verify.md +1 -1
  43. package/.bkit/core/prompts/bkit-build-summary.md +1 -1
  44. package/.bkit/core/prompts/bkit-debug-abort-handover.md +1 -1
  45. package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +1 -1
  46. package/.bkit/core/prompts/bkit-debug-failure-remediate.md +1 -1
  47. package/.bkit/core/prompts/bkit-debug-failure-soak.md +1 -1
  48. package/.bkit/core/prompts/bkit-debug-summary.md +1 -1
  49. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +1 -1
  50. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +1 -1
  51. package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +1 -1
  52. package/.bkit/core/prompts/bkit-design-generate.md +1 -1
  53. package/.bkit/core/prompts/bkit-design-organise.md +1 -1
  54. package/.bkit/core/prompts/bkit-design-review-1.md +1 -1
  55. package/.bkit/core/prompts/bkit-design-review-2.md +1 -1
  56. package/.bkit/core/prompts/bkit-design-spike.md +1 -1
  57. package/.bkit/core/prompts/bkit-design-summary.md +1 -1
  58. package/.bkit/core/prompts/bkit-design-update.md +1 -1
  59. package/.bkit/core/prompts/bkit-plan-complexity-check.md +1 -1
  60. package/.bkit/core/prompts/bkit-plan-complexity-split.md +1 -1
  61. package/.bkit/core/prompts/bkit-plan-generate.md +1 -1
  62. package/.bkit/core/prompts/bkit-plan-review-1.md +1 -1
  63. package/.bkit/core/prompts/bkit-plan-review-2.md +1 -1
  64. package/.bkit/core/prompts/bkit-plan-review-3.md +1 -1
  65. package/.bkit/core/prompts/bkit-plan-scope-check-1.md +1 -1
  66. package/.bkit/core/prompts/bkit-plan-scope-check-2.md +1 -1
  67. package/.bkit/core/prompts/bkit-plan-summary.md +1 -1
  68. package/.bkit/core/prompts/bkit-plan-update.md +1 -1
  69. package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +1 -1
  70. package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +1 -1
  71. package/.bkit/core/prompts/bkit-ship-summary.md +1 -1
  72. package/.bkit/core/prompts/bkit-ship-update-docs.md +1 -1
  73. package/.bkit/core/prompts/bkit-utility-compress-markdown.md +1 -1
  74. package/.bkit/core/prompts/bkit-utility-update-decisions.md +1 -1
  75. package/.bkit/core/prompts/bkit-utility-update-deferrals.md +1 -1
  76. package/.bkit/core/prompts/bkit-utility-update-documentation.md +1 -1
  77. package/.bkit/core/prompts/bkit-utility-update-failures.md +1 -1
  78. package/.bkit/core/prompts/bkit-utility-update-knowledge.md +1 -1
  79. package/.bkit/core/prompts/bkit-utility-update-roadmap.md +3 -3
  80. package/.bkit/core/workflows/bkit-auto.md +1 -1
  81. package/.bkit/core/workflows/bkit-build.md +3 -1
  82. package/.bkit/core/workflows/bkit-debug.md +3 -1
  83. package/.bkit/core/workflows/bkit-design.md +3 -1
  84. package/.bkit/core/workflows/bkit-plan.md +3 -1
  85. package/.bkit/core/workflows/bkit-ship.md +3 -1
  86. package/.bkit/shared/.agents/plugins/bkit/hooks.json +26 -0
  87. package/.bkit/shared/.agents/plugins/bkit/plugin.json +5 -0
  88. package/.bkit/shared/GEMINI.md +11 -0
  89. package/.bkit/shared/docs/security.md +3 -3
  90. package/.bkit/templates/.github/workflows/bkit-ci.yml +24 -0
  91. package/.bkit/templates/.prettierignore +3 -0
  92. package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +2 -2
  93. package/.bkit/templates/slop-scan.config.json +3 -1
  94. package/CHANGELOG.md +20 -0
  95. package/README.md +9 -8
  96. package/dist/checks/after/managed.js +1 -0
  97. package/dist/cli.js +21 -8
  98. package/dist/commands/install/check.js +2 -0
  99. package/dist/commands/install/doctor.js +4 -0
  100. package/dist/commands/install/install.js +22 -1
  101. package/dist/commands/install/uninstall.js +34 -22
  102. package/dist/commands/install/upgrade.js +18 -3
  103. package/dist/commands/workflow/prs.js +13 -1
  104. package/dist/commands/workflow/runs.js +23 -3
  105. package/dist/install/manifest.js +35 -1
  106. package/dist/install/modules/antigravity.js +224 -0
  107. package/dist/install/modules/codex.js +3 -0
  108. package/dist/install/modules/core.js +7 -1
  109. package/dist/install/modules/index.js +17 -6
  110. package/dist/render/hosts.js +149 -1
  111. package/dist/render/models.js +9 -0
  112. package/package.json +5 -3
@@ -40,7 +40,7 @@
40
40
  - **Banned shapes:** a parenthetical explaining why a clause exists, an inline comment justifying behaviour, a note on what a previous version did.
41
41
  - **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.
42
42
  - **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.
43
- - **Self-contained:** every prompt must stand alone; inline all instructions; no file references. Exceptions: `.agents/rules.md`, `.agents/docs.md`, `*.jsonl` ledgers, supplied templates (plan, audit) — those carry their own rules.
43
+ - **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
44
  - **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.
45
45
  - **Removal = delete:** drop instruction outright; never leave removal explanations.
46
46
  - **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.
@@ -104,13 +104,13 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
104
104
  **Effort → host thinking (canonical):** Prompt `effort:` = row key in **Default**. **Keyed on HOST, not provider** — field name + ladder come from the host config format (`effort:` claude/cursor, a `variant:` field opencode, `model_reasoning_effort` codex), not the model → every opencode provider shares the one **OpenCode** column. A provider key here THROWS (axis confusion, not a fallback). Codex ceilings `max`→`xhigh` (no higher rung). Install parses this table — no hardcoded ladders in TS. **opencode columns ceiling out, they do not downshift:** a provider below its tier target spends **more** thinking to close the gap, and can afford to — every non-Claude pin costs $0.03–$1.76 per agentic task vs Claude's $2.14–$5.34 (`providers.md` § Agentic-coding parity board). Haiku-tier summary writers run at `high` (OpenCode `max`): every non-Claude board score was measured with heavy thinking, so the haiku target compares like with like, and haiku-cell pins cost $0.03–$0.11 per task. **Effort and model are independent** — the `*-summary` writers run `claude-haiku-5-5` at `high` and source modifiers run `claude-sonnet-5-5` at `high`; the map above is the default model per rung, not a constraint. **Cursor stays identity with Default** — its thinking lever is the model-ID suffix (`cursor-grok-4.5-high`), not `effort:`, so ceiling-out happens at the pin.
105
105
 
106
106
  <!-- prettier-ignore -->
107
- | Default | Claude | Cursor | OpenCode | Codex |
108
- | --- | --- | --- | --- | --- |
109
- | `low` | `low` | `low` | `none` | `low` |
110
- | `medium` | `medium` | `medium` | `high` | `medium` |
111
- | `high` | `high` | `high` | `max` | `high` |
112
- | `xhigh` | `xhigh` | `xhigh` | `max` | `xhigh` |
113
- | `max` | `max` | `max` | `max` | `xhigh` |
107
+ | Default | Claude | Cursor | OpenCode | Codex | Antigravity |
108
+ | --- | --- | --- | --- | --- | --- |
109
+ | `low` | `low` | `low` | `none` | `low` | `low` |
110
+ | `medium` | `medium` | `medium` | `high` | `medium` | `medium` |
111
+ | `high` | `high` | `high` | `max` | `high` | `high` |
112
+ | `xhigh` | `xhigh` | `xhigh` | `max` | `xhigh` | `max` |
113
+ | `max` | `max` | `max` | `max` | `xhigh` | `max` |
114
114
 
115
115
  ### Field rationale
116
116
 
@@ -174,7 +174,7 @@ Pinning `model:` locks agent model regardless of orchestrator session. Without p
174
174
 
175
175
  ## Models
176
176
 
177
- 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), one per opencode provider (`OpenRouter`, `Ollama`, …). `bkit install --opencode=<provider>` reads the matching column; every allowlisted provider ships one.
177
+ 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.
178
178
 
179
179
  **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.
180
180
 
@@ -191,56 +191,56 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
191
191
  > **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`).
192
192
 
193
193
  <!-- prettier-ignore -->
194
- | Prompt | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Effort | Max Turns | Role |
195
- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
196
- | `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` | `high` | 100 | parallel slot 1 (pragmatic lens) |
197
- | `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` | `medium` | 100 | parallel slot 2 (optimal-tradeoff lens; Composer vs Grok siblings on Cursor; cross-tier on Claude) |
198
- | `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` | `high` | 100 | parallel slot 3 (risk-premortem lens) |
199
- | `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` | `high` | 100 | design review slot 1 (web search + feasibility analysis) |
200
- | `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` | `medium` | 100 | design review slot 2 (Composer vs Grok sibling on Cursor; cross-tier on Claude) |
201
- | `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` | `high` | 100 | settle review-named unknowns with throwaway probe code (conditional step) |
202
- | `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` | `xhigh` | 100 | merge review critiques into design (whole-doc rewrite — needs depth) |
203
- | `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` | `high` | 100 | decompose reviewed design into dependency-annotated workstreams; coverage self-verify + DAG cycle detection |
204
- | `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` | `high` | 50 | summary writer |
205
- | `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` | `xhigh` | 100 | generate design from brainstorms (top-of-pipeline synthesizer; whole-doc rewrite) |
206
- | `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` | `medium` | 50 | complexity check |
207
- | `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` | `xhigh` | 100 | plan draft generator (top-of-pipeline synthesizer) |
208
- | `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` | `xhigh` | 150 | audit report from one template (top-of-pipeline synthesizer) |
209
- | `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` | `high` | 100 | review slot 1 (tightness + design-coverage) |
210
- | `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` | `medium` | 100 | review slot 2 (dependency-correctness + design-coverage; depth-sensitive lens — both opus) |
211
- | `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` | `high` | 100 | review slot 3 (regression-risk + design-coverage) |
212
- | `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` | `medium` | 50 | scope audit slot 1 (mechanical audit — medium effort) |
213
- | `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` | `medium` | 50 | scope audit slot 2 (Composer vs Grok sibling on Cursor) |
214
- | `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` | `high` | 100 | split large plan |
215
- | `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` | `high` | 50 | summary writer |
216
- | `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` | `xhigh` | 100 | merge review + scope critiques into plan (whole-doc rewrite — needs depth) |
217
- | `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` | `medium` | 50 | skill identifier |
218
- | `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` | `high` | 100 | parallel slot 1 (bug-hunting lens) |
219
- | `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` | `high` | 100 | parallel slot 2 (security lens; depth-sensitive — both opus) |
220
- | `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` | `xhigh` | 100 | merge parallel challenge findings (whole-doc rewrite) |
221
- | `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` | `high` | 100 | test generator (source modifier, no test loop) |
222
- | `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` | `high` | 150 | task executor (source modifier with test loop; ceiling — split if exceeded) |
223
- | `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` | `high` | 150 | fix challenge findings (source modifier with test loop) |
224
- | `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` | `high` | 150 | fix verification gaps (source modifier with test loop) |
225
- | `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` | `high` | 50 | summary writer |
226
- | `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` | `high` | 100 | verify impl vs plan |
227
- | `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` | `high` | 100 | judge plan vs changes landed since its base commit |
228
- | `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` | `medium` | 50 | handover writer |
229
- | `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` | `xhigh` | 100 | failure diagnosis (Final-strategy attempts especially benefit from depth before human handover) |
230
- | `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` | `high` | 150 | implement diagnosis fixes (source modifier with test loop) |
231
- | `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` | `xhigh` | 150 | soak fix — one accumulating-context instrument-or-fix step per iteration against the live boundary (orchestrator re-runs tests + loops) |
232
- | `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` | `high` | 50 | summary writer |
233
- | `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` | `high` | 50 | summary writer |
234
- | `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` | `high` | 100 | sync cataloged docs (multi-doc writer) |
235
- | `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` | `high` | 150 | mechanical rebase-conflict resolver (source modifier with test loop) |
236
- | `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` | `high` | 100 | pre-merge completeness gate — intended-vs-actual + declared-deferral resurface |
237
- | `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` | `high` | 100 | deferrals update |
238
- | `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` | `high` | 100 | failures update |
239
- | `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` | `high` | 100 | decisions update |
240
- | `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` | `high` | 100 | knowledge update |
241
- | `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` | `high` | 100 | roadmap analysis |
242
- | `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` | `medium` | 100 | token-optimize markdown |
243
- | `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` | `medium` | 100 | doc sync (multi-doc writer) |
194
+ | Prompt | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Google | Effort | Max Turns | Role |
195
+ | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
196
+ | `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) |
197
+ | `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) |
198
+ | `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) |
199
+ | `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) |
200
+ | `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) |
201
+ | `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) |
202
+ | `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) |
203
+ | `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 |
204
+ | `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 |
205
+ | `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) |
206
+ | `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 |
207
+ | `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) |
208
+ | `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` | 150 | audit report from one template (top-of-pipeline synthesizer) |
209
+ | `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) |
210
+ | `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) |
211
+ | `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) |
212
+ | `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) |
213
+ | `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) |
214
+ | `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 |
215
+ | `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 |
216
+ | `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) |
217
+ | `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 |
218
+ | `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) |
219
+ | `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) |
220
+ | `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) |
221
+ | `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) |
222
+ | `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) |
223
+ | `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) |
224
+ | `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) |
225
+ | `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 |
226
+ | `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 |
227
+ | `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 |
228
+ | `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 |
229
+ | `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) |
230
+ | `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) |
231
+ | `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) |
232
+ | `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 |
233
+ | `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 |
234
+ | `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) |
235
+ | `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) |
236
+ | `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 |
237
+ | `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 |
238
+ | `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 |
239
+ | `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 |
240
+ | `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 |
241
+ | `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 |
242
+ | `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 |
243
+ | `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) |
244
244
 
245
245
  **Effort vs maxTurns vs model — three independent knobs:**
246
246
 
@@ -257,6 +257,7 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
257
257
  >
258
258
  > - **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.
259
259
  > - **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.
260
+ > - **Google** — Antigravity pins `gemini-3.8-pro` for reasoning/synthesis, `gemini-3.8-flash` for summaries.
260
261
  >
261
262
  > **OpenAI-compatible providers curated + tool-call-smoked** (`tools:` chat / completions round-trip per pin, confirming `tool_calls` — `/models` existence ≠ tool-calls):
262
263
  >
@@ -273,13 +274,13 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
273
274
  `.bkit/core/workflows/*.md` = workflow orchestrators — dispatch subagents, synthesize results. **Not subagents** (no `effort:` / `maxTurns:` frontmatter); run on session model. Pin session model to table below when invoking.
274
275
 
275
276
  <!-- prettier-ignore -->
276
- | Orchestrator | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Role |
277
- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
278
- | `/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` | Synthesizes conflicting brainstorms; resolves design ambiguity. |
279
- | `/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` | Decides single vs split; merges review (triplet) + scope-check (pair) critiques. |
280
- | `/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` | Picks remediation path under uncertainty; Standard / Pivot / Final escalation. |
281
- | `/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` | 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). |
282
- | `/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` | Mostly mechanical: merge + archive + parallel docs / summary. |
277
+ | Orchestrator | Anthropic | Cursor | OpenRouter | Ollama | OpenCode Zen | OpenCode Go | OpenAI | Google | Role |
278
+ | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
279
+ | `/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. |
280
+ | `/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. |
281
+ | `/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. |
282
+ | `/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). |
283
+ | `/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
284
 
284
285
  **Rule:** Opus where orchestrator resolves ambiguity; Sonnet for defined sequence. **If** Sonnet orchestrator skips Failure Path branches or mis-routes verify gaps → escalate Opus.
285
286
 
@@ -325,7 +326,7 @@ Canonical per-agent metadata — **single source of truth for model per agent**.
325
326
  | Agent | Scope |
326
327
  | --- | --- |
327
328
  | `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. |
328
- | `bkit-build-install-skills` | Identify and install relevant skills via `npx skills find`/`add`. |
329
+ | `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. |
329
330
  | `bkit-build-plan-execute` | Execute plan tasks sequentially; 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. |
330
331
  | `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 — 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). |
331
332
  | `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. |
@@ -416,7 +417,7 @@ Every template under `docs/templates/bkit-audit-*.md`:
416
417
  | `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. |
417
418
  | `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. |
418
419
  | `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. |
419
- | `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. Rewrites ONLY the `roadmap-analysis` block. |
420
+ | `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. |
420
421
  | `bkit-utility-compress-markdown` | Token-optimize a single markdown file; preserve 100 % load-bearing tokens. **Destructive** (overwrites target). |
421
422
  | `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. |
422
423
 
@@ -24,6 +24,7 @@
24
24
  | Cursor | derived | `.cursor/agents/` | `.cursor/commands/` | `.cursor/settings.json` + `.cursor/environment.json` + `.cursor/Dockerfile` (templates, `.bkit/templates.md`) | `.cursor/hooks/` (registered in `.cursor/hooks.json`) | `bkit install --cursor` |
25
25
  | opencode | additive (opt-in) | `.opencode/agents/` | `.opencode/commands/` | `.opencode/opencode.json` | `.opencode/plugin/bkit-gateguard.js` (PreToolUse) | `bkit install --opencode=<provider>` |
26
26
  | Codex CLI | additive (opt-in) | `.codex/agents/` (TOML) | none — skills (below) | none (`openai` = reserved built-in id) | `.codex/hooks/bkit-gateguard.cjs` + `.codex/hooks/bkit-guardrails.cjs` (PreToolUse `apply_patch` / `Bash`, via `.codex/hooks.json`) | `bkit install --codex` |
27
+ | Google Antigravity | additive (opt-in) | `.agents/plugins/bkit/agents/` | none — skills (plugin, below) | `GEMINI.md` (workspace rule) | `.agents/plugins/bkit/hooks/bkit-gateguard.cjs` + `.agents/plugins/bkit/hooks/bkit-guardrails.cjs` (PreToolUse `write_to_file` / `replace_file_content` / `run_command`, via `.agents/plugins/bkit/hooks.json`) | `bkit install --antigravity` |
27
28
 
28
29
  **Two axes — host != provider.** **Host** = program reading what bkit writes, identified by its dir (`.claude/`, `.cursor/`, `.opencode/`, `.codex/`). **Provider** = gateway tokens are bought through. Model IDs are per-provider → `prompts.md` § Models = one column per PROVIDER (shared provider = one column, never two). Thinking depth is per-host (field name + ladder set by host config format: `effort:` claude/cursor, a `variant:` field opencode, `model_reasoning_effort` codex) → § Effort = one column per HOST. Neither table grows as hosts x providers.
29
30
 
@@ -35,6 +36,7 @@
35
36
  | Claude Code | `anthropic` | Claude subscription = cheapest path to Claude models |
36
37
  | Cursor | `cursor` | Cursor subscription covers its whole catalog |
37
38
  | Codex CLI | `openai` | ChatGPT subscription |
39
+ | Google Antigravity | `google` | Antigravity free tier / Google subscription — cheapest path to Gemini |
38
40
  | opencode | **pick one**: `openrouter`, `ollama`, `opencode-zen`, `opencode-go` | no subscription — BYO key, so the choice is yours |
39
41
 
40
42
  Subscription-bearing host → pinned, nullary flag (`--claude`, `--codex`). BYO-key host → pluggable, flag names the provider (`--opencode=<provider>`). Per-model deviation → consumer `## Model Overrides` below `bkit:end`; no provider override.
@@ -45,13 +47,26 @@ Subscription-bearing host → pinned, nullary flag (`--claude`, `--codex`). BYO-
45
47
  | Concern | On Codex |
46
48
  | --- | --- |
47
49
  | Agent files | `.codex/agents/*.toml` (TOML, not markdown). Required: `name`, `description`, `developer_instructions`. Pin + rung: `model`, `model_reasoning_effort`. |
48
- | Workflows = SKILLS, invoked `$bkit-design` | no project-scoped command surface — custom prompts are `~/.codex/prompts` only, not repo-shared, deprecated for skills (upstream declined repo-scoped prompts). bkit renders `.agents/skills/bkit-<workflow>/SKILL.md`, on Codex's skill path (`$REPO_ROOT/.agents/skills`). `.agents/` is shared → visible to every host. |
50
+ | Workflows = SKILLS, invoked `$bkit-design` | no project-scoped command surface — custom prompts are `~/.codex/prompts` only, not repo-shared, deprecated for skills (upstream declined repo-scoped prompts). bkit renders `.agents/skills/bkit-<workflow>/SKILL.md`, on Codex's skill path (`$REPO_ROOT/.agents/skills`). This path is Codex's; Antigravity ships its own skills in a plugin (`.agents/plugins/bkit/skills/`). |
49
51
  | `tools:` not enforced | No per-agent tool allowlist upstream; `sandbox_mode` cannot substitute — every bkit agent is write-capable, so all would be `workspace-write`. Each agent gets the full built-in tool set regardless of declared `tools:`. GateGuard still gates, as everywhere. |
50
52
 
51
53
  > **GateGuard needs the `.codex/` layer TRUSTED.** Codex loads project-local hooks only once trusted. Until then the hook is installed and never fires — present, proving nothing. Same for `bkit-guardrails.cjs`.
52
54
  >
53
55
  > **Codex cannot prompt.** It parses `permissionDecision: "ask"` but does not implement it — an ask is recorded as an error and the call proceeds. `bkit-guardrails.cjs` therefore blocks the `deny` tier for real and emits the `ask` tier as advisory `additionalContext`: the gate fires and informs, it cannot stop the command. Every ask-tier command is already PROHIBITED in all five workflow headers, so no bkit workflow reaches one. Asserted in `.bkit/core/engine/install/modules/index.integration.test.ts`.
54
56
 
57
+ ### Google Antigravity — installs as a workspace plugin
58
+
59
+ <!-- prettier-ignore -->
60
+ | Concern | On Antigravity |
61
+ | --- | --- |
62
+ | Install layout | the whole host is a workspace **plugin** at `.agents/plugins/bkit/` (`plugin.json` + `skills/` + `agents/` + `hooks.json` + `hooks/`) — Antigravity's own packaging surface, activated per project. `.agents/` root stays the dedicated Codex install. |
63
+ | Workflows = SKILLS at `.agents/plugins/bkit/skills/bkit-<workflow>/SKILL.md` | Antigravity auto-discovers a workspace plugin's `skills/`. Codex's workflow skills stay at `.agents/skills/bkit-*/`; with both hosts installed Antigravity's selector lists both sets (accepted; `antigravity-codex-skill-overlap` advisory names which to pick). |
64
+ | Prompt files + no native subagent tool | prompts at `.agents/plugins/bkit/agents/*.md` — frontmatter `name`/`description`, model pin from § Models `Google` column, `effort` from § Effort `Antigravity` column, `tools:` respelled to Antigravity tool names. The orchestrator loads each with `view_file` and runs it in-session; isolated runs use `run_command` (`agy`). `**Subagent:** @name` respells to `` `view_file` `.agents/plugins/bkit/agents/name.md` `` rather than a `/name` slash command. |
65
+
66
+ > **Antigravity tool names differ from Claude's.** `Read`→`view_file`, `Write`→`write_to_file`, `Edit`→`replace_file_content`, `Bash`→`run_command`, `Grep`→`grep_search`, `Glob`→`list_dir`, `WebSearch`→`search_web`, `WebFetch`→`read_url`. `mcp__<server>__<tool>` keeps its spelling. `applyAntigravityPrompt` / `antigravityToolsBlock` (`.bkit/core/engine/render/hosts.ts`) apply the map at render.
67
+ >
68
+ > **GateGuard + guardrails wired from `.agents/plugins/bkit/hooks.json`** (PreToolUse on `write_to_file` / `replace_file_content` / `run_command`). Same fail-open advisory engine as the other hosts; the deny tier blocks for real.
69
+
55
70
  **Explicit host axis (no implicit full):** `bkit install` requires ≥1 module flag — bare `bkit install` errors. Every host explicit; hosts compose: `bkit install --claude --cursor --opencode=opencode-zen` installs all three (+ implicit core). `--opencode` cannot render without `=<provider>` (strict allowlist). Switch providers: re-run install. All hosts render from `.bkit/`; run state in `status.jsonl` + plan docs + tracker (never host session) — phase/resumed run moves across hosts/providers mid-feature with identical gates + per-agent pins: hit limit on one, continue on another. `bkit status` → installed hosts + active providers; `bkit doctor` → credentials + tool reachability.
56
71
 
57
72
  **Cheap models inside an IDE — no extension needed.** A host is its dir, not the window its process runs in. `bkit install --claude --cursor --opencode=openrouter` + opencode in the IDE's integrated terminal = every agent pin, GateGuard and the full workflow on OpenRouter while editing in Cursor. Supported path when the Claude subscription is spent.
@@ -104,6 +119,7 @@ Persistent variant: `RunAtLoad` LaunchAgent plist (`~/Library/LaunchAgents/`) wi
104
119
  | Claude | `Agent` | `@` | `@bkit-build-plan-execute` invoked via `Agent` tool |
105
120
  | Cursor | `Task` | `/` | `/bkit-build-plan-execute` invoked via `Task` tool |
106
121
  | opencode | `/` (slash command) | `/` | `/bkit-build-plan-execute` invoked via opencode slash command |
122
+ | Antigravity | `view_file` (in-session prompt load) | `.agents/plugins/bkit/agents/` | `view_file` `.agents/plugins/bkit/agents/bkit-build-plan-execute.md` |
107
123
 
108
124
  **Transform (Claude → Cursor, command bodies):**
109
125
 
@@ -259,17 +275,17 @@ Both hosts: `/<filename-without-ext>` (`/bkit-build`, `/bkit-plan`, etc.). Ident
259
275
  <!-- prettier-ignore -->
260
276
  | Part | Shared by | Holds |
261
277
  | --- | --- | --- |
262
- | `gateguard-engine.js` | Claude, Cursor, Codex, opencode `gateguard` | gate-config table, checklists, docs advisory, dedup state, `firstTouchAdvice` |
278
+ | `gateguard-engine.js` | Claude, Cursor, Codex, Google Antigravity, opencode `gateguard` | gate-config table, checklists, docs advisory, dedup state, `firstTouchAdvice` |
263
279
  | `gateguard-edit-payload.js` | Claude, Cursor `gateguard` | `Edit` / `Write` / `MultiEdit` payload adapter `bkitGateguard(payload)` |
264
- | `guardrails-shell.js` | Claude, Cursor, Codex `guardrails` | segment parsing, curl / wget host allowlist, shell-as-edit-channel detection |
265
- | `guardrails-tiers.js` | Cursor, Codex `guardrails` | deny rules, ask patterns, `classifyShell` precedence |
280
+ | `guardrails-shell.js` | Claude, Cursor, Codex, Google Antigravity `guardrails` | segment parsing, curl / wget host allowlist, shell-as-edit-channel detection |
281
+ | `guardrails-tiers.js` | Cursor, Codex, Google Antigravity `guardrails` | deny rules, ask patterns, `classifyShell` precedence |
266
282
  | `preflight-linear.sh` | Claude, Cursor `preflight` | Linear key / issue checks, GraphQL query, `bkit:auto` + terminal-state guards |
267
283
 
268
- Per host, outside the parts: Claude `gateguard` / `guardrails` — `require` + `hookSpecificOutput` driver, guardrails advisory-only; Cursor — `{ permission }` output, guardrails read gate (`.pem` / `.env`), gateguard workspace-relative path resolve; Codex — `apply_patch` envelope parser, ask tier emitted as advisory; opencode — ES module, `write` / `edit` / `patch` vocabulary, checklist appended to the tool result in `execute.after` + throw from `execute.before` to block (2.0 exposes no pre-edit context hook, and stderr does not reach the model); `preflight` — trigger (Claude `LINEAR_ISSUE_ID`, Cursor `is_background_agent` + `.bkit/.runtime-cursor` marker), Claude-only Darwin brew check, `emit_context` shape.
284
+ Per host, outside the parts: Claude `gateguard` / `guardrails` — `require` + `hookSpecificOutput` driver, guardrails advisory-only; Cursor — `{ permission }` output, guardrails read gate (`.pem` / `.env`), gateguard workspace-relative path resolve; Codex — `apply_patch` envelope parser, ask tier emitted as advisory; Google Antigravity — Claude's `hookSpecificOutput` contract, `write_to_file` / `replace_file_content` edit tools and `run_command` shell tool, path read from `tool_input.file_path`; opencode — ES module, `write` / `edit` / `patch` vocabulary, checklist appended to the tool result in `execute.after` + throw from `execute.before` to block (2.0 exposes no pre-edit context hook, and stderr does not reach the model); `preflight` — trigger (Claude `LINEAR_ISSUE_ID`, Cursor `is_background_agent` + `.bkit/.runtime-cursor` marker), Claude-only Darwin brew check, `emit_context` shape.
269
285
 
270
286
  ### GateGuard
271
287
 
272
- Advisory hook, on all four hosts (Claude Code, Cursor, Codex, opencode). Claude / Cursor / Codex inject the checklist pre-edit (PreToolUse); opencode 2.0 exposes no pre-edit context hook, so it appends the checklist to the tool result in the post-execute hook — the first edit's result, not a pre-edit gate — and reserves the pre-execute hook for deny mode. First file touch per session → investigation checklist; gate-config paths (JS/TS: tsconfig/eslint/prettier/vitest/jest/vale/slop/lint-staged; Python: pyproject.toml/ruff/flake8/mypy; Go: golangci; Rust: clippy/rustfmt) → "fix code, don't weaken gate" advisory, except under a consumer's `.bkit/templates/` (reference copies; in bkit's own repo, package name `@cbartens/bkit`, that folder is the template source and stays guarded); new-file writes → reuse-over-duplicate nudge; `docs/**.md` (not `docs/plans/`) → density advisory appended. **fail-open**, **subagents included**, dedup `(session, file)` via OS-temp state, 24h TTL.
288
+ Advisory hook, on all five hosts (Claude Code, Cursor, Codex, Google Antigravity, opencode). Claude / Cursor / Codex / Antigravity inject the checklist pre-edit (PreToolUse); opencode 2.0 exposes no pre-edit context hook, so it appends the checklist to the tool result in the post-execute hook — the first edit's result, not a pre-edit gate — and reserves the pre-execute hook for deny mode. First file touch per session → investigation checklist; gate-config paths (JS/TS: tsconfig/eslint/prettier/vitest/jest/vale/slop/lint-staged; Python: pyproject.toml/ruff/flake8/mypy; Go: golangci; Rust: clippy/rustfmt) → "fix code, don't weaken gate" advisory, except under a consumer's `.bkit/templates/` (reference copies; in bkit's own repo, package name `@cbartens/bkit`, that folder is the template source and stays guarded); new-file writes → reuse-over-duplicate nudge; `docs/**.md` (not `docs/plans/`) → density advisory appended. **fail-open**, **subagents included**, dedup `(session, file)` via OS-temp state, 24h TTL.
273
289
 
274
290
  <!-- prettier-ignore -->
275
291
  | Host | Implementation | File | Registration |
@@ -278,6 +294,7 @@ Advisory hook, on all four hosts (Claude Code, Cursor, Codex, opencode). Claude
278
294
  | opencode | `bkit-gateguard.js` (ESM) | `.opencode/plugin/bkit-gateguard.js` | `.opencode/opencode.json` → `plugin` array, spec `./plugin/bkit-gateguard.js` (config-file-relative; opencode 2.0 reads a bare `.opencode/…` spec as an npm package and fails to load — the plugin also auto-loads from `.opencode/plugin/`) |
279
295
  | Cursor | `bkit-gateguard.cjs` (CJS) — managed block generated from the same parts as the Claude twin, so byte-identical | `.cursor/hooks/bkit-gateguard.cjs` | `.cursor/hooks.json` → `preToolUse` (matcher `Write`), no `failClosed` — an advisory hook that fails closed would block the edit it only meant to comment on |
280
296
  | Codex | `bkit-gateguard.cjs` (CJS) — Claude's stdin/stdout contract; parses the `apply_patch` envelope for target paths | `.codex/hooks/bkit-gateguard.cjs` | `.codex/hooks.json` → `hooks.PreToolUse` on `apply_patch` |
297
+ | Antigravity | `bkit-gateguard.cjs` (CJS) — Claude's stdin/stdout contract; `write_to_file` / `replace_file_content` edit tools, path from `tool_input.file_path` | `.agents/plugins/bkit/hooks/bkit-gateguard.cjs` | `.agents/plugins/bkit/hooks.json` → `hooks.PreToolUse` on `write_to_file\|replace_file_content` |
281
298
  | Cursor | `bkit-guardrails.cjs` (CJS) — destructive-op / secret-exposure gates, the Cursor equivalent of Claude's `permissions` and opencode's `permission` map | `.cursor/hooks/bkit-guardrails.cjs` | `.cursor/hooks.json` → `beforeShellExecution` + `preToolUse` (`Read\|TabRead`), both `failClosed` |
282
299
 
283
300
  **Ownership:** both GateGuard files — and Cursor's `bkit-guardrails.cjs` — are **markered-text** (slash-comment: `// bkit:start` / `// bkit:end`). bkit owns only the advisory engine between the markers and reconverges it on every install / upgrade; the driver around it — Claude's stdin read + single `emit()`, opencode's exported `plugin` — is consumer-owned from first install onward, so consumer advisories survive upgrades. bkit's block is pure (no stdin, no stdout / stderr, no top-level call): Claude Code parses hook stdout as one JSON document, so two emitters would produce `{...}{...}` and the whole hook's output — bkit's included — is discarded. Marker-less file on upgrade → hash matches a bkit release: replaced wholesale; hash unknown: block appended plus printed wiring instructions. Uninstall strips the block, leaving the consumer's driver working. `bkit-guardrails.cjs` follows the identical split: bkit owns `bkitGuardrails(payload)`, which returns a decision object or `null` for no-opinion, and the consumer owns the stdin read and the single `emit()`.
@@ -286,9 +303,9 @@ Advisory hook, on all four hosts (Claude Code, Cursor, Codex, opencode). Claude
286
303
 
287
304
  **Subagents:** not exempt on any host. A subagent edit is an edit, and dedup is per (session, file) with a subagent carrying its own session id, so it gets its own checklist. No host reads a subagent marker (Claude's `agent_id`, opencode's `parentID`); Cursor's payload carries none.
288
305
 
289
- **Deny mode, per host:** Claude and Codex `permissionDecision: "deny"` with the checklist as `permissionDecisionReason`; Cursor `permission: "deny"` with the checklist as `agent_message` (`user_message` goes to the human, not the model); opencode throws from `execute.before` — the only hook that can block — and appends the checklist to the tool result in `execute.after`, because 2.0 exposes no pre-edit context hook and stderr does not reach the model. Same behaviour, three delivery mechanisms across four hosts; asserted uniformly in `.bkit/core/engine/audits/hooks/gateguard-parity.integration.test.ts`.
306
+ **Deny mode, per host:** Claude, Codex and Antigravity `permissionDecision: "deny"` with the checklist as `permissionDecisionReason`; Cursor `permission: "deny"` with the checklist as `agent_message` (`user_message` goes to the human, not the model); opencode throws from `execute.before` — the only hook that can block — and appends the checklist to the tool result in `execute.after`, because 2.0 exposes no pre-edit context hook and stderr does not reach the model. Same behaviour, three delivery mechanisms across five hosts; asserted uniformly in `.bkit/core/engine/audits/hooks/gateguard-parity.integration.test.ts`.
290
307
 
291
- **Divergence budget:** every host's block carries `hooks/gateguard-engine.js` verbatim, and the Claude and Cursor blocks are byte-identical (both test-asserted on the generated hooks). opencode's differs only where the runtime forces it — ES module rather than CJS, tool vocabulary `write`/`edit`/`patch` rather than `Edit`/`Write`/`MultiEdit`. Codex's differs only in its payload — every edit arrives as `apply_patch` with a V4A envelope and no file path, so its block carries the envelope parser. Every advisory string, gate-config pattern and docs-path rule is identical across all four.
308
+ **Divergence budget:** every host's block carries `hooks/gateguard-engine.js` verbatim, and the Claude and Cursor blocks are byte-identical (both test-asserted on the generated hooks). opencode's differs only where the runtime forces it — ES module rather than CJS, tool vocabulary `write`/`edit`/`patch` rather than `Edit`/`Write`/`MultiEdit`. Codex's differs only in its payload — every edit arrives as `apply_patch` with a V4A envelope and no file path, so its block carries the envelope parser. Antigravity's differs only in its tool vocabulary (`write_to_file` / `replace_file_content`) and its `file_path` extraction. Every advisory string, gate-config pattern and docs-path rule is identical across all five.
292
309
 
293
310
  ---
294
311
 
@@ -308,7 +325,7 @@ Advisory hook, on all four hosts (Claude Code, Cursor, Codex, opencode). Claude
308
325
 
309
326
  **Install behaviour:** template drops, host-specific encoding of the **same** shared policy. No single canonical JSON — three native forms kept in lockstep. Machine-local paths stay out of templates.
310
327
 
311
- ### Network allowlist — one source, four hosts
328
+ ### Network allowlist — one source, five hosts
312
329
 
313
330
  **Source of truth:** bkit's own hosts come from the egress registry (`.bkit/core/engine/shared/egress.ts`) and must never be re-declared. Stack domains come from consumer `.agents/context.md` → `<!-- allowed-domains:start -->` **after** `<!-- bkit:end -->` (apex domains). Never ship Vercel/Supabase/Sentry/etc. into every consumer.
314
331
 
@@ -321,6 +338,7 @@ Advisory hook, on all four hosts (Claude Code, Cursor, Codex, opencode). Claude
321
338
  | **OpenCode** | Baked into `.opencode/opencode.json`: `permission.webfetch` URL map (`"*": "ask"` then `*{domain}*: allow`) for the fetch tool, and `permission.bash` `curl *`/`wget *` **ask** then `curl *{domain}*`/`wget *{domain}*` **allow** for shell fetch (last-match-wins on both) | Both fetch surfaces are domain-gated, so an allowlisted host does not prompt whichever path the agent takes. `webfetch` matches the resource against the requested URL, `bash` against the command string. No separate allowlist file. |
322
339
  | **Cursor** | Generated `.cursor/allowlist.json` read at **runtime** by `.cursor/hooks/bkit-guardrails.cjs` | Cursor has no project settings equivalent to Claude `permissions` / OpenCode `permission` for curl host globs. Parity is a **hook** (`beforeShellExecution`): ask on `curl`/`wget` unless the command contains a host from the allowlist. The JSON is Cursor-only by design (IDE-scoped artifact under `.cursor/`, not `.bkit/`). |
323
340
  | **Codex** | Reads the same `.cursor/allowlist.json` at runtime via `.codex/hooks/bkit-guardrails.cjs` | Codex has no project-level permission file. The hook host-parses `curl`/`wget` and emits an advisory `ask` — Codex cannot prompt, so the allowlist informs rather than enforces. |
341
+ | **Antigravity** | Reads the same `.cursor/allowlist.json` at runtime via `.agents/plugins/bkit/hooks/bkit-guardrails.cjs` | Antigravity has no project-level permission file. The hook host-parses `curl`/`wget` on the `run_command` matcher and emits an advisory `ask`. |
324
342
 
325
343
  **Do not hand-edit** `.cursor/allowlist.json` — regenerate via install/upgrade after changing `allowed-domains`. Missing file ⇒ the hook resolves no hosts and every host reads as unknown; there is deliberately no list embedded in the hook, because a second copy drifts from the registry silently.
326
344
 
@@ -405,7 +423,7 @@ Installed provider catalog changes. Look up model IDs before pinning in `.openco
405
423
 
406
424
  **opencode-zen / opencode-go — two OpenCode built-in providers.** Both emit minimal `provider.<id>` with only `options.apiKey: "{env:BKIT_OPENCODE_API_KEY}"` (no npm driver, no baseURL). OpenCode resolves from models.dev — Go Qwen/MiniMax use Anthropic `/messages`, not openai-compatible `/chat/completions`. Zen keyed `opencode`; Go `opencode-go`. `bkit install --opencode=opencode-zen` (or `=opencode-go`) → `bkit.opencodeProvider` in `package.json`; legacy `opencode` → `opencode-zen` via `OPENCODE_PROVIDER_ALIASES`. Reinstall **replaces** seeded block (heals hijacked npm/baseURL). Set `BKIT_OPENCODE_API_KEY` in `.bkit/.env` (<https://opencode.ai/auth>). Columns from **models.dev**.
407
425
 
408
- **All four providers ship curated columns.** Tier design — **per-tier quality target, cheapest sufficient pin**. A tier cell is not "the same rung of this provider's ladder": it is the cheapest model that **reaches that tier's Claude score**, and reaching means _approaching_ — it does not have to beat it. Targets are the LiveBench Agentic Coding scores on the board below (opus `claude-opus-5` **65.2**, sonnet `claude-sonnet-5` **59.4**, haiku `claude-haiku-5-5` **~51**). The opus and sonnet targets stay the 5.0 scores although the 5.5 pins are on the CSV: `claude-opus-5-5` lands level at `xhigh` (65.4), and the `claude-sonnet-5-5` rows don't read cleanly (see the board). The haiku target is Haiku 5.5 at `xhigh`, the closest measured rung to the `high` effort the summary writers run at. Where a provider's ceiling sits under the sonnet target, opus+sonnet **collapse onto that ceiling** — spreading them across two rungs buys nothing and costs quality on the sonnet half. Where a cheap model already clears the haiku target, the haiku cell **stays cheap** — a $5/task flagship serving a read-and-emit summariser is waste, not safety.
426
+ **All four opencode providers ship curated columns.** Tier design — **per-tier quality target, cheapest sufficient pin**. A tier cell is not "the same rung of this provider's ladder": it is the cheapest model that **reaches that tier's Claude score**, and reaching means _approaching_ — it does not have to beat it. Targets are the LiveBench Agentic Coding scores on the board below (opus `claude-opus-5` **65.2**, sonnet `claude-sonnet-5` **59.4**, haiku `claude-haiku-5-5` **~51**). The opus and sonnet targets stay the 5.0 scores although the 5.5 pins are on the CSV: `claude-opus-5-5` lands level at `xhigh` (65.4), and the `claude-sonnet-5-5` rows don't read cleanly (see the board). The haiku target is Haiku 5.5 at `xhigh`, the closest measured rung to the `high` effort the summary writers run at. Where a provider's ceiling sits under the sonnet target, opus+sonnet **collapse onto that ceiling** — spreading them across two rungs buys nothing and costs quality on the sonnet half. Where a cheap model already clears the haiku target, the haiku cell **stays cheap** — a $5/task flagship serving a read-and-emit summariser is waste, not safety.
409
427
 
410
428
  ### Selecting pins
411
429
 
@@ -335,7 +335,7 @@ PyPI name `serena-agent`, CLI `serena`. PyPI `serena` is an unrelated package.
335
335
 
336
336
  ## graphify — map
337
337
 
338
- On-demand only — not an MCP server, installed skill, CI job, or git hook. Agents read `docs/capabilities.md`; audit templates that need the graph build it via `scripts/graphify/bkit-graphify.sh`. Only tracked output: `docs/capabilities.md`. Mermaid views: `docs/graphify-out/reports/graph-packages.mmd`, `graph-modules.mmd`. Reference: https://github.com/Graphify-Labs/graphify.
338
+ On-demand only — not an installed skill or git hook. graphify ships an MCP server (`graphify-mcp`, stdio default); it stays unwired because its answers come from the `graph.json` snapshot and build/debug agents invalidate the graph faster than it rebuilds — Serena (no index to go stale) owns the agent surface. The one CI touch is the self-skipping register-freshness gate below: on pushes it installs a pinned graphify and runs `pnpm graph:check`, forcing `docs/capabilities.md` to be current. Agents read `docs/capabilities.md`; audit templates that need the graph build it via `scripts/graphify/bkit-graphify.sh`. Only tracked output: `docs/capabilities.md`. Mermaid views: `docs/graphify-out/reports/graph-packages.mmd`, `graph-modules.mmd`. Reference: https://github.com/Graphify-Labs/graphify.
339
339
 
340
340
  ```bash
341
341
  uv tool install "graphifyy[sql]"
@@ -371,6 +371,8 @@ graphify-out/
371
371
  ```
372
372
 
373
373
  - Paste `scripts/graphify/bkit-graph-pre-push.sh` at the end of your `.husky/pre-push`, below the bkit lines. Warn-only: does not run graphify, does not block push.
374
+ - `.github/workflows/bkit-ci.yml` ships `Check Capability Register` (push events): installs pinned graphify and runs `pnpm graph:check`, so a stale register fails CI. Self-skips without `scripts/graphify/bkit-graphify.sh`; bump `GRAPHIFY_SPEC` and refresh the register in the same change.
375
+ - graphify's MCP server is opt-in: install `graphifyy[mcp]` (`mcp` + `starlette`; HTTP transport also needs `uvicorn`) and pass the graph path explicitly — `graphify-mcp` defaults to `graphify-out/graph.json`, not the pinned `docs/graphify-out/graph.json`. Snapshot-dated answers suit audit/orientation, never build or debug.
374
376
  - `.graphifyignore` merges `.gitignore`.
375
377
  - Keep `package.json` in corpus — excluding it drops workspace `name` fields graphify resolves package imports with; graph still looks complete.
376
378
  - Keep `tsconfig.json` out; graphify reads `paths` regardless.
@@ -383,7 +385,7 @@ graphify-out/
383
385
  | `pnpm graph:clean` | Same, after deleting `docs/graphify-out/`. Required after any tsconfig `paths` change. `--force` does not invalidate the module-resolution cache. |
384
386
  | `pnpm graph:update` | Re-extract changed files, then recluster. |
385
387
  | `pnpm graph:rollup` | Package and module views, plus `docs/capabilities.md`. |
386
- | `pnpm graph:check` | Rebuild and fail if `docs/capabilities.md` is not what this tree produces. Run from a clean checkout before the dev → main PR. |
388
+ | `pnpm graph:check` | Rebuild and fail if `docs/capabilities.md` is not what this tree produces. Shipped as a self-skipping CI step (push events); enabled in bkit's own CI. |
387
389
  | `pnpm graph:scoped [path]` | One subtree. Default `apps/web/src`. |
388
390
  | `pnpm graph:graphml` | Opt-in GraphML for Gephi / yEd. |
389
391
 
@@ -196,7 +196,7 @@ Every phase command (`design`, `plan`, `build`, `debug`, `ship`) shares skeleton
196
196
  6. Step 2 — Worktree Setup (`bkit worktrees setup`: create / resume / adopt, copy `bkit.worktree.copy` (default `.env`, `.env.local`), install unless `bkit.worktree.install` is false; `bkit workflows start` + `bkit runtime row`; save input; `start-workflow` + `worktree-setup` step entries committed on `feat/{FID}`)
197
197
  7. Phase-specific steps (subagent invocations, gates, per-step new comment post)
198
198
  8. Summary step (subagent → commit → push → verdict)
199
- 9. Close Workflow (`bkit workflows close`, lock release, state → hand-off via `issue-update-review`; ship terminal `bkit:merged` + In Review via `issue-update-merged` (issue left OPEN — human reviews + closes); non-ship phases update state only, phase label unchanged; **final return** = verbatim `{phase}-summary.md` to user as the last action)
199
+ 9. Close Workflow (`bkit workflows close`, lock release, state → hand-off via `issue-update-review`; ship terminal `bkit:merged` + In Review via `issue-update-merged` (issue left OPEN — human reviews + closes); non-ship phases update state only, phase label unchanged; **final return** = verbatim `{phase}-summary.md` to user, then a plain-English offer, as the last actions)
200
200
  ```
201
201
 
202
202
  **Step convention:** every step ends `### 🔒 Gate N — {Step Name}` checklist (verify before proceed) + new tracker comment with one fenced section (§ Comment Lifecycle).
@@ -819,7 +819,7 @@ Each subsection documents command behaviour — steps, subagents, artifacts, ver
819
819
  | 8 — Design Organise | `@bkit-design-organise` | `design-v2-reviewed.md` | `design-v3-organised.md` (versioned draft) | Decompose design into dependency-annotated workstreams (`WS-N`). `ORGANISE_VERDICT` = FAIL (cycles) → Failure Path. |
820
820
  | 9 — Summary | `@bkit-design-summary` | highest design-v* + glob design-* | `design-summary.md` | Commit `chore({FID}): summary bkit [skip ci]` → push. `SUMMARY_VERDICT` = FAIL → Failure Path. Glob picks up `design-spike.md` — `Feasibility` leads with a spike FAIL. |
821
821
  | 10 — Suggest Workstreams | — | `design-v3-organised.md` | parent-issue comment, `status.jsonl` | `bkit workstreams comment` reads `## Suggested Workstreams` (none parsed → exit 3 → Failure Path) and builds one advisory comment for the parent issue: one line per `WS-N` (`Requires` included) plus the design link. `NEVER auto-trigger`. Never creates an issue, never comments on another issue, never sets blockers. |
822
- | 11 — Close Workflow | — | — | `{YYYYMM}/{FID}-design.md` (copy of v3), `{YYYYMM}/archive/` (superseded, re-run only) | `bkit workflows promote` (anchor stamped from the runtime-resolved base commit, any changed canonical archived, v3 copied to the canonical bucket) → `bkit workflows close --record-step --outbox --message=` (compliance grade, close row, telemetry, `chore({FID}): close-workflow` commit in the worktree) → `cd {REPO_ROOT}` → `bkit branches land`. Local (runtime pushes dev, dev lock): checkout `dev` → stray-artifact check → squash `feat/{FID}` → non-doc and canonical-blob checks → roadmap row → `docs({FID}): design DONE` commit (`--squash-of`) → push `dev` → remove the workflow-created worktree and its branch. PR mode: roadmap commit → push → open or reuse the PR → squash-merge it (exit 80 hands either stage to MCP; re-run with `--pr` / `--merged-sha`). Both: landed-body scan, transport cross-check, `close-transport` row, lock release → `bkit workflows links --ref={CANONICAL_REF} --outbox` prints the close comment. Set state `In Review`; phase label `Design` persists. Final return displays `design-summary.md` verbatim. |
822
+ | 11 — Close Workflow | — | — | `{YYYYMM}/{FID}-design.md` (copy of v3), `{YYYYMM}/archive/` (superseded, re-run only) | `bkit workflows promote` (anchor stamped from the runtime-resolved base commit, any changed canonical archived, v3 copied to the canonical bucket) → `bkit workflows close --record-step --outbox --message=` (compliance grade, close row, telemetry, `chore({FID}): close-workflow` commit in the worktree) → `cd {REPO_ROOT}` → `bkit branches land`. Local (runtime pushes dev, dev lock): checkout `dev` → stray-artifact check → squash `feat/{FID}` → non-doc and canonical-blob checks → roadmap row → `docs({FID}): design DONE` commit (`--squash-of`) → push `dev` → remove the workflow-created worktree and its branch. PR mode: roadmap commit → push → open or reuse the PR → squash-merge it (exit 80 hands either stage to MCP; re-run with `--pr` / `--merged-sha`). Both: landed-body scan, transport cross-check, `close-transport` row, lock release → `bkit workflows links --ref={CANONICAL_REF} --outbox` prints the close comment. Set state `In Review`; phase label `Design` persists. Final return displays `design-summary.md` verbatim, then offers a plain-English explanation on request. |
823
823
 
824
824
  **Hard stop in Step 11 caution block:** "Design requires human review. Do not invoke `/bkit-plan`."
825
825
 
@@ -843,7 +843,7 @@ Each subsection documents command behaviour — steps, subagents, artifacts, ver
843
843
  | 9 — Check `Complexity` | `@bkit-plan-complexity-check` | `COMPLEXITY_VERDICT` ∈ {SINGLE, SPLIT}, read and recorded on the `plan-complexity-check` row as `verdict` by `steps finish --agent=bkit-plan-complexity-check` (the agent's own verdict set); exit 5 / 6 re-asks the agent. |
844
844
  | 10 — Split Plan | `@bkit-plan-complexity-split` _(only if `split`)_ | Writes `{FID}-plan-N.md` sub-plans + `plan-split.md` log; self-verifies losslessness (`SPLIT_VERDICT` ∈ {PASS, FAIL}; FAIL → Failure Path). |
845
845
  | 11 — Summary | `@bkit-plan-summary` | Commit `chore({FID}): summary bkit [skip ci]` → push. |
846
- | 12 — Close Workflow | — | Archive any existing canonical → copy v4 → sync to `dev`, remove worktree, delete branches (same as `/bkit-design` Step 11, except `workflows promote` moves the whole `{FID}-plan*.md` set to the archive under one timestamp, copies the split's children as `{FID}-plan-{k}.md` with working names rewritten, and stamps `designPath` / `designBaseSha` into the anchor). Set state `In Review`; phase label `Plan` persists. Final return displays `plan-summary.md` verbatim. |
846
+ | 12 — Close Workflow | — | Archive any existing canonical → copy v4 → sync to `dev`, remove worktree, delete branches (same as `/bkit-design` Step 11, except `workflows promote` moves the whole `{FID}-plan*.md` set to the archive under one timestamp, copies the split's children as `{FID}-plan-{k}.md` with working names rewritten, and stamps `designPath` / `designBaseSha` into the anchor). Set state `In Review`; phase label `Plan` persists. Final return displays `plan-summary.md` verbatim, then offers a plain-English explanation on request. |
847
847
 
848
848
  **Hard stop in Step 12 caution block:** "Plan requires human review. Do not invoke `/bkit-build`."
849
849
 
@@ -875,7 +875,7 @@ Each subsection documents command behaviour — steps, subagents, artifacts, ver
875
875
  | 15 — Diagnose Failure | `@bkit-debug-failure-diagnose` _(only if Step 14 FAIL)_ | Reads the committed Step 14 test log `docs/plans/{YYYYMM}/logs/{FID}/run-tests-{TEST_ATTEMPT}.md`. Writes `build-failure-diagnose-{TEST_ATTEMPT}.md`. |
876
876
  | 16 — Remediate Failure | `@bkit-debug-failure-remediate` _(only if Step 14 FAIL)_ | Writes `build-failure-remediate-{TEST_ATTEMPT}-log.md`. Stub-first artifact + flat append-only log (`DONE —` per fix step; `BLOCKED —` per blocked step, appended via `Bash echo >>`). No skip-done — each attempt is diagnosis-driven and may pick a different strategy. Re-run Step 14 (its next row is the next `TEST_ATTEMPT`). > `MAX_TEST_ATTEMPT` → Failure Path. |
877
877
  | 17 — Summary | `@bkit-build-summary` | Commit `chore({FID}): summary` → open-PR probe → push (`-u origin {BRANCH}`). PR already open (resumed build) → push would fire CI + cloud auto-router on a branch build is still writing → probe stops run first (same probe as Step 18). `bkit-cloud.yml` backstop: no-op while build runs (`.bkit/cloud.md` § Branch-aware routing). |
878
- | 18 — Close Workflow & Create PR | — | `bkit:auto` re-read before close-workflow commit; open-PR probe; if any changed path sits under a `migrations/` or `migrate/` directory (case-insensitive, any depth — covers Supabase, Prisma, Drizzle, Rails) and HEAD lacks `bkit [force build]` → amend or empty commit with `bkit [force build]` → push. `bkit prs open` (base pinned `dev`; body = the `bkit:issue` / `bkit:fid` marker + plan path; retries the create once; reads the base back → exit 6 when it is not `dev`, guarding repos whose default base is `main`); exit 80 → `create_pull_request` with the printed `title` / `body` / `base` / `head`. Then CI-Dispatch Gate (`bkit runs dispatch`). Set state `In Review`; phase label `Build` persists. Worktree persists for follow-up `/bkit-debug` or `/bkit-ship`. Final return displays `build-summary.md` verbatim. |
878
+ | 18 — Close Workflow & Create PR | — | `bkit:auto` re-read before close-workflow commit; open-PR probe; if any changed path sits under a `migrations/` or `migrate/` directory (case-insensitive, any depth — covers Supabase, Prisma, Drizzle, Rails) and HEAD lacks `bkit [force build]` → amend or empty commit with `bkit [force build]` → push. `bkit prs open` (base pinned `dev`; body = the `bkit:issue` / `bkit:fid` marker + plan path; retries the create once; reads the base back → exit 6 when it is not `dev`, guarding repos whose default base is `main`); exit 80 → `create_pull_request` with the printed `title` / `body` / `base` / `head`. Then CI-Dispatch Gate (`bkit runs dispatch`). Set state `In Review`; phase label `Build` persists. Worktree persists for follow-up `/bkit-debug` or `/bkit-ship`. Final return displays `build-summary.md` verbatim, then offers a plain-English explanation on request. |
879
879
 
880
880
  **Failure Path includes handover** — when triggered by exhausted retry counts, invokes `@bkit-debug-abort-handover` and posts `Workflow Handover` comment.
881
881
 
@@ -905,7 +905,7 @@ Each subsection documents command behaviour — steps, subagents, artifacts, ver
905
905
  | 7 — Failure Remediate Soak | `@bkit-debug-failure-soak` _(only if `DEBUG_MODE` = SOAK)_ | `SOAK_ATTEMPT` = soak rows since `soakEntryAt` + 1 (`counters derive --since=soakEntryAt`). One accumulating context (reads its prior `debug-failure-soak-*-log.md`) applies the single next instrument-or-fix step against the failing boundary (the real model/DB/stream behind a live tier when one ran, else the failing tier the run surfaced); adds `[DEBUG-OBSERVE]` scaffolding and strips every marker before any declared fix (no-leak); commits `fix({FID}): soak {description}`. → loop to Step 3. Bounded by `SOAK_ATTEMPT` (`MAX_SOAK_ATTEMPT`, counted from each SOAK entry). |
906
906
  | 8 — Push Remediation | — | _(PASS after a fix)_ Status file-only (no intermediate commit so Step 6/7's `fix(...)` stays HEAD at push). PR-mode: append `bkit [verbose ci]` to PR title if absent. Push. → Step 9. |
907
907
  | 9 — Summary | `@bkit-debug-summary` | Commit `chore({FID}): summary{VERBOSE_SUFFIX}` → push. `SUMMARY_VERDICT` = PASS/CONCERNS → Step 10; FAIL → Failure Path. |
908
- | 10 — Close Workflow | — | No-leak assertion: fails the run if any added `[DEBUG-OBSERVE]` line survives the debug diff (`git diff origin/dev..HEAD`, excluding `docs/plans/`) before the CI-triggering push — diff-scoped, not a tree-wide `git grep`, so the bkit-managed prompt/command files that quote the literal marker never false-trip (the soak agent's own `git grep '[DEBUG-OBSERVE]'` self-check in `bkit-debug-failure-soak.md` is the first layer). Else Failure Path. PR-mode: strip `bkit [verbose ci]` from PR title. Commit `chore({FID}): close-workflow{VERBOSE_SUFFIX}` → push + (LOCAL, no PR) `chore({FID}): create-pr{VERBOSE_SUFFIX}` (`VERBOSE_SUFFIX = " bkit [verbose ci]"` iff `PUSH_MODE = LOCAL`). Auto-route marker `bkit [auto route]` on the CI-triggering HEAD when `bkit:auto`. Records `testsLiveSkipped` when no live tier ran (no `test:...:live` task in `scope`). Set state `In Review`; phase label `Debug` persists. Worktree persists. The handover path runs via Failure Path. Final return displays `debug-summary.md` verbatim. |
908
+ | 10 — Close Workflow | — | No-leak assertion: fails the run if any added `[DEBUG-OBSERVE]` line survives the debug diff (`git diff origin/dev..HEAD`, excluding `docs/plans/`) before the CI-triggering push — diff-scoped, not a tree-wide `git grep`, so the bkit-managed prompt/command files that quote the literal marker never false-trip (the soak agent's own `git grep '[DEBUG-OBSERVE]'` self-check in `bkit-debug-failure-soak.md` is the first layer). Else Failure Path. PR-mode: strip `bkit [verbose ci]` from PR title. Commit `chore({FID}): close-workflow{VERBOSE_SUFFIX}` → push + (LOCAL, no PR) `chore({FID}): create-pr{VERBOSE_SUFFIX}` (`VERBOSE_SUFFIX = " bkit [verbose ci]"` iff `PUSH_MODE = LOCAL`). Auto-route marker `bkit [auto route]` on the CI-triggering HEAD when `bkit:auto`. Records `testsLiveSkipped` when no live tier ran (no `test:...:live` task in `scope`). Set state `In Review`; phase label `Debug` persists. Worktree persists. The handover path runs via Failure Path. Final return displays `debug-summary.md` verbatim, then offers a plain-English explanation on request. |
909
909
 
910
910
  **Failure Path** includes conditional handover via `@bkit-debug-abort-handover` when max-retry exhausted → `debug-handover.md`. PR-mode `bkit [verbose ci]` **preserved** (not stripped) — investigator wants ongoing verbose CI; § `bkit [verbose ci]` Marker Propagation cleanup invariant.
911
911
 
@@ -962,7 +962,7 @@ Each subsection documents command behaviour — steps, subagents, artifacts, ver
962
962
  | 12 — Failure Remediate | `@bkit-debug-failure-remediate` _(only if not merged)_ | Writes `ship-failure-remediate-{MERGE_ATTEMPT}-log.md`. `Strategy` ladder (`STANDARD → PIVOT → FINAL`). PASS → Step 10 (re-merge). FAIL → Failure Path. |
963
963
  | 13 — Switch to Dev | — | `bkit branches switch --dev-pushes= --worktrees=`: under the dev lock, `git checkout dev`, fetch + fast-forward, rebase-and-push local `dev` commits that are all skip-CI (any CI-running local commit → exit 82, needs a human), install dependencies (failure → exit 16 → **Failure Path**). `RUNTIME_DEVPUSHES=false`: skipped (merge already landed server-side). |
964
964
  | 14 — Worktree Cleanup | — | `bkit worktrees remove --branch={SHIP_BRANCH}` removes only a worktree a workflow created (`.worktree-owned` marker in the outbox; absent = "not mine"), prunes, then deletes the local and remote branch and prunes tracking refs. A worktree still holding the branch (an unmarked one) blocks both deletes and is named in `branchBlockedBy` — a local delete would fail while the remote delete went through. `dev` / `main` refused (exit 2). |
965
- | 15 — Close Workflow | — | `bkit runs gate --squash-of=<PR> --capstone-only --record={STATUS}` → records `ship-merge-ci`, then refuses unless the capstone passed at the squash commit. The capstone job's result alone decides: the run's conclusion and other jobs (deploys, notifications) never fail the close of a merged PR. `bkit workflows close --flush --pr-number= --squash-sha= --outbox= --token=` grades compliance, records `ship-close-workflow`, writes telemetry, and makes the single path-scoped `[skip ci]` close commit under the dev lock: with `--dev-pushes` → `dev` checkout + push `dev`; else a close worktree off `origin/dev` → push `dev`, refused → `ship-close/{FID}` PR; the workflow lock is released before the push. Add `bkit:merged` label, drop `bkit:failed`. Final return displays `ship-summary.md` verbatim. **HARD STOP**. |
965
+ | 15 — Close Workflow | — | `bkit runs gate --squash-of=<PR> --capstone-only --record={STATUS}` → records `ship-merge-ci`, then refuses unless the capstone passed at the squash commit. The capstone job's result alone decides: the run's conclusion and other jobs (deploys, notifications) never fail the close of a merged PR. `bkit workflows close --flush --pr-number= --squash-sha= --outbox= --token=` grades compliance, records `ship-close-workflow`, writes telemetry, and makes the single path-scoped `[skip ci]` close commit under the dev lock: with `--dev-pushes` → `dev` checkout + push `dev`; else a close worktree off `origin/dev` → push `dev`, refused → `ship-close/{FID}` PR; the workflow lock is released before the push. Add `bkit:merged` label, drop `bkit:failed`. Final return displays `ship-summary.md` verbatim, then offers a plain-English explanation on request. **HARD STOP**. |
966
966
 
967
967
  **Failure Path** resolves `BOOK_ROOT` (not `--git-common-dir`), runs `bkit workflows fail` (aborts a rebase, appends `workflow-failed`, releases the lock, clears `.deferred-blocked`), and includes conditional handover via `@bkit-debug-abort-handover` writing `ship-handover.md` when max-retry exhausted.
968
968
 
@@ -74,4 +74,15 @@ Read and execute the matched command file for the current IDE.
74
74
  | `Plan` | `.claude/commands/bkit-plan.md` |
75
75
  | `Design` | `.claude/commands/bkit-design.md` |
76
76
 
77
+ **Antigravity** (`.agents/plugins/bkit/skills/`):
78
+
79
+ <!-- prettier-ignore -->
80
+ | Label | Command |
81
+ | --- | --- |
82
+ | `Ship` | `.agents/plugins/bkit/skills/bkit-ship/SKILL.md` |
83
+ | `Debug` | `.agents/plugins/bkit/skills/bkit-debug/SKILL.md` |
84
+ | `Build` | `.agents/plugins/bkit/skills/bkit-build/SKILL.md` |
85
+ | `Plan` | `.agents/plugins/bkit/skills/bkit-plan/SKILL.md` |
86
+ | `Design` | `.agents/plugins/bkit/skills/bkit-design/SKILL.md` |
87
+
77
88
  <!-- bkit:end -->
@@ -174,11 +174,14 @@ export interface MissingOwnedHook {
174
174
  }
175
175
 
176
176
  /** Host modules whose manifest hook files a host config runs, and the flag that installs each. */
177
- const HOOK_HOST_FLAGS: ReadonlyArray<["claude" | "cursor" | "codex" | "opencode", string]> = [
177
+ const HOOK_HOST_FLAGS: ReadonlyArray<
178
+ ["claude" | "cursor" | "codex" | "opencode" | "antigravity", string]
179
+ > = [
178
180
  ["claude", "--claude"],
179
181
  ["cursor", "--cursor"],
180
182
  ["codex", "--codex"],
181
183
  ["opencode", "--opencode=<provider>"],
184
+ ["antigravity", "--antigravity"],
182
185
  ];
183
186
 
184
187
  /** Manifest paths a host runs as a hook: `.<host>/hooks/<file>` and `.opencode/plugin/<file>`. */