@cbartens/bkit 5.2.4 → 5.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.bkit/README.md +27 -11
- package/.bkit/core/.agents/context.md +1 -1
- package/.bkit/core/.agents/docs.md +1 -1
- package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +1 -1
- package/.bkit/core/.agents/rules.md +18 -1
- package/.bkit/core/.bkit/README.md +26 -10
- package/.bkit/core/.bkit/cloud.md +40 -39
- package/.bkit/core/.bkit/comparison.md +68 -345
- package/.bkit/core/.bkit/install.md +16 -9
- package/.bkit/core/.bkit/lite.md +73 -0
- package/.bkit/core/.bkit/pipeline.md +346 -0
- package/.bkit/core/.bkit/prompts.md +90 -74
- package/.bkit/core/.bkit/providers.md +42 -23
- package/.bkit/core/.bkit/templates.md +138 -19
- package/.bkit/core/.bkit/trackers.md +49 -4
- package/.bkit/core/.bkit/workflows.md +144 -123
- package/.bkit/core/.claude/hooks/bkit-guardrails.cjs +1 -1
- package/.bkit/core/.codex/hooks/bkit-guardrails.cjs +7 -4
- package/.bkit/core/.cursor/hooks/bkit-guardrails.cjs +8 -5
- package/.bkit/core/docs/templates/bkit-audit-accessibility.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-adoption.md +2 -2
- package/.bkit/core/docs/templates/bkit-audit-agents.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-analytics.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-annotations.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-app-performance.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-app-store.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-architecture.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +4 -2
- package/.bkit/core/docs/templates/bkit-audit-config.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-cost.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-coverage.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-database.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-dead-code.md +5 -5
- package/.bkit/core/docs/templates/bkit-audit-deferrals.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-dependencies.md +26 -21
- package/.bkit/core/docs/templates/bkit-audit-documentation.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-duplication.md +2 -2
- package/.bkit/core/docs/templates/bkit-audit-failures.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-flakes.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-gates.md +5 -2
- package/.bkit/core/docs/templates/bkit-audit-issues.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-llm.md +22 -15
- package/.bkit/core/docs/templates/bkit-audit-logs.md +10 -6
- package/.bkit/core/docs/templates/bkit-audit-models.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-privacy.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-prompts.md +7 -7
- package/.bkit/core/docs/templates/bkit-audit-red-team.md +12 -9
- package/.bkit/core/docs/templates/bkit-audit-reliability.md +3 -2
- package/.bkit/core/docs/templates/bkit-audit-repo.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-security.md +14 -12
- package/.bkit/core/docs/templates/bkit-audit-slop.md +1 -1
- package/.bkit/core/docs/templates/bkit-audit-testing.md +10 -8
- package/.bkit/core/docs/templates/bkit-audit-usability.md +1 -1
- package/.bkit/core/docs/templates/bkit-plan.md +8 -6
- package/.bkit/core/engine/checks/after/auth.ts +9 -9
- package/.bkit/core/engine/checks/after/ci-yml.ts +14 -12
- package/.bkit/core/engine/checks/after/github.ts +29 -120
- package/.bkit/core/engine/checks/after/index.ts +2 -2
- package/.bkit/core/engine/checks/after/managed.ts +8 -28
- package/.bkit/core/engine/checks/after/tools.ts +3 -15
- package/.bkit/core/engine/checks/before/context-fetch.ts +1 -21
- package/.bkit/core/engine/checks/before/index.ts +7 -43
- package/.bkit/core/engine/checks/before/mcp.ts +17 -8
- package/.bkit/core/engine/checks/before/repo.ts +9 -12
- package/.bkit/core/engine/checks/status-holes.ts +4 -6
- package/.bkit/core/engine/checks/tips/catalogue.ts +76 -24
- package/.bkit/core/engine/checks/tips/detect.ts +45 -2
- package/.bkit/core/engine/checks/tips/index.ts +77 -26
- package/.bkit/core/engine/cli.ts +57 -27
- package/.bkit/core/engine/commands/analysis.ts +36 -26
- package/.bkit/core/engine/commands/comply.ts +42 -32
- package/.bkit/core/engine/commands/harvest.ts +12 -12
- package/.bkit/core/engine/commands/install/doctor.ts +57 -28
- package/.bkit/core/engine/commands/install/install.ts +73 -130
- package/.bkit/core/engine/commands/install/uninstall.ts +191 -33
- package/.bkit/core/engine/commands/install/upgrade.ts +49 -43
- package/.bkit/core/engine/commands/land.ts +156 -0
- package/.bkit/core/engine/commands/lib.ts +45 -18
- package/.bkit/core/engine/commands/registry.ts +2 -0
- package/.bkit/core/engine/commands/tips.ts +12 -5
- package/.bkit/core/engine/commands/workflow/branches.ts +386 -286
- package/.bkit/core/engine/commands/workflow/counters.ts +21 -12
- package/.bkit/core/engine/commands/workflow/disk.ts +556 -0
- package/.bkit/core/engine/commands/workflow/fids.ts +46 -0
- package/.bkit/core/engine/commands/workflow/issues.ts +73 -28
- package/.bkit/core/engine/commands/workflow/ledgers.ts +3 -1
- package/.bkit/core/engine/commands/workflow/locks.ts +38 -152
- package/.bkit/core/engine/commands/workflow/prs.ts +15 -4
- package/.bkit/core/engine/commands/workflow/repo.ts +2 -2
- package/.bkit/core/engine/commands/workflow/roadmap.ts +49 -53
- package/.bkit/core/engine/commands/workflow/runs.ts +8 -7
- package/.bkit/core/engine/commands/workflow/runtime.ts +3 -2
- package/.bkit/core/engine/commands/workflow/status.ts +33 -11
- package/.bkit/core/engine/commands/workflow/steps.ts +25 -15
- package/.bkit/core/engine/commands/workflow/tests.ts +17 -5
- package/.bkit/core/engine/commands/workflow/workflows.ts +436 -267
- package/.bkit/core/engine/commands/workflow/workstreams.ts +4 -2
- package/.bkit/core/engine/commands/workflow/worktrees.ts +24 -6
- package/.bkit/core/engine/install/cloud-env.ts +10 -31
- package/.bkit/core/engine/install/manifest.ts +14 -7
- package/.bkit/core/engine/install/modules/antigravity.ts +15 -26
- package/.bkit/core/engine/install/modules/claude.ts +20 -28
- package/.bkit/core/engine/install/modules/cloud.ts +5 -2
- package/.bkit/core/engine/install/modules/codex.ts +15 -29
- package/.bkit/core/engine/install/modules/core.ts +106 -70
- package/.bkit/core/engine/install/modules/cursor.ts +6 -20
- package/.bkit/core/engine/install/modules/index.ts +7 -1
- package/.bkit/core/engine/install/modules/opencode.ts +48 -70
- package/.bkit/core/engine/install/network-allowlist.ts +73 -0
- package/.bkit/core/engine/install/placeholders.ts +16 -35
- package/.bkit/core/engine/install/write.ts +59 -12
- package/.bkit/core/engine/ledgers/telemetry.ts +6 -4
- package/.bkit/core/engine/render/hosts.ts +47 -67
- package/.bkit/core/engine/render/models.ts +29 -11
- package/.bkit/core/engine/shared/branches.ts +13 -0
- package/.bkit/core/engine/shared/egress.ts +3 -3
- package/.bkit/core/engine/shared/json.ts +18 -1
- package/.bkit/core/engine/shared/package-json.ts +63 -0
- package/.bkit/core/engine/shared/package-roots.ts +0 -10
- package/.bkit/core/engine/shared/protected-paths.ts +5 -130
- package/.bkit/core/engine/shared/settings.ts +44 -0
- package/.bkit/core/engine/shared/timeouts.ts +8 -7
- package/.bkit/core/hooks/antigravity-hook.js +1 -0
- package/.bkit/core/hooks/guardrails-shell.js +186 -40
- package/.bkit/core/hooks/guardrails-tiers.js +5 -78
- package/.bkit/core/prompts/bkit-audit-generate.md +103 -7
- package/.bkit/core/prompts/bkit-build-challenge-1.md +1 -1
- package/.bkit/core/prompts/bkit-build-challenge-2.md +1 -1
- package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +1 -1
- package/.bkit/core/prompts/bkit-build-challenge-remediate.md +1 -1
- package/.bkit/core/prompts/bkit-build-challenge-tests.md +1 -1
- package/.bkit/core/prompts/bkit-build-install-skills.md +1 -1
- package/.bkit/core/prompts/bkit-build-plan-current.md +1 -1
- package/.bkit/core/prompts/bkit-build-plan-execute.md +4 -4
- package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +1 -1
- package/.bkit/core/prompts/bkit-build-plan-verify.md +2 -2
- package/.bkit/core/prompts/bkit-debug-abort-handover.md +1 -1
- package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +1 -1
- package/.bkit/core/prompts/bkit-debug-failure-remediate.md +1 -1
- package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +78 -0
- package/.bkit/core/prompts/bkit-debug-failure-soak.md +1 -1
- package/.bkit/core/prompts/bkit-debug-summary.md +3 -3
- package/.bkit/core/prompts/bkit-design-spike.md +1 -1
- package/.bkit/core/prompts/bkit-design-summary.md +2 -2
- package/.bkit/core/prompts/bkit-design-update.md +1 -1
- package/.bkit/core/prompts/bkit-plan-complexity-check.md +1 -1
- package/.bkit/core/prompts/bkit-plan-generate.md +1 -1
- package/.bkit/core/prompts/bkit-plan-scope-check-1.md +1 -1
- package/.bkit/core/prompts/bkit-plan-scope-check-2.md +1 -1
- package/.bkit/core/prompts/bkit-plan-summary.md +1 -1
- package/.bkit/core/prompts/bkit-plan-update.md +1 -1
- package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +1 -1
- package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +1 -1
- package/.bkit/core/prompts/bkit-ship-update-docs.md +1 -1
- package/.bkit/core/prompts/bkit-utility-update-decisions.md +9 -2
- package/.bkit/core/prompts/bkit-utility-update-deferrals.md +9 -2
- package/.bkit/core/prompts/bkit-utility-update-documentation.md +2 -1
- package/.bkit/core/prompts/bkit-utility-update-failures.md +9 -2
- package/.bkit/core/prompts/bkit-utility-update-knowledge.md +9 -2
- package/.bkit/core/prompts/bkit-utility-update-roadmap.md +11 -4
- package/.bkit/core/workflows/bkit-auto.md +2 -2
- package/.bkit/core/workflows/bkit-build.md +10 -10
- package/.bkit/core/workflows/bkit-debug.md +80 -44
- package/.bkit/core/workflows/bkit-design.md +22 -13
- package/.bkit/core/workflows/bkit-plan.md +33 -16
- package/.bkit/core/workflows/bkit-ship.md +87 -98
- package/.bkit/shared/.claude/bkit-cloud.md +58 -25
- package/.bkit/shared/.claude/settings.json +19 -0
- package/.bkit/shared/.cursor/mcp.json +2 -1
- package/.bkit/shared/.opencode/opencode.json +19 -1
- package/.bkit/shared/docs/deployments.md +49 -29
- package/.bkit/shared/docs/security.md +8 -6
- package/.bkit/shared/docs/testing.md +9 -5
- package/.bkit/shared/gitignore +1 -2
- package/.bkit/templates/.cursor/Dockerfile +30 -16
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +78 -0
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +91 -0
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +56 -0
- package/.bkit/templates/.github/renovate.json5 +91 -12
- package/.bkit/templates/.github/workflows/bkit-ci.yml +73 -55
- package/.bkit/templates/.github/workflows/bkit-cloud.yml +3 -1
- package/.bkit/templates/.github/workflows/bkit-renovate.yml +8 -1
- package/.bkit/templates/.github/workflows/bkit-trivy.yml +67 -0
- package/.bkit/templates/.husky/pre-commit +6 -0
- package/.bkit/templates/.husky/pre-push +15 -3
- package/.bkit/templates/.lintstagedrc.json +5 -1
- package/.bkit/templates/.oxlintrc.json +21 -0
- package/.bkit/templates/docs/capabilities.md +1 -1
- package/.bkit/templates/scripts/ci/check-capstone.mjs +176 -0
- package/.bkit/templates/scripts/ci/check-capstone.test.mjs +311 -0
- package/.bkit/templates/scripts/cleanup/bkit-disk-prune.machine.mjs +197 -0
- package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +164 -0
- package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +2 -2
- package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +43 -20
- package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +33 -11
- package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -2
- package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +5 -5
- package/.bkit/templates/scripts/graphify/bkit-graphify.sh +79 -19
- package/CHANGELOG.md +98 -3
- package/README.md +252 -122
- package/dist/checks/after/auth.js +10 -11
- package/dist/checks/after/ci-yml.js +11 -14
- package/dist/checks/after/github.js +32 -125
- package/dist/checks/after/index.js +3 -2
- package/dist/checks/after/managed.js +8 -24
- package/dist/checks/after/tools.js +3 -16
- package/dist/checks/before/context-fetch.js +1 -21
- package/dist/checks/before/index.js +6 -42
- package/dist/checks/before/mcp.js +14 -9
- package/dist/checks/before/repo.js +8 -11
- package/dist/checks/status-holes.js +5 -7
- package/dist/checks/tips/catalogue.js +65 -18
- package/dist/checks/tips/detect.js +41 -2
- package/dist/checks/tips/index.js +61 -25
- package/dist/cli.js +52 -26
- package/dist/commands/analysis.js +21 -5
- package/dist/commands/comply.js +40 -31
- package/dist/commands/harvest.js +12 -13
- package/dist/commands/install/doctor.js +55 -23
- package/dist/commands/install/install.js +72 -122
- package/dist/commands/install/uninstall.js +165 -31
- package/dist/commands/install/upgrade.js +46 -39
- package/dist/commands/land.js +129 -0
- package/dist/commands/lib.js +41 -16
- package/dist/commands/registry.js +2 -0
- package/dist/commands/tips.js +10 -3
- package/dist/commands/workflow/branches.js +303 -248
- package/dist/commands/workflow/counters.js +17 -7
- package/dist/commands/workflow/disk.js +452 -0
- package/dist/commands/workflow/fids.js +39 -0
- package/dist/commands/workflow/issues.js +63 -27
- package/dist/commands/workflow/ledgers.js +3 -1
- package/dist/commands/workflow/locks.js +35 -130
- package/dist/commands/workflow/prs.js +8 -5
- package/dist/commands/workflow/repo.js +2 -2
- package/dist/commands/workflow/roadmap.js +50 -57
- package/dist/commands/workflow/runs.js +5 -5
- package/dist/commands/workflow/runtime.js +3 -2
- package/dist/commands/workflow/status.js +32 -12
- package/dist/commands/workflow/steps.js +19 -11
- package/dist/commands/workflow/tests.js +16 -3
- package/dist/commands/workflow/workflows.js +390 -249
- package/dist/commands/workflow/workstreams.js +4 -2
- package/dist/commands/workflow/worktrees.js +15 -6
- package/dist/install/cloud-env.js +10 -23
- package/dist/install/manifest.js +14 -7
- package/dist/install/modules/antigravity.js +15 -26
- package/dist/install/modules/claude.js +17 -21
- package/dist/install/modules/cloud.js +6 -2
- package/dist/install/modules/codex.js +15 -29
- package/dist/install/modules/core.js +95 -63
- package/dist/install/modules/cursor.js +6 -9
- package/dist/install/modules/index.js +6 -1
- package/dist/install/modules/opencode.js +41 -72
- package/dist/install/network-allowlist.js +62 -0
- package/dist/install/placeholders.js +16 -35
- package/dist/install/write.js +55 -15
- package/dist/ledgers/telemetry.js +5 -4
- package/dist/render/hosts.js +30 -55
- package/dist/render/models.js +20 -9
- package/dist/shared/branches.js +11 -0
- package/dist/shared/egress.js +0 -2
- package/dist/shared/json.js +14 -0
- package/dist/shared/package-json.js +61 -0
- package/dist/shared/package-roots.js +0 -8
- package/dist/shared/protected-paths.js +5 -122
- package/dist/shared/settings.js +23 -1
- package/dist/shared/timeouts.js +8 -7
- package/package.json +21 -17
- package/.bkit/core/.agents/shortcuts.md +0 -73
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
<!-- bkit:start -->
|
|
2
|
+
|
|
3
|
+
{{BKIT_MANAGED_MARKER}}
|
|
4
|
+
|
|
5
|
+
# Lite Workflows
|
|
6
|
+
|
|
7
|
+
> [!CAUTION]
|
|
8
|
+
> **Purpose:** Opt-in prompts that run a phase's steps and subagents without the full workflow's ceremony. The full workflow is the default.
|
|
9
|
+
>
|
|
10
|
+
> **Rules:**
|
|
11
|
+
>
|
|
12
|
+
> - All `.agents/rules.md` rules still apply. Fewer steps, never fewer rules.
|
|
13
|
+
> - The named reference is **inspiration, not a command file**: read it for its steps and subagents, take what fits, drop the rest.
|
|
14
|
+
> - Assume the right repo and branch are already checked out; do not re-detect them.
|
|
15
|
+
> - Local project lite workflows → `Project Lite Workflows` below the bkit-managed block.
|
|
16
|
+
|
|
17
|
+
## When to use
|
|
18
|
+
|
|
19
|
+
Full workflow when in doubt; a lite workflow only when it is clearly enough. These are opt-in at your own judgement — they skip the gates, worktree isolation, PR, CI and audit trail, so they suit users who know what they are trading away. Add whichever full-phase step or subagent the work needs; go full when the cost of being wrong is high — irreversible changes (releases, data), blast radius past one small change, security / secrets / PII.
|
|
20
|
+
|
|
21
|
+
NEVER a lite workflow for: schema / migrations, public API, dependencies, secrets / config, auth / security, large multi-file refactors.
|
|
22
|
+
|
|
23
|
+
## Contract
|
|
24
|
+
|
|
25
|
+
Read `.agents/rules.md`. Work on the current branch; commit as you go; push only when shipping or when asked. Tracker-wired: issue → **In progress** + `bkit:<phase>` label at start (drops other `bkit:*` workflow labels, `next:*`, `bkit:failed` per `.agents/rules.md` § Tracker workflow labels), **In review** at end, one short comment per step. No tracker: skip the tracker lines.
|
|
26
|
+
|
|
27
|
+
## Paste
|
|
28
|
+
|
|
29
|
+
Start the session on the phase's model from `.bkit/prompts.md` § Orchestrators. Copy one block — its heading is the lite workflow's name — then insert the issue or instructions at the bracketed line.
|
|
30
|
+
|
|
31
|
+
### design:lite
|
|
32
|
+
|
|
33
|
+
```text
|
|
34
|
+
Handle the issue below as a design. Read `.bkit/workflows.md` § Per-Phase Workflows and `.bkit/prompts.md` as inspiration only — keep the steps that fit, skip the rest. Dispatch each kept subagent step to its `bkit-*` subagent on the model `.bkit/prompts.md` § Models pins for it; NEVER do subagent work inline. No subagent tool → run its prompt file in-session. Follow `.bkit/lite.md` § Contract.
|
|
35
|
+
|
|
36
|
+
[INSERT ISSUE ID / INSTRUCTIONS]
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
### plan:lite
|
|
40
|
+
|
|
41
|
+
```text
|
|
42
|
+
Handle the issue below as a plan. Read `.bkit/workflows.md` § Per-Phase Workflows and `.bkit/prompts.md` as inspiration only — keep the steps that fit, skip the rest. Dispatch each kept subagent step to its `bkit-*` subagent on the model `.bkit/prompts.md` § Models pins for it; NEVER do subagent work inline. No subagent tool → run its prompt file in-session. Follow `.bkit/lite.md` § Contract.
|
|
43
|
+
|
|
44
|
+
[INSERT ISSUE ID / INSTRUCTIONS]
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
### build:lite
|
|
48
|
+
|
|
49
|
+
```text
|
|
50
|
+
Handle the issue below as a build. Read `.bkit/workflows.md` § Per-Phase Workflows and `.bkit/prompts.md` as inspiration only — keep the steps that fit, skip the rest. Dispatch each kept subagent step to its `bkit-*` subagent on the model `.bkit/prompts.md` § Models pins for it; NEVER do subagent work inline. No subagent tool → run its prompt file in-session. Follow `.bkit/lite.md` § Contract.
|
|
51
|
+
|
|
52
|
+
[INSERT ISSUE ID / INSTRUCTIONS]
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
### debug:lite
|
|
56
|
+
|
|
57
|
+
```text
|
|
58
|
+
Handle the issue below as a debug. Read `.bkit/workflows.md` § Per-Phase Workflows and `.bkit/prompts.md` as inspiration only — keep the steps that fit, skip the rest. Dispatch each kept subagent step to its `bkit-*` subagent on the model `.bkit/prompts.md` § Models pins for it; NEVER do subagent work inline. No subagent tool → run its prompt file in-session. Follow `.bkit/lite.md` § Contract.
|
|
59
|
+
|
|
60
|
+
[INSERT ISSUE ID / INSTRUCTIONS]
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
### ship:lite
|
|
64
|
+
|
|
65
|
+
```text
|
|
66
|
+
Handle the issue below as a ship. Read `.bkit/workflows.md` § Per-Phase Workflows and `.bkit/prompts.md` as inspiration only — keep the steps that fit, skip the rest. Dispatch each kept subagent step to its `bkit-*` subagent on the model `.bkit/prompts.md` § Models pins for it; NEVER do subagent work inline. No subagent tool → run its prompt file in-session. Follow `.bkit/lite.md` § Contract.
|
|
67
|
+
|
|
68
|
+
[INSERT ISSUE ID / INSTRUCTIONS]
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
<!-- bkit:end -->
|
|
72
|
+
|
|
73
|
+
## Project Lite Workflows
|
|
@@ -0,0 +1,346 @@
|
|
|
1
|
+
# bkit — Pipeline Reference
|
|
2
|
+
|
|
3
|
+
{{BKIT_MANAGED_MARKER}}
|
|
4
|
+
|
|
5
|
+
> [!CAUTION]
|
|
6
|
+
> **Purpose:** Human-facing reference. Five-phase pipeline + every subagent (phases in execution order, then audit and utilities) + every audit template. Evaluation, onboarding — not agent workflow doc-matrix. bkit vs other frameworks and vs _Agentic Design Patterns_: `.bkit/comparison.md`.
|
|
7
|
+
>
|
|
8
|
+
> **Rules:**
|
|
9
|
+
>
|
|
10
|
+
> - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
|
|
11
|
+
> - Describe current state / rules, not reasons / history; state what to do, not why.
|
|
12
|
+
> - Keep prose factual; house / write-good linters apply to `*.md`; no hype adjectives.
|
|
13
|
+
> - Headings linked from outside carry a fixed `<a id>` above them; keep the id when rewording the heading.
|
|
14
|
+
> - No model, effort or tier per subagent: those live in `.bkit/prompts.md` § Models only.
|
|
15
|
+
> - Pipeline or subagents change → update to match `.bkit/core/workflows/*` and `.bkit/core/.bkit/prompts.md`.
|
|
16
|
+
> - Audit templates added, removed or renamed → update § Audits to match `.bkit/core/docs/templates/bkit-audit-*.md`.
|
|
17
|
+
|
|
18
|
+
**Contents**
|
|
19
|
+
|
|
20
|
+
- [What this is](#what-this-is)
|
|
21
|
+
- [Pipeline map](#pipeline-map) · [CI test scaffold](#ci-scaffold)
|
|
22
|
+
- [Design](#bkit-design) · [Plan](#bkit-plan) · [Build](#bkit-build) · [Debug](#bkit-debug) · [Ship](#bkit-ship)
|
|
23
|
+
- [Audits: every template](#audits) · [Utilities](#utilities)
|
|
24
|
+
|
|
25
|
+
## What this is
|
|
26
|
+
|
|
27
|
+
bkit turns a single coding-agent request into gated, peer-reviewed engineering. Five commands — `/bkit-design` → `/bkit-plan` → `/bkit-build` → `/bkit-debug` → `/bkit-ship` — each fans out to specialised single-purpose subagents (49 in total, phases + audit + utilities). Many run parallel under different _lenses_ (bug review vs security review) → independent review before human sees output. Same pipeline on five hosts: Claude Code, Cursor, Codex, Google Antigravity, opencode.
|
|
28
|
+
|
|
29
|
+
Beside those commands, 35 read-only audit templates live at `docs/templates/bkit-audit-*.md`. `@bkit-audit-generate` runs one and writes `docs/audits/{YYYYMM}/{slug}.md`. `/bkit-plan` takes a design, one or more of those reports, or both.
|
|
30
|
+
|
|
31
|
+
Each phase lists subagents in execution order. "Parallel" = same-time run, merged after; distinct lenses = multi-perspective review. Orchestrator steps (git, worktree, tracker) noted but not listed as subagents. Model and thinking depth per subagent and host: `.bkit/prompts.md` § Models.
|
|
32
|
+
|
|
33
|
+
<a id="pipeline-map"></a>
|
|
34
|
+
|
|
35
|
+
## Pipeline map (key steps only)
|
|
36
|
+
|
|
37
|
+
```
|
|
38
|
+
┌────────────────────── bkit-auto (opt-in cloud router) ─────────────────┐
|
|
39
|
+
│ workflow_run on feat/** → ship (CI green) / debug (CI red) │
|
|
40
|
+
│ workflow_dispatch → ship|debug|plan|build (design: local only) │
|
|
41
|
+
│ Dispatches the matching /bkit-* skill — runs unattended in cloud │
|
|
42
|
+
│ (Claude Code on the web / Cursor cloud agents / opencode). │
|
|
43
|
+
│ Opt-in: `bkit install --auto=claude|cursor|opencode`. See `.bkit/cloud.md`. │
|
|
44
|
+
└────────────────────────────────────────────────────────────────────────┘
|
|
45
|
+
│
|
|
46
|
+
▼
|
|
47
|
+
|
|
48
|
+
/bkit-design ───── output: detailed design ───────────────────────────────────
|
|
49
|
+
1. grill (human interview, one decision frontier per round;
|
|
50
|
+
skipped headless: recommended answers recorded as assumed)
|
|
51
|
+
2. fetch related (semantic tracker search, rank order → related-issues.md)
|
|
52
|
+
3. brainstorm × 3 (parallel, distinct lenses, no sibling reads)
|
|
53
|
+
• pragmatic • optimal-tradeoff • risk / pre-mortem
|
|
54
|
+
4. generate design (synthesise across lenses + related issues)
|
|
55
|
+
5. review × 2 (parallel, cross-tier models)
|
|
56
|
+
• feasibility (web) • operability (failure modes, observability, on-call)
|
|
57
|
+
6. spike (only if review flags load-bearing unknowns:
|
|
58
|
+
throwaway probe code, confined to the run's log folder)
|
|
59
|
+
7. update design (fold reviews + spike back in)
|
|
60
|
+
8. organise (decompose into workstreams + DAG)
|
|
61
|
+
9. summary (tracker-facing)
|
|
62
|
+
|
|
63
|
+
/bkit-plan ───── output: detailed plan ───────────────────────────────────────
|
|
64
|
+
1. generate plan
|
|
65
|
+
2. fetch context (tracker: related issues; ledgers: prior deferrals,
|
|
66
|
+
prior failures, strongest term-overlap first, top 40
|
|
67
|
+
→ feeds all three reviewers below)
|
|
68
|
+
3. review × 3 (parallel, distinct lenses)
|
|
69
|
+
• tightness + design-coverage • dependency-correctness • regression-risk
|
|
70
|
+
4. update plan (merge critiques, max-wins on CRITICAL)
|
|
71
|
+
5. scope-check × 2 (parallel)
|
|
72
|
+
• internal-completeness • scope audit (cross-family)
|
|
73
|
+
6. update plan (merge scope findings)
|
|
74
|
+
7. complexity-check (single vs split)
|
|
75
|
+
8. complexity-split (only if SPLIT)
|
|
76
|
+
9. summary (tracker-facing)
|
|
77
|
+
|
|
78
|
+
/bkit-build ─── output: code, PR to dev, CI takes over ──────────────────────
|
|
79
|
+
1. plan-current (plan still executable against code landed since it was written?)
|
|
80
|
+
2. install-skills
|
|
81
|
+
3. execute build (producer — implement tasks)
|
|
82
|
+
4. verify build (critic — verify each task; tick only on confirmed artifacts)
|
|
83
|
+
↶ producer-critic loop, capped 3 attempts
|
|
84
|
+
5. gaps-remediate (fix verifier gaps, re-verify)
|
|
85
|
+
6. verify build (holistic second pass across whole plan)
|
|
86
|
+
7. challenge × 2 (parallel, distinct lenses, no sibling reads)
|
|
87
|
+
• bug-hunting • security
|
|
88
|
+
8. challenge-reconcile (merge findings, severity + verdict max-wins)
|
|
89
|
+
9. challenge-remediate (classify-gate: architectural → FAIL; else fix + test)
|
|
90
|
+
10. challenge-tests (edge-case tests for changed files)
|
|
91
|
+
11. run tests (local tier: lint + typecheck + unit + slop:delta + bkit check;
|
|
92
|
+
no integration / e2e / @live — those run in CI)
|
|
93
|
+
↳ on test failure → /bkit-debug (debug-failure-diagnose + remediate)
|
|
94
|
+
12. summary (tracker-facing + PR link)
|
|
95
|
+
→ PR opened; CI runs the full multi-tier scaffold (see "CI test scaffold" below)
|
|
96
|
+
|
|
97
|
+
/bkit-debug ─── side-rail, invoked on test/CI failure ────────────────────────
|
|
98
|
+
1. run tests (broader tier than build: lint + typecheck + unit
|
|
99
|
+
+ integration + e2e + optional @live canary —
|
|
100
|
+
reproduces against the deployed boundary)
|
|
101
|
+
2. fetch context (only if tests FAIL; CI: failed jobs/steps + error
|
|
102
|
+
annotations + failed-step logs; e2e test reports; local
|
|
103
|
+
test output; diff vs last-passing CI; runtime logs via
|
|
104
|
+
context-fetch blocks; tracker: related issues by error
|
|
105
|
+
signature → feeds diagnose below)
|
|
106
|
+
[repro] (first run passes — bug not reproduced yet):
|
|
107
|
+
2. fetch context, then reproduce (tests that fail on the reported
|
|
108
|
+
symptoms → back to 1; can't reproduce → summary)
|
|
109
|
+
Normal mode (localisable failure):
|
|
110
|
+
3. diagnose (reads docs/knowledge.jsonl for prior failures;
|
|
111
|
+
Standard → Pivot → Final strategy escalation)
|
|
112
|
+
4. remediate (apply diagnosis fix)
|
|
113
|
+
5. re-run tests
|
|
114
|
+
6. summary
|
|
115
|
+
↳ if diagnose can't localise, or loop exhausts 3 strategies → Soak mode
|
|
116
|
+
Soak mode (non-localisable / runtime-only failure):
|
|
117
|
+
1. soak loop (one accumulating context per iteration:
|
|
118
|
+
instrument OR smallest evidence-backed fix;
|
|
119
|
+
strips all scaffolding before declaring a fix)
|
|
120
|
+
Escape hatch:
|
|
121
|
+
abort-handover (unrecoverable failure → human handover doc + stop)
|
|
122
|
+
|
|
123
|
+
/bkit-ship ─── output: squash-merged PR, hard stop before main ──────────────
|
|
124
|
+
1. conflict-resolve (only if rebase sentinels exist)
|
|
125
|
+
2. deferred-sweep (pre-merge completeness gate; FAIL blocks merge)
|
|
126
|
+
3. run tests (wait for CI on squash-merge SHA; bkit-tests-check
|
|
127
|
+
must be green — every planned tier ran and passed;
|
|
128
|
+
a planned bkit-tests-live-web failure reds it)
|
|
129
|
+
4. merge (orchestrator-only guarded git op)
|
|
130
|
+
↳ on post-merge failure → /bkit-debug (diagnose + remediate)
|
|
131
|
+
5. update-docs / summary (parallel)
|
|
132
|
+
6. prune skills + update local dev + close (orchestrator-only;
|
|
133
|
+
close removes the worktree)
|
|
134
|
+
```
|
|
135
|
+
|
|
136
|
+
<a id="ci-scaffold"></a>
|
|
137
|
+
|
|
138
|
+
## CI test scaffold (runs on every PR + push)
|
|
139
|
+
|
|
140
|
+
The template `bkit-ci.yml` (copied into `.bkit/templates/`, adopted and owned by the consumer) is static: two lanes run in parallel and the `bkit-tests-check` capstone joins them as the single branch-protection check. No planner. The capstone fails unless both lanes concluded `success`, and fails a unit lane that reports zero executed tests.
|
|
141
|
+
|
|
142
|
+
```
|
|
143
|
+
bkit-tests-static (typecheck, lint, format, prose lint, slop, actionlint, bkit check)
|
|
144
|
+
bkit-tests-unit (unit tests; writes the executed-test count)
|
|
145
|
+
│
|
|
146
|
+
▼
|
|
147
|
+
bkit-tests-check (capstone: needs both lanes; sole required check)
|
|
148
|
+
```
|
|
149
|
+
|
|
150
|
+
Add the lanes the repo has (integration, E2E, migration, live) as further `needs:` of the capstone. Full tier rules: `docs/testing.md`.
|
|
151
|
+
|
|
152
|
+
Hard stops after Design, Plan, and Ship (production merge needs explicit human approval). Shared subagents cross-invoked: `bkit-debug-failure-diagnose` / `bkit-debug-failure-remediate` run inside Build and Ship failure paths as well as the Debug phase.
|
|
153
|
+
|
|
154
|
+
With `bkit-auto` enabled, the loop is unattended: Build opens a PR → CI runs → on green `bkit-auto` dispatches `/bkit-ship`, on red it dispatches `/bkit-debug`; debug re-pushes, CI re-runs, auto-routes again — no local session required until a human gate fires.
|
|
155
|
+
|
|
156
|
+
<a id="bkit-design"></a>
|
|
157
|
+
|
|
158
|
+
## Phase 1 — `/bkit-design`
|
|
159
|
+
|
|
160
|
+
Output: reviewed design (`docs/plans/{YYYYMM}/{FID}-design.md`). Hard stop for human approval.
|
|
161
|
+
|
|
162
|
+
<!-- prettier-ignore -->
|
|
163
|
+
| Subagent | Lens / focus | What it does |
|
|
164
|
+
| --- | --- | --- |
|
|
165
|
+
| `bkit-design-brainstorm-ideate-1` | Pragmatic | Independent design exploration. Forbidden from reading siblings (circular-reasoning guard). |
|
|
166
|
+
| `bkit-design-brainstorm-ideate-2` | Optimal-tradeoff | Same task, different lens, on a different model from its siblings. |
|
|
167
|
+
| `bkit-design-brainstorm-ideate-3` | Risk / pre-mortem | Same task, failure-mode lens. |
|
|
168
|
+
| `bkit-design-generate` | Synthesiser | Merges three brainstorms into one design. Merges across lenses rather than collapsing to consensus. |
|
|
169
|
+
| `bkit-design-review-1` | Feasibility (web) | Adversarial review with live web search; checks ecosystem feasibility per capability. |
|
|
170
|
+
| `bkit-design-review-2` | Operability (cross-tier) | Parallel review on a different model from review-1: failure modes, observability, on-call ergonomics. |
|
|
171
|
+
| `bkit-design-spike` | Probe unknowns | Only when a review flags load-bearing unknowns: settles them with throwaway probe code, confined to the run's log folder. |
|
|
172
|
+
| `bkit-design-update` | Apply review | Folds both reviews (and the spike, if run) back into the design. |
|
|
173
|
+
| `bkit-design-organise` | Structure | Cleans and organises the final design doc. |
|
|
174
|
+
| `bkit-design-summary` | Summarise | Writes the tracker-facing summary (capped, scannable). |
|
|
175
|
+
|
|
176
|
+
<a id="bkit-plan"></a>
|
|
177
|
+
|
|
178
|
+
## Phase 2 — `/bkit-plan`
|
|
179
|
+
|
|
180
|
+
Output: executable plan (`{FID}-plan.md`, split into `-plan-N.md` if too large). Consumes design. Hard stop.
|
|
181
|
+
|
|
182
|
+
<!-- prettier-ignore -->
|
|
183
|
+
| Subagent | Lens / focus | What it does |
|
|
184
|
+
| --- | --- | --- |
|
|
185
|
+
| `bkit-plan-generate` | Generate | Turns the design into a tasked plan. |
|
|
186
|
+
| `bkit-plan-review-1` | Tightness + design-coverage | Read-only critique; flags vague or missing `Done when:` as CRITICAL. Parallel. |
|
|
187
|
+
| `bkit-plan-review-2` | Dependency-correctness | Same scope, dependency lens. Depth-sensitive: stays on the top model tier. Parallel. |
|
|
188
|
+
| `bkit-plan-review-3` | Regression-risk | Same scope, regression lens. Parallel. |
|
|
189
|
+
| `bkit-plan-update` | Apply review (merge) | Merges all three critiques, max-wins on CRITICAL findings. |
|
|
190
|
+
| `bkit-plan-scope-check-1` | Internal-completeness | Mechanical scope audit — verifies template structure and criteria slots. Parallel. |
|
|
191
|
+
| `bkit-plan-scope-check-2` | Scope audit (cross-family) | Second scope audit in parallel for independent coverage. |
|
|
192
|
+
| `bkit-plan-update` | Apply scope fixes | Second merge pass folding scope-check findings in. |
|
|
193
|
+
| `bkit-plan-complexity-check` | Single → split classifier | Decides whether the plan is too big for one build and must be split. |
|
|
194
|
+
| `bkit-plan-complexity-split` | Splitter | If SPLIT: divides the plan into sequenced sub-plans. |
|
|
195
|
+
| `bkit-plan-summary` | Summarise | Tracker-facing summary. |
|
|
196
|
+
|
|
197
|
+
<a id="bkit-build"></a>
|
|
198
|
+
|
|
199
|
+
## Phase 3 — `/bkit-build`
|
|
200
|
+
|
|
201
|
+
Output: PR to `dev`. Heaviest phase — most steps verify rather than produce. CI takes over after PR.
|
|
202
|
+
|
|
203
|
+
<!-- prettier-ignore -->
|
|
204
|
+
| Subagent | Lens / focus | What it does |
|
|
205
|
+
| --- | --- | --- |
|
|
206
|
+
| `bkit-build-plan-current` | Plan freshness | Judges whether changes landed since the plan was written leave it executable; findings feed execute. |
|
|
207
|
+
| `bkit-build-install-skills` | Setup | Installs the skills the plan needs for this build. |
|
|
208
|
+
| `bkit-build-plan-execute` | Producer | Implements the plan tasks; iterates edit → lint/typecheck/test → edit. |
|
|
209
|
+
| `bkit-build-plan-verify` | Critic | Verifies each task against the plan; ticks boxes only on confirmed artifacts. Producer-critic loop, capped at 3 attempts. |
|
|
210
|
+
| `bkit-build-plan-gaps-remediate` | Gap-fixer | Fills gaps the verifier found, then re-verifies. |
|
|
211
|
+
| `bkit-build-plan-verify` | Holistic critic | Second, whole-of-plan verification pass across everything built. |
|
|
212
|
+
| `bkit-build-challenge-1` | Bug-hunting | Adversarial review of the full diff. Forbidden from reading its sibling. Parallel. |
|
|
213
|
+
| `bkit-build-challenge-2` | Security | Same diff, security lens. Depth-sensitive: stays on the top model tier. Parallel. |
|
|
214
|
+
| `bkit-build-challenge-reconcile` | Merge findings | Unifies both challenges. `Severity` and verdict max-wins; downgrades need explicit justification. |
|
|
215
|
+
| `bkit-build-challenge-remediate` | Fixer (classify-gate) | Any architectural finding → FAIL (no silent fixes); else applies mechanical fixes and re-runs tests. |
|
|
216
|
+
| `bkit-build-challenge-tests` | Test author | Adds edge-case tests for changed files; runs the test suite. |
|
|
217
|
+
| `bkit-debug-failure-diagnose` | Diagnostician | (If tests fail) diagnoses with Standard / Pivot / Final strategy escalation. Shared with debug. |
|
|
218
|
+
| `bkit-debug-failure-remediate` | Fixer | (If tests fail) applies the diagnosed fix. |
|
|
219
|
+
| `bkit-build-summary` | Summarise | Tracker-facing summary plus PR link. |
|
|
220
|
+
|
|
221
|
+
<a id="bkit-debug"></a>
|
|
222
|
+
|
|
223
|
+
## Phase 4 — `/bkit-debug`
|
|
224
|
+
|
|
225
|
+
Output: remediated commit on feature branch. Two modes — normal (diagnose → remediate localisable failure) and soak (one accumulating-context instrument-or-fix loop for non-localisable / runtime-only failures). Normal escalates to soak when diagnose can't localise, or normal loop exhausts three strategies; observation logging (`[DEBUG-OBSERVE]`) inside soak, stripped before fix ships.
|
|
226
|
+
|
|
227
|
+
**Context fetch.** Per failed attempt, `/bkit-debug` runs each `context-fetch` bash block below `<!-- bkit:end -->` in `.agents/context.md` — failing CI logs, the diff since the last green run, end-to-end reports, runtime errors (Sentry, Vercel, Supabase, Stripe and more) and web search (Tavily) — writing one artifact per context and narrating `CHECKED` / `SELF-SKIPPED` / `NOT CONFIGURED` before fetching. Fail-soft and block-driven: bkit hardcodes no CI host, workflow filename or test framework, and a context with no block is never read as a clean result.
|
|
228
|
+
|
|
229
|
+
**Normal mode**
|
|
230
|
+
|
|
231
|
+
<!-- prettier-ignore -->
|
|
232
|
+
| Subagent | Lens / focus | What it does |
|
|
233
|
+
| --- | --- | --- |
|
|
234
|
+
| `bkit-debug-failure-reproduce` | Reproducer (`[repro]` only) | Nothing fails yet → tests failing on the reported symptoms, never a fix; soak mode → tests repeat the scenario. Not reproduced → tests removed, run ends at Summary; reproduced but the re-run passes with no fix → Summary. |
|
|
235
|
+
| `bkit-debug-failure-diagnose` | Diagnostician | Reproduces and diagnoses. Accumulates per-attempt context; escalates Standard → Pivot → Final. |
|
|
236
|
+
| `bkit-debug-failure-remediate` | Fixer | Applies whatever the strategy-aware diagnosis produced, with a test loop. |
|
|
237
|
+
| `bkit-debug-summary` | Summarise | Tracker-facing summary. |
|
|
238
|
+
|
|
239
|
+
**Soak mode**
|
|
240
|
+
|
|
241
|
+
<!-- prettier-ignore -->
|
|
242
|
+
| Subagent | Lens / focus | What it does |
|
|
243
|
+
| --- | --- | --- |
|
|
244
|
+
| `bkit-debug-failure-soak` | Instrument-or-fix loop | One accumulating context against the failing boundary; each iteration either adds `[DEBUG-OBSERVE]` instrumentation or applies the smallest evidence-backed fix, stripping all scaffolding before declaring a fix. Bounded by `SOAK_ATTEMPT` (reset per soak entry). |
|
|
245
|
+
|
|
246
|
+
**Escape hatch**
|
|
247
|
+
|
|
248
|
+
<!-- prettier-ignore -->
|
|
249
|
+
| Subagent | Lens / focus | What it does |
|
|
250
|
+
| --- | --- | --- |
|
|
251
|
+
| `bkit-debug-abort-handover` | Handover | On unrecoverable failure: writes a human handover doc and stops cleanly. Shared across phases. |
|
|
252
|
+
|
|
253
|
+
<a id="bkit-ship"></a>
|
|
254
|
+
|
|
255
|
+
## Phase 5 — `/bkit-ship`
|
|
256
|
+
|
|
257
|
+
Output: squash-merged PR, updated docs, pruned skills, torn-down worktree. Safety-critical — hard guards on production branch, explicit human approval to touch `main`.
|
|
258
|
+
|
|
259
|
+
<!-- prettier-ignore -->
|
|
260
|
+
| Subagent | Lens / focus | What it does |
|
|
261
|
+
| --- | --- | --- |
|
|
262
|
+
| `bkit-ship-conflict-resolve` | Conflict resolver | Resolves merge conflicts against the integration branch, then runs the tests. |
|
|
263
|
+
| `bkit-ship-deferred-sweep` | Pre-merge completeness gate | Builds the intended-delivery set from plan `Acceptance Scenario` sections + `Done when` lines; FAILs the merge if any unplanned gap (silent `TODO`, skipped test) is found. Declared deferrals resurfaced, never blocking. Gates only what the repo can prove — plan gate checkboxes, `Verification Plan` boxes and `Manual Verification` steps are build-phase process, never gated, and no plan precondition or merge condition blocks however a log or summary restates it. |
|
|
264
|
+
| `bkit-debug-failure-diagnose` | Diagnostician | (If post-merge checks fail) diagnoses the regression. Shared with debug. |
|
|
265
|
+
| `bkit-debug-failure-remediate` | Fixer | (If post-merge checks fail) applies the fix. |
|
|
266
|
+
| `bkit-ship-update-docs` | Docs | Updates knowledge / decisions / completed docs. Parallel with summary. |
|
|
267
|
+
| `bkit-ship-summary` | Summarise | Final tracker-facing summary. Parallel with docs. |
|
|
268
|
+
|
|
269
|
+
Orchestrator-only ship steps: regression guard, merge, skill pruning, update local dev (`bkit branches sync-dev`; never checks out `dev`), close (removes the worktree). Guarded git / tracker ops orchestrator performs directly, not subagents.
|
|
270
|
+
|
|
271
|
+
## Audits
|
|
272
|
+
|
|
273
|
+
No command and no phase label. One subagent, one template per run.
|
|
274
|
+
|
|
275
|
+
<!-- prettier-ignore -->
|
|
276
|
+
| Subagent | Lens / focus | What it does |
|
|
277
|
+
| --- | --- | --- |
|
|
278
|
+
| `bkit-audit-generate` | One template | Runs `docs/templates/bkit-audit-*.md`. Writes `docs/audits/{YYYYMM}/{slug}.md` (`{slug}` = basename without `bkit-audit-`; same slug already in that month → `{slug}-{TIMESTAMP}.md`). Report is the template through `bkit:end`. Refines that template's `Project Instructions` below `bkit:end`. Issue named in the invocation + tracker wired → posts the final summary there as one comment. |
|
|
279
|
+
|
|
280
|
+
`/bkit-plan` reads a design doc, one or more reports, or both. The invocation names which findings are in scope. The rest of each report stays context. With neither, the issue is the plan's source: a well-defined change issue carries its narrative, success criteria, edge cases, tests and tasks into the plan.
|
|
281
|
+
|
|
282
|
+
All 35 templates, by area. Template file = `docs/templates/bkit-audit-{template}.md`.
|
|
283
|
+
|
|
284
|
+
<!-- prettier-ignore -->
|
|
285
|
+
| Area | Audit | Template | What it finds |
|
|
286
|
+
| --- | --- | --- | --- |
|
|
287
|
+
| **Security and privacy** | Security | `security` | Holes in sign-in, permissions, secrets and input checks, plus documented protections that never run. |
|
|
288
|
+
| | Red team | `red-team` | Attacks a test copy of the app, never production, one hostile request at a time. Keeps each request and response, then cleans up. |
|
|
289
|
+
| | Privacy | `privacy` | Where personal data goes and how long it stays, whether deleting an account removes the person, whether the privacy policy matches the code. |
|
|
290
|
+
| **Code quality** | Architecture | `architecture` | Code that breaks the intended layers: server code reaching the client, modules tied together with no visible import. |
|
|
291
|
+
| | Duplication | `duplication` | One behaviour built more than once: copied rules, competing mechanisms, restated types, merges that should not have happened. |
|
|
292
|
+
| | Dead code | `dead-code` | Code, settings, routes, events, tables and assets that look live and never run. |
|
|
293
|
+
| | Slop | `slop` | Every switched-off check: disabled lint rules, casts that hide type errors, skipped tests, config opt-outs. |
|
|
294
|
+
| | Documentation | `documentation` | Docs that disagree with the code, links that land nowhere, facts agents rely on that nobody wrote down. |
|
|
295
|
+
| | Dependencies | `dependencies` | Pending dependency updates merged as one verified batch; security advisories, licences, end-of-life packages, supply-chain settings. |
|
|
296
|
+
| **Tests and CI** | Testing | `testing` | Tests that can't fail, don't run, or skip what the product must and must never do. |
|
|
297
|
+
| | Coverage | `coverage` | How much code the tests reach, against the minimum CI enforces, and the next minimum to set. |
|
|
298
|
+
| | Flaky tests | `flakes` | Tests that pass only on retry or fail on one platform, and the change that makes each one reliable. |
|
|
299
|
+
| | Gates | `gates` | Problems audits keep finding by hand that an automatic check could block, and the order to add those checks. |
|
|
300
|
+
| | Annotations | `annotations` | Warnings buried in green CI runs: silent failures, deprecations with a deadline, ignored lint warnings. |
|
|
301
|
+
| | CI performance | `ci-performance` | The lane that makes CI slow or expensive, and what each change would save. |
|
|
302
|
+
| **Running in production** | Reliability | `reliability` | What breaks when a service is slow, down or answers twice: missing timeouts, unsafe retries, races, failures no alert reports. |
|
|
303
|
+
| | Database | `database` | Who can read and write what, migrations, data integrity, capacity, and whether a restore works. |
|
|
304
|
+
| | Logs | `logs` | Error-tracker issues and logs sorted into real bugs, noise at the wrong level, and failures that never got reported. |
|
|
305
|
+
| | App performance | `app-performance` | Web, phone and server speed, measured against published targets and your own budgets. |
|
|
306
|
+
| | Config | `config` | Settings outside the code that disagree across environments, dashboards, repo and docs; anything with an expiry date. |
|
|
307
|
+
| | Cost | `cost` | Vendor plans that don't fit your usage, what drives each bill, whether a spike shows up before the invoice. |
|
|
308
|
+
| **Users and reach** | Accessibility | `accessibility` | What automated accessibility checks miss against WCAG 2.2 AA, plus the manual checks nothing automates. |
|
|
309
|
+
| | Usability | `usability` | Screens that don't match their design or the other platforms, and main flows a person can't finish. |
|
|
310
|
+
| | Analytics | `analytics` | Product events that don't fire, differ between web and phone, fire before consent, or carry personal data. |
|
|
311
|
+
| | AI search & SEO | `aio-seo` | Whether search engines and AI answer engines can find, read and describe your public pages. |
|
|
312
|
+
| | App Store | `app-store` | What keeps an iOS or Android app listed: deadlines, privacy declarations, permissions, signing, review readiness, crashes, ratings. |
|
|
313
|
+
| **AI features** | LLM | `llm` | What each AI model call can make happen, and what stops it when the input is hostile: prompts, tool limits, output checks, evals. |
|
|
314
|
+
| | Models | `models` | Whether each AI call uses the best current model for the job, whether models and fallbacks still exist, whether one list holds them all. |
|
|
315
|
+
| | Prompts | `prompts` | Product prompts that are unclear, badly structured, or off the model maker's current guide. |
|
|
316
|
+
| **Project upkeep** | Issues | `issues` | Size and priority for every open issue, by rules a later run applies the same way; board, parent, milestone and blocking links. |
|
|
317
|
+
| | Deferrals | `deferrals` | Postponed work sorted into done, replaced, tracked, parked, or in scope and never finished. |
|
|
318
|
+
| | Failures | `failures` | Known bugs sorted into still reachable, already fixed, misdescribed, unconfirmed, or a repeat of an earlier one. |
|
|
319
|
+
| | Repo | `repo` | Leftovers and layout: stale worktrees, branches and stashes, ignored files, files in the wrong place. |
|
|
320
|
+
| | Agents | `agents` | Each AI tool's setup: which instructions load, permissions, hooks, tool servers, model choices, untrusted input each agent reads. |
|
|
321
|
+
| | Adoption | `adoption` | Whether every file bkit installed is used and used correctly: install current, docs filled in, audits run on schedule, each template adopted or declined with a reason. |
|
|
322
|
+
|
|
323
|
+
Agent-facing scope per template: `.bkit/prompts.md` § Audit (Ad-hoc).
|
|
324
|
+
|
|
325
|
+
<a id="utilities"></a>
|
|
326
|
+
|
|
327
|
+
## Utilities
|
|
328
|
+
|
|
329
|
+
No command and no phase label. Run on demand, one subagent per run.
|
|
330
|
+
|
|
331
|
+
<!-- prettier-ignore -->
|
|
332
|
+
| Subagent | Lens / focus | What it does |
|
|
333
|
+
| --- | --- | --- |
|
|
334
|
+
| `bkit-utility-update-roadmap` | Roadmap | Ranks the next items to work on from the board, the ledgers and due audits. Rewrites only the `roadmap-analysis` block. |
|
|
335
|
+
| `bkit-utility-update-documentation` | Docs drift | Syncs every doc listed in `.agents/docs.md` with the current system — drift cleanup across several plans. |
|
|
336
|
+
| `bkit-utility-update-decisions` | Decisions ledger | Checks each active `docs/decisions.jsonl` entry against the docs and the code; appends a corrected or superseded row where it no longer holds. |
|
|
337
|
+
| `bkit-utility-update-knowledge` | Gotchas ledger | Same over `docs/knowledge.jsonl`. Never retracts an entry about upstream behaviour for lack of local evidence. |
|
|
338
|
+
| `bkit-utility-update-deferrals` | Deferrals ledger | Closes `docs/deferrals.jsonl` entries the code already resolves, with evidence. An entry an open tracker issue covers is marked triaged, not closed. |
|
|
339
|
+
| `bkit-utility-update-failures` | Failures ledger | Same over `docs/failures.jsonl`, judged on whether the bug still reproduces from the code. A flaky entry closes only on a landed determinism fix. |
|
|
340
|
+
| `bkit-utility-compress-markdown` | Compressor | Rewrites one markdown file in fewer tokens without changing its meaning. Overwrites the file. |
|
|
341
|
+
|
|
342
|
+
Agent-facing scope per utility: `.bkit/prompts.md` § Utility (Ad-hoc).
|
|
343
|
+
|
|
344
|
+
---
|
|
345
|
+
|
|
346
|
+
Sources: bkit workflow and prompt definitions (`.bkit/core/workflows/*`, `.bkit/core/.bkit/prompts.md`).
|