@cbartens/bkit 5.5.1 → 6.0.0
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 +30 -20
- package/.bkit/core/.agents/docs.md +1 -0
- package/.bkit/core/.agents/rules.md +35 -26
- package/.bkit/core/.bkit/README.md +29 -19
- package/.bkit/core/.bkit/authoring.md +117 -0
- package/.bkit/core/.bkit/cloud.md +11 -11
- package/.bkit/core/.bkit/comparison.md +5 -5
- package/.bkit/core/.bkit/install.md +19 -18
- package/.bkit/core/.bkit/jsonl.md +202 -122
- package/.bkit/core/.bkit/lite.md +1 -1
- package/.bkit/core/.bkit/pipeline.md +49 -52
- package/.bkit/core/.bkit/prompts.md +91 -167
- package/.bkit/core/.bkit/providers.md +29 -32
- package/.bkit/core/.bkit/templates.md +12 -11
- package/.bkit/core/.bkit/trackers.md +51 -28
- package/.bkit/core/.bkit/workflows.md +394 -355
- package/.bkit/core/AGENTS.md +16 -22
- package/.bkit/core/docs/templates/bkit-audit-accessibility.md +14 -38
- package/.bkit/core/docs/templates/bkit-audit-adoption.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-agents.md +19 -43
- package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-analytics.md +14 -38
- package/.bkit/core/docs/templates/bkit-audit-annotations.md +11 -35
- package/.bkit/core/docs/templates/bkit-audit-app-performance.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-app-store.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-architecture.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-config.md +18 -42
- package/.bkit/core/docs/templates/bkit-audit-cost.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-coverage.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-database.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-dead-code.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-deferrals.md +15 -38
- package/.bkit/core/docs/templates/bkit-audit-dependencies.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-documentation.md +11 -35
- package/.bkit/core/docs/templates/bkit-audit-duplication.md +18 -42
- package/.bkit/core/docs/templates/bkit-audit-failures.md +13 -37
- package/.bkit/core/docs/templates/bkit-audit-flakes.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-gates.md +14 -38
- package/.bkit/core/docs/templates/bkit-audit-issues.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-llm.md +16 -40
- package/.bkit/core/docs/templates/bkit-audit-logs.md +14 -38
- package/.bkit/core/docs/templates/bkit-audit-models.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-privacy.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-prompts.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-red-team.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-reliability.md +15 -39
- package/.bkit/core/docs/templates/bkit-audit-repo.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-security.md +13 -37
- package/.bkit/core/docs/templates/bkit-audit-slop.md +14 -38
- package/.bkit/core/docs/templates/bkit-audit-testing.md +12 -36
- package/.bkit/core/docs/templates/bkit-audit-usability.md +16 -40
- package/.bkit/core/docs/templates/bkit-plan.md +97 -226
- package/.bkit/core/engine/checks/after/ci-yml.ts +39 -29
- package/.bkit/core/engine/checks/after/github.ts +95 -17
- package/.bkit/core/engine/checks/after/index.ts +10 -7
- package/.bkit/core/engine/checks/after/suppression.ts +8 -5
- package/.bkit/core/engine/checks/after/tools.ts +46 -91
- package/.bkit/core/engine/checks/before/env.ts +2 -2
- package/.bkit/core/engine/checks/before/files.ts +5 -4
- package/.bkit/core/engine/checks/before/index.ts +18 -1
- package/.bkit/core/engine/checks/before/repo.ts +168 -2
- package/.bkit/core/engine/checks/tips/catalogue.ts +16 -5
- package/.bkit/core/engine/checks/tips/detect.ts +34 -0
- package/.bkit/core/engine/checks/tips/index.ts +6 -6
- package/.bkit/core/engine/cli.ts +20 -53
- package/.bkit/core/engine/commands/analysis.ts +171 -140
- package/.bkit/core/engine/commands/ci/ci.ts +6 -6
- package/.bkit/core/engine/commands/comply.ts +77 -103
- package/.bkit/core/engine/commands/install/doctor.ts +2 -2
- package/.bkit/core/engine/commands/install/install.ts +57 -18
- package/.bkit/core/engine/commands/install/uninstall.ts +65 -28
- package/.bkit/core/engine/commands/land.ts +18 -12
- package/.bkit/core/engine/commands/lib.ts +79 -17
- package/.bkit/core/engine/commands/registry.ts +4 -0
- package/.bkit/core/engine/commands/setup/setup.ts +7 -7
- package/.bkit/core/engine/commands/stats.ts +204 -0
- package/.bkit/core/engine/commands/tips.ts +10 -5
- package/.bkit/core/engine/commands/workflow/branches.ts +741 -62
- package/.bkit/core/engine/commands/workflow/challenge.ts +673 -0
- package/.bkit/core/engine/commands/workflow/context.ts +853 -29
- package/.bkit/core/engine/commands/workflow/counters.ts +267 -84
- package/.bkit/core/engine/commands/workflow/decisions.ts +541 -0
- package/.bkit/core/engine/commands/workflow/disk.ts +2 -2
- package/.bkit/core/engine/commands/workflow/fids.ts +793 -33
- package/.bkit/core/engine/commands/workflow/issues.ts +407 -64
- package/.bkit/core/engine/commands/workflow/ledgers.ts +884 -27
- package/.bkit/core/engine/commands/workflow/locks.ts +26 -2
- package/.bkit/core/engine/commands/workflow/plan-blocks.ts +582 -0
- package/.bkit/core/engine/commands/workflow/plan-versions.ts +21 -0
- package/.bkit/core/engine/commands/workflow/prs.ts +166 -30
- package/.bkit/core/engine/commands/workflow/repo.ts +58 -8
- package/.bkit/core/engine/commands/workflow/roadmap.ts +16 -7
- package/.bkit/core/engine/commands/workflow/run-facts.ts +501 -0
- package/.bkit/core/engine/commands/workflow/runs.ts +179 -49
- package/.bkit/core/engine/commands/workflow/runtime.ts +22 -1
- package/.bkit/core/engine/commands/workflow/status.ts +142 -29
- package/.bkit/core/engine/commands/workflow/step-table.ts +339 -0
- package/.bkit/core/engine/commands/workflow/steps.ts +213 -88
- package/.bkit/core/engine/commands/workflow/summary.ts +398 -0
- package/.bkit/core/engine/commands/workflow/tests.ts +1013 -148
- package/.bkit/core/engine/commands/workflow/tracker.ts +1195 -0
- package/.bkit/core/engine/commands/workflow/workflows.ts +984 -207
- package/.bkit/core/engine/commands/workflow/workstreams.ts +11 -5
- package/.bkit/core/engine/commands/workflow/worktrees.ts +185 -8
- package/.bkit/core/engine/install/manifest.ts +11 -9
- package/.bkit/core/engine/install/modules/cloud.ts +21 -13
- package/.bkit/core/engine/install/modules/core.ts +250 -3
- package/.bkit/core/engine/install/modules/opencode.ts +2 -2
- package/.bkit/core/engine/install/version-file.ts +6 -2
- package/.bkit/core/engine/ledgers/migrate.ts +92 -0
- package/.bkit/core/engine/ledgers/status.ts +92 -15
- package/.bkit/core/engine/ledgers/telemetry.ts +1261 -254
- package/.bkit/core/engine/render/hosts.ts +4 -0
- package/.bkit/core/engine/render/models.ts +12 -0
- package/.bkit/core/engine/shared/branches.ts +4 -1
- package/.bkit/core/engine/shared/egress.ts +7 -0
- package/.bkit/core/engine/shared/json.ts +25 -7
- package/.bkit/core/engine/shared/settings.ts +157 -20
- package/.bkit/core/engine/shared/text.ts +361 -0
- package/.bkit/core/engine/tools/grammar-density.ts +215 -0
- package/.bkit/core/engine/tools/instructions-sources.ts +834 -0
- package/.bkit/core/engine/tools/instructions.ts +1751 -0
- package/.bkit/core/hooks/gateguard-engine.js +24 -23
- package/.bkit/core/hooks/guardrails-shell.js +2 -3
- package/.bkit/core/hooks/guardrails-tiers.js +7 -1
- package/.bkit/core/hooks/readguard-engine.js +2 -2
- package/.bkit/core/prompts/bkit-audit-generate.md +62 -25
- package/.bkit/core/prompts/bkit-build-challenge-1.md +40 -17
- package/.bkit/core/prompts/bkit-build-challenge-2.md +44 -17
- package/.bkit/core/prompts/bkit-build-install-skills.md +26 -13
- package/.bkit/core/prompts/bkit-build-plan-convert.md +74 -0
- package/.bkit/core/prompts/bkit-build-plan-current.md +26 -13
- package/.bkit/core/prompts/bkit-build-plan-execute.md +74 -26
- package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +64 -23
- package/.bkit/core/prompts/bkit-build-plan-verify.md +57 -33
- package/.bkit/core/prompts/bkit-debug-abort-handover.md +29 -15
- package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +34 -14
- package/.bkit/core/prompts/bkit-debug-failure-remediate.md +34 -17
- package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +26 -13
- package/.bkit/core/prompts/bkit-debug-failure-soak.md +31 -16
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +21 -11
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +20 -11
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +20 -11
- package/.bkit/core/prompts/bkit-design-generate.md +32 -14
- package/.bkit/core/prompts/bkit-design-organise.md +25 -12
- package/.bkit/core/prompts/bkit-design-review-1.md +31 -15
- package/.bkit/core/prompts/bkit-design-review-2.md +28 -13
- package/.bkit/core/prompts/bkit-design-spike.md +30 -13
- package/.bkit/core/prompts/bkit-design-update.md +33 -19
- package/.bkit/core/prompts/bkit-plan-generate.md +72 -18
- package/.bkit/core/prompts/bkit-plan-review-1.md +50 -27
- package/.bkit/core/prompts/bkit-plan-review-2.md +59 -28
- package/.bkit/core/prompts/bkit-plan-scope-check.md +109 -0
- package/.bkit/core/prompts/bkit-plan-update.md +61 -24
- package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +27 -15
- package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +31 -16
- package/.bkit/core/prompts/bkit-ship-update-docs.md +29 -14
- package/.bkit/core/prompts/bkit-utility-compress-markdown.md +24 -14
- package/.bkit/core/prompts/bkit-utility-update-decisions.md +32 -14
- package/.bkit/core/prompts/bkit-utility-update-deferrals.md +29 -14
- package/.bkit/core/prompts/bkit-utility-update-documentation.md +27 -12
- package/.bkit/core/prompts/bkit-utility-update-failures.md +31 -14
- package/.bkit/core/prompts/bkit-utility-update-knowledge.md +33 -14
- package/.bkit/core/prompts/bkit-utility-update-roadmap.md +38 -17
- package/.bkit/core/prompts/bkit-utility-update-tracker.md +41 -18
- package/.bkit/core/workflows/bkit-auto.md +54 -46
- package/.bkit/core/workflows/bkit-build.md +577 -458
- package/.bkit/core/workflows/bkit-debug.md +348 -333
- package/.bkit/core/workflows/bkit-design.md +201 -237
- package/.bkit/core/workflows/bkit-plan.md +210 -321
- package/.bkit/core/workflows/bkit-ship.md +328 -278
- package/.bkit/shared/.bkit/.env.example +2 -2
- package/.bkit/shared/.claude/settings.json +11 -0
- package/.bkit/shared/.cursor/mcp.json +1 -1
- package/.bkit/shared/.cursor/rules/bkit-rules.mdc +1 -1
- package/.bkit/shared/.gitattributes +1 -1
- package/.bkit/shared/.mcp.json +1 -1
- package/.bkit/shared/.opencode/opencode.json +11 -0
- package/.bkit/shared/CLAUDE.md +2 -2
- package/.bkit/shared/GEMINI.md +2 -2
- package/.bkit/shared/docs/architecture.md +1 -1
- package/.bkit/shared/docs/data-schema.md +1 -1
- package/.bkit/shared/docs/deployments.md +11 -11
- package/.bkit/shared/docs/design.md +1 -1
- package/.bkit/shared/docs/noise.md +1 -1
- package/.bkit/shared/docs/observability.md +2 -2
- package/.bkit/shared/docs/security.md +1 -1
- package/.bkit/shared/docs/setup.md +1 -1
- package/.bkit/shared/docs/technology.md +1 -1
- package/.bkit/shared/docs/testing.md +16 -7
- package/.bkit/templates/.claude/hooks/bkit-cloud-bootstrap.sh +1 -1
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +26 -5
- package/.bkit/templates/.github/workflows/bkit-ci.yml +1 -1
- package/.bkit/templates/.github/workflows/bkit-cloud.yml +21 -19
- package/.bkit/templates/.husky/pre-push +4 -4
- package/.bkit/templates/.prettierignore +7 -0
- package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +1 -1
- package/CHANGELOG.md +112 -0
- package/README.md +50 -35
- package/dist/checks/after/ci-yml.js +39 -28
- package/dist/checks/after/github.js +91 -17
- package/dist/checks/after/index.js +11 -8
- package/dist/checks/after/suppression.js +8 -5
- package/dist/checks/after/tools.js +39 -82
- package/dist/checks/before/env.js +2 -2
- package/dist/checks/before/files.js +5 -3
- package/dist/checks/before/index.js +15 -2
- package/dist/checks/before/repo.js +163 -2
- package/dist/checks/tips/catalogue.js +14 -5
- package/dist/checks/tips/detect.js +32 -0
- package/dist/checks/tips/index.js +4 -4
- package/dist/cli.js +19 -47
- package/dist/commands/analysis.js +109 -100
- package/dist/commands/ci/ci.js +6 -6
- package/dist/commands/comply.js +54 -91
- package/dist/commands/install/doctor.js +2 -2
- package/dist/commands/install/install.js +50 -19
- package/dist/commands/install/uninstall.js +59 -28
- package/dist/commands/land.js +16 -12
- package/dist/commands/lib.js +51 -16
- package/dist/commands/registry.js +4 -0
- package/dist/commands/setup/setup.js +7 -7
- package/dist/commands/stats.js +136 -0
- package/dist/commands/tips.js +7 -3
- package/dist/commands/workflow/branches.js +656 -56
- package/dist/commands/workflow/challenge.js +556 -0
- package/dist/commands/workflow/context.js +709 -30
- package/dist/commands/workflow/counters.js +208 -75
- package/dist/commands/workflow/decisions.js +441 -0
- package/dist/commands/workflow/disk.js +2 -2
- package/dist/commands/workflow/fids.js +689 -33
- package/dist/commands/workflow/issues.js +343 -59
- package/dist/commands/workflow/ledgers.js +762 -27
- package/dist/commands/workflow/locks.js +24 -2
- package/dist/commands/workflow/plan-blocks.js +437 -0
- package/dist/commands/workflow/plan-versions.js +22 -0
- package/dist/commands/workflow/prs.js +142 -32
- package/dist/commands/workflow/repo.js +52 -8
- package/dist/commands/workflow/roadmap.js +9 -7
- package/dist/commands/workflow/run-facts.js +426 -0
- package/dist/commands/workflow/runs.js +144 -43
- package/dist/commands/workflow/runtime.js +12 -1
- package/dist/commands/workflow/status.js +130 -29
- package/dist/commands/workflow/step-table.js +276 -0
- package/dist/commands/workflow/steps.js +171 -80
- package/dist/commands/workflow/summary.js +275 -0
- package/dist/commands/workflow/tests.js +834 -136
- package/dist/commands/workflow/tracker.js +983 -0
- package/dist/commands/workflow/workflows.js +834 -195
- package/dist/commands/workflow/workstreams.js +11 -5
- package/dist/commands/workflow/worktrees.js +147 -9
- package/dist/install/manifest.js +11 -9
- package/dist/install/modules/cloud.js +22 -13
- package/dist/install/modules/core.js +247 -3
- package/dist/install/modules/opencode.js +2 -2
- package/dist/install/version-file.js +6 -2
- package/dist/ledgers/migrate.js +81 -0
- package/dist/ledgers/status.js +61 -8
- package/dist/ledgers/telemetry.js +905 -124
- package/dist/render/hosts.js +4 -0
- package/dist/render/models.js +12 -0
- package/dist/shared/branches.js +3 -1
- package/dist/shared/egress.js +7 -0
- package/dist/shared/json.js +20 -7
- package/dist/shared/settings.js +125 -17
- package/dist/shared/text.js +333 -0
- package/dist/tools/grammar-density.js +183 -0
- package/dist/tools/instructions-sources.js +721 -0
- package/dist/tools/instructions.js +1579 -0
- package/package.json +113 -24
- package/.bkit/core/engine/commands/harvest.ts +0 -459
- package/.bkit/core/engine/tools/wording.ts +0 -748
- package/.bkit/core/prompts/bkit-build-challenge-reconcile.md +0 -69
- package/.bkit/core/prompts/bkit-build-challenge-remediate.md +0 -71
- package/.bkit/core/prompts/bkit-build-challenge-tests.md +0 -74
- package/.bkit/core/prompts/bkit-build-summary.md +0 -94
- package/.bkit/core/prompts/bkit-debug-summary.md +0 -96
- package/.bkit/core/prompts/bkit-design-summary.md +0 -107
- package/.bkit/core/prompts/bkit-plan-complexity-check.md +0 -67
- package/.bkit/core/prompts/bkit-plan-complexity-split.md +0 -88
- package/.bkit/core/prompts/bkit-plan-review-3.md +0 -93
- package/.bkit/core/prompts/bkit-plan-scope-check-1.md +0 -85
- package/.bkit/core/prompts/bkit-plan-scope-check-2.md +0 -85
- package/.bkit/core/prompts/bkit-plan-summary.md +0 -107
- package/.bkit/core/prompts/bkit-ship-summary.md +0 -78
- package/dist/commands/harvest.js +0 -353
- package/dist/tools/wording.js +0 -680
|
@@ -11,14 +11,6 @@
|
|
|
11
11
|
>
|
|
12
12
|
> **Rules:**
|
|
13
13
|
>
|
|
14
|
-
> - Read-only audit; never edit code, config, or data.
|
|
15
|
-
> - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
|
|
16
|
-
> - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
|
|
17
|
-
> - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
|
|
18
|
-
> - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
|
|
19
|
-
> - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
|
|
20
|
-
> - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
|
|
21
|
-
> - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
|
|
22
14
|
> - NEVER submit a build, change a listing, accept an agreement, submit a declaration, or create, rotate, or download a credential.
|
|
23
15
|
> - never copy certificate, key, token, or password material into the report; expiry, holder, and recovery path only.
|
|
24
16
|
> - Every store, deadline, and credential claim names the platform and the account it was read from.
|
|
@@ -33,7 +25,7 @@ Stores change rules on their own schedule. New target API, higher upload SDK, pr
|
|
|
33
25
|
|
|
34
26
|
**Cadence:** monthly. Extra pass after yearly conference that sets upload minimums (e.g. Apple's June developer conference) and after yearly target-API announcement (e.g. Google Play).
|
|
35
27
|
|
|
36
|
-
**Anchor Standards:**
|
|
28
|
+
**Anchor Standards:**
|
|
37
29
|
|
|
38
30
|
- Apple App Review Guidelines. Record last-updated date.
|
|
39
31
|
- Apple upcoming requirements and Apple developer news. Record newest item read.
|
|
@@ -76,22 +68,14 @@ Stores change rules on their own schedule. New target API, higher upload SDK, pr
|
|
|
76
68
|
|
|
77
69
|
### Pre-Flight / Dependencies
|
|
78
70
|
|
|
79
|
-
**Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
|
|
80
|
-
|
|
81
|
-
**Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
|
|
82
|
-
|
|
83
71
|
#### Core
|
|
84
72
|
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
- [ ] **Permissions:** Before Step 1 — one cheap read-only call per tool this run uses (every item below, every rule under `Project Instructions` `Permissions`), e.g. `gh run list --limit 1`, one MCP read, one anchor-standard fetch. Blocked / denied (here or in any step) → record call verbatim and narrow allow rule clearing it (e.g. `Bash(gh run list *)`) in `Not Checked`, `Process Improvements`, and `Project Instructions` `Permissions`; run every step the remaining tools allow; work needing blocked call → `Not Checked`. never stop the run for a blocked call; never retry or reword a blocked call to get past it.
|
|
88
|
-
- [ ] **Build Config:** Steps 2–6, 10 — app config and build profiles in repo, e.g. `app.json`, `eas.json`, `project.pbxproj`. Fallback: none; missing config = finding.
|
|
73
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
74
|
+
- [ ] **Build Config:** Steps 2-6, 10 — app config and build profiles in repo, e.g. `app.json`, `eas.json`, `project.pbxproj`. Fallback: none; missing config = finding.
|
|
89
75
|
- [ ] **Web:** Step 12 — fetch anchor standards and deadline pages. Fallback: versions and dates recorded as unread.
|
|
90
76
|
|
|
91
77
|
#### Conditional
|
|
92
78
|
|
|
93
|
-
Verify only when applicable.
|
|
94
|
-
|
|
95
79
|
- [ ] **Build Service:** Hosted native builds → Steps 2, 3, 6 — version and build number from service, not local config; last built artifact for native-library alignment, e.g. `eas build:list`, `eas build:view`. Fallback: local config only; remote version = hypothesis.
|
|
96
80
|
- [ ] **Store Consoles:** Store accounts exist → Steps 2, 4, 8, 9, 11 — policy status, app content, agreements, listings, e.g. App Store Connect, Play Console. Fallback: repo only; store state `Not Checked`.
|
|
97
81
|
- [ ] **Credential Metadata:** Signing material exists → Step 6 — expiry and holder from build service or console, never the material, e.g. `eas credentials`. Fallback: `Not Checked`.
|
|
@@ -100,14 +84,12 @@ Verify only when applicable.
|
|
|
100
84
|
|
|
101
85
|
### 🔒 Gate 1: Prerequisites Check
|
|
102
86
|
|
|
103
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
104
|
-
|
|
105
87
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
106
|
-
- [ ] **Gate 1
|
|
88
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
107
89
|
|
|
108
90
|
### Probe Steps
|
|
109
91
|
|
|
110
|
-
- [ ] **Step 1 — Previous Run:**
|
|
92
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
111
93
|
- [ ] **Step 2 — Store State:** Per platform: version · build from build service when config keeps version remotely, not local app config; store state (not submitted, in review, live); readable accounts. Read Android policy-status and app-content pages, iOS agreements page. Unaccepted updated agreement or pending declaration blocks uploads = finding → account holder, with page. **Done when:** `Store State` table per platform: version · build · target SDK · store state · accounts read · nearest deadline (filled in `Deadlines`).
|
|
112
94
|
- [ ] **Step 3 — Deadlines:** Confirm each date on current store page; page wins if it differs. (a) Target API level and date vs app target SDK from last built Android bundle, not config only. (b) Memory page size: date and target API the requirement names (e.g. updates targeting that API cannot ship unless native libraries support 16 KB pages). Check `.so` alignment in last built bundle, not config. Any app shipping native code in scope. (c) Upload minimum SDK and toolchain vs build image. (d) Native framework SDK support window. (e) Store policy announced since previous run. (f) Guideline and policy diff since previous report's date, tested against app, not deadline-only. Due within 90 days = finding. Due within 30 days = at least `HIGH`. Upgrade fix → `bkit-audit-dependencies`. **Done when:** `Deadlines` row per item: requirement · date · app value · verdict.
|
|
113
95
|
- [ ] **Step 4 — Declarations:** Match each declaration to `bkit-audit-privacy`'s inventory and privacy policy. Do not rebuild the inventory. (a) iOS privacy manifest — required-reason APIs for app and every third-party SDK — and store privacy labels. (b) Each SDK on vendor's commonly-used list ships own privacy manifest and signature; tracking-domain list names any tracking domain the app contacts. (c) Android data-safety form. (d) Third-party AI: review guideline requiring disclosure where personal data is shared with third parties, including third-party AI, and explicit permission before sharing (e.g. App Review Guideline 5.1.2(i)). In-app consent screen, stored consent flag gating each call, withdraw path, and privacy label describe same flow. Gap → `bkit-audit-privacy`, and plan item for consent screen. (e) Both stores require account deletion started inside the app, not only on the web. The Android form also requires a working web link, entered on the data-safety form, that names the app or developer and lets someone request deletion without reinstalling. Deleting an account revokes Sign in with Apple tokens through the revoke endpoint, and the server handles the server-to-server notifications for revoked consent and deleted accounts (e.g. Apple technote TN3194), when that provider exists. (f) Advertising-id and tracking answers match what `bkit-audit-analytics` found the app collects. Declaration mismatch = at least `HIGH` → `bkit-audit-privacy`. **Done when:** `Declarations` row per label, manifest entry, and form answer: declared · inventory · verdict.
|
|
@@ -116,20 +98,18 @@ Verify only when applicable.
|
|
|
116
98
|
- [ ] **Step 7 — Links:** Native app with invite/deep links → association files on web domain over HTTPS, no redirect, cover invite/join/email deep-link paths, match shipped apps: iOS team and bundle id; Android SHA-256 fingerprints including store signing key's, not upload key only. Open invite link on device with app and without. Hosting/DNS drift where store build still matches → `bkit-audit-config`. File mismatch vs store build = finding → plan from this report. **Done when:** `Links` row per file and per device case.
|
|
117
99
|
- [ ] **Step 8 — Live:** Not listed → `N/A` in `Live`, never "clean"; skip rest. (a) Crash-free sessions; Android ANR rate — store vitals, Xcode Organizer, error tracker. Compare crash/ANR vs overall and per-device bad-behaviour thresholds, not overall only. Cluster → `bkit-audit-logs`. (b) Android vitals beyond crashes: excessive partial wake locks (core vital; record vitals-page date) and slow cold/warm starts. (c) Xcode Organizer beyond crashes: hang rate, launch time, memory, disk writes, battery, per version. Slow starts, hangs, wake locks, battery → `bkit-audit-app-performance`. (d) Rating and change since previous run; recent review themes. How-app-works themes → `bkit-audit-usability`. (e) Review prompts via store review API only — never incentivised or gated. Replies vs owner response-rate target. (f) Rejections since previous run and reasons. (g) Production: phased release and staged rollout, halt rule tied to crash-free sessions; external test tracks active. (h) Screenshots current, description true, support and privacy URLs work. Out-of-date listing → owner, with screen or text. **Done when:** `Live` holds rates, rating, each verdict, or `N/A`.
|
|
118
100
|
- [ ] **Step 9 — Listing:** Pre-submission → draft listing; live → published. Title, subtitle, keyword field, short/full description: within store field limits, search-oriented words. Localised listings for shipped locales. Screenshot sets per required device size; tablet if supported. Live: conversion funnel (impressions, product-page views, installs) from both stores' acquisition reports, change since previous run. Record listing experiments; propose one quarterly test (screenshots or icon) to owner. **Done when:** `Listing` row per field and locale: within limits · true · verdict.
|
|
119
|
-
- [ ] **Step 10 — Readiness:** (a) Working demo account for reviewers, not seeded owner. (b) Sign in with Apple if any other third-party sign-in on iOS. (c) How digital subscriptions sold in-app. External processor vs in-app purchase limited by store/country rules — owner decision in `docs/decisions.jsonl`; match record to app behaviour. (d) Out-of-app purchase links vs same rules. (e) Subscription disclosures: terms, price, renewal before purchase; manage/cancel path; restore purchases if IAP used. External-processor-only subscriptions → account deletion explains cancellation. (f) App ships over-the-air updates (e.g. Expo Updates, CodePush) → script and assets only — never change primary purpose or skip-review feature. Runtime-version policy prevents incompatible binary landing. Breach → plan from this report. None → `N/A`. (g) Tablet supported → layouts work on tablet for review; else flag false on purpose. (h) Export-compliance flag set so uploads not held. (i) Trader status on both stores — undeclared apps removed from EU storefronts. (j) Current closed-test rule for personal developer account (e.g. account created after 2023-11-13 needs closed test with
|
|
101
|
+
- [ ] **Step 10 — Readiness:** (a) Working demo account for reviewers, not seeded owner. (b) Sign in with Apple if any other third-party sign-in on iOS. (c) How digital subscriptions sold in-app. External processor vs in-app purchase limited by store/country rules — owner decision in `docs/decisions.jsonl`; match record to app behaviour. (d) Out-of-app purchase links vs same rules. (e) Subscription disclosures: terms, price, renewal before purchase; manage/cancel path; restore purchases if IAP used. External-processor-only subscriptions → account deletion explains cancellation. (f) App ships over-the-air updates (e.g. Expo Updates, CodePush) → script and assets only — never change primary purpose or skip-review feature. Runtime-version policy prevents incompatible binary landing. Breach → plan from this report. None → `N/A`. (g) Tablet supported → layouts work on tablet for review; else flag false on purpose. (h) Export-compliance flag set so uploads not held. (i) Trader status on both stores — undeclared apps removed from EU storefronts. (j) Current closed-test rule for personal developer account (e.g. account created after 2023-11-13 needs closed test with >=12 testers opted in 14 consecutive days before production). Identity verification and package-name registration; record store-page date for unregistered package removal (e.g. 2026-09-30). (k) Pre-launch report for latest build: crashes, accessibility, security warnings; failed devices/OS versions. (l) Accessibility nutrition labels: store declaration vs vendor criteria per feature (every common task completable). Voluntary until store requires. Evidence → `bkit-audit-accessibility`. Unused permission, missing deletion path, review-rule gap → plan from this report. **Done when:** `Readiness` row per item: met / finding / not applicable.
|
|
120
102
|
- [ ] **Step 11 — Age:** Both stores' age-rating questionnaires answered; re-answer when features change (messaging, UGC, AI chat, unrestricted web). Record store due date for new questions (e.g. Apple added bands due 2026-01-31 to keep submitting updates); unanswered past date = finding. Age assurance: owner decision in `docs/decisions.jsonl` when product holds children's data. Read both stores' jurisdiction lists (e.g. Texas SB 2420 for new Texas accounts from 2026-06-04 via declared-age-range API, significant-change API, server notification for revoked parental consent; Play age-signals API for eligible accounts). How child is known and consent given → `bkit-audit-privacy`. Target-audience declaration accurate; Play Families applicability recorded. Age-rating or age-assurance gap → owner; child safety → `bkit-audit-privacy`. **Done when:** `Age` row per questionnaire and jurisdiction: answered · matches the app · verdict.
|
|
121
103
|
- [ ] **Step 12 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per App Review Guidelines section and per Play policy area (User Data, Permissions, Families, Data safety, and the rest) → checked (name step) / not applicable (why) / finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
|
|
122
104
|
- [ ] **Step 13 — Anything Else:** (a) All changes since previous report's commit touching native apps and listings (app config, build profiles, native permissions and config plugins, privacy manifest, entitlements, native SDK versions, store listing text, subscription and purchase flows, account deletion, over-the-air channels) → one-line verdict each. (b) Bounded ~30 min pass: senior mobile release manager flags no step asks; read since previous run (incidents, `bkit-audit-logs` reports, new `docs/failures.jsonl` rows, vendor status incidents) — what would no step catch? **Done when:** `Beyond the Steps` holds both passes, or `none`. Class seen on 2 runs → propose step in `Process Improvements`.
|
|
123
105
|
|
|
124
106
|
### 🔒 Gate 2: Probes Check
|
|
125
107
|
|
|
126
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
127
|
-
|
|
128
108
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
129
109
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
130
110
|
- [ ] **Consoles untouched:** no build submitted, no listing or declaration edited, no agreement accepted, no credential created, rotated, or downloaded.
|
|
131
111
|
- [ ] **No secrets:** report contains no certificate, key, token, or password material.
|
|
132
|
-
- [ ] **Gate 2
|
|
112
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
133
113
|
|
|
134
114
|
## Findings
|
|
135
115
|
|
|
@@ -141,7 +121,7 @@ Verify only when applicable.
|
|
|
141
121
|
| `MEDIUM` | Unused permission; association file does not match the store build; over-the-air update can change reviewed behaviour; age questionnaire stale; listing out of date; agreement unaccepted |
|
|
142
122
|
| `LOW` | Listing wording within limits that does not use search words; nutrition-label gap while the labels are still voluntary; no listing experiment proposed |
|
|
143
123
|
|
|
144
|
-
|
|
124
|
+
Within a severity: blocked release and credentials first, then declarations. A deadline within 30 days, a privacy declaration that does not match the app, a credential with no recovery path, and personal data sent to a third-party AI without explicit in-app permission are each at least `HIGH`. `Expected` names where it goes.
|
|
145
125
|
|
|
146
126
|
<!-- prettier-ignore -->
|
|
147
127
|
| Finding | Goes to |
|
|
@@ -248,17 +228,13 @@ PENDING
|
|
|
248
228
|
|
|
249
229
|
### 🔒 Gate 3: Report Check
|
|
250
230
|
|
|
251
|
-
|
|
252
|
-
|
|
253
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
231
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
254
232
|
- [ ] **Summary:** names count per severity, and per platform the store state and nearest deadline.
|
|
255
233
|
- [ ] **Series:** ratings and the listing conversion funnel beside previous report's, or marked baseline / not live.
|
|
256
|
-
- [ ] **Writes:** only this report
|
|
257
|
-
- [ ] **Process Improvements:** `Universal`
|
|
234
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway worktrees / remote targets removed.
|
|
235
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
258
236
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
259
|
-
- [ ] **Gate 3
|
|
260
|
-
|
|
261
|
-
> `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
|
|
237
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
262
238
|
|
|
263
239
|
<!-- bkit:end -->
|
|
264
240
|
|
|
@@ -11,14 +11,6 @@
|
|
|
11
11
|
>
|
|
12
12
|
> **Rules:**
|
|
13
13
|
>
|
|
14
|
-
> - Read-only audit; never edit code, config, or data.
|
|
15
|
-
> - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
|
|
16
|
-
> - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
|
|
17
|
-
> - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
|
|
18
|
-
> - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
|
|
19
|
-
> - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
|
|
20
|
-
> - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
|
|
21
|
-
> - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
|
|
22
14
|
> - A code graph confirms presence; a missing edge proves nothing. Corroborate every load-bearing claim with a language server or text search before it is a finding.
|
|
23
15
|
> - Build the graph locally and code-only; NEVER send the corpus or credentials to a model backend.
|
|
24
16
|
|
|
@@ -32,7 +24,7 @@ File reading cannot answer acyclic package graph, hub modules, or copied types.
|
|
|
32
24
|
|
|
33
25
|
**Cadence:** quarterly. Extra pass when a cycle adds a package, moves a module, or changes path aliases or project references. Production-checklist walk = part of quarterly pass.
|
|
34
26
|
|
|
35
|
-
**Anchor Standards:**
|
|
27
|
+
**Anchor Standards:**
|
|
36
28
|
|
|
37
29
|
- C4 model (System Context, Container, Component).
|
|
38
30
|
- Architecture decision records (e.g. adr.github.io) and architectural fitness functions (e.g. _Building Evolutionary Architectures_).
|
|
@@ -70,45 +62,35 @@ File reading cannot answer acyclic package graph, hub modules, or copied types.
|
|
|
70
62
|
|
|
71
63
|
### Pre-Flight / Dependencies
|
|
72
64
|
|
|
73
|
-
**Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
|
|
74
|
-
|
|
75
|
-
**Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
|
|
76
|
-
|
|
77
65
|
#### Core
|
|
78
66
|
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
- [ ] **
|
|
82
|
-
- [ ] **Code Graph:** Steps 2–4 — local code-only extractor, e.g. graphify via a wrapper that strips API keys. Fallback: dependency linter and text search; graph counts `Not Checked`.
|
|
83
|
-
- [ ] **Dependency Linter:** Steps 5–6 — resolves through the compiler, e.g. dependency-cruiser, import-linter. Fallback: read import statements; say so per claim.
|
|
67
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
68
|
+
- [ ] **Code Graph:** Steps 2-4 — local code-only extractor, e.g. graphify via a wrapper that strips API keys. Fallback: dependency linter and text search; graph counts `Not Checked`.
|
|
69
|
+
- [ ] **Dependency Linter:** Steps 5-6 — resolves through the compiler, e.g. dependency-cruiser, import-linter. Fallback: read import statements; say so per claim.
|
|
84
70
|
- [ ] **Git History:** Steps 1, 9, 13 — change coupling and the diff since the previous report. Fallback: change coupling `Not Checked`.
|
|
85
71
|
- [ ] **Web:** Step 12 — fetch anchor standards. Fallback: versions recorded as unread.
|
|
86
72
|
|
|
87
73
|
#### Conditional
|
|
88
74
|
|
|
89
|
-
Verify only when applicable.
|
|
90
|
-
|
|
91
75
|
- [ ] **Language Server:** Typed language → Steps 7, 11 — references, e.g. Serena, `tsserver`, gopls. Fallback: text search; name it per claim. Repeat any surprising low count.
|
|
92
76
|
- [ ] **Workspace Boundaries:** Monorepo task runner with a boundaries command → Step 5 — e.g. `turbo boundaries`, Nx. Fallback: layer matrix by hand.
|
|
93
77
|
- [ ] **Host Checklists:** Managed host → Step 10 — production checklist, e.g. vendor docs, dashboard. Fallback: docs only; live settings `Not Checked`.
|
|
94
78
|
|
|
95
79
|
### 🔒 Gate 1: Prerequisites Check
|
|
96
80
|
|
|
97
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
98
|
-
|
|
99
81
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
100
|
-
- [ ] **Gate 1
|
|
82
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
101
83
|
|
|
102
84
|
### Probe Steps
|
|
103
85
|
|
|
104
|
-
- [ ] **Step 1 — Previous Run:**
|
|
105
|
-
- [ ] **Step 2 — Graph:** Build locally, code-only, credentials stripped, via project wrapper (never bare extract). Record tool version, `built_at_commit`, node count, edge count, cross-package edge count. Graph commit
|
|
106
|
-
- [ ] **Step 3 — Report:** Read extractor report. Every finding-like section checked against source before it counts. Import cycles: type-only edges erased at compile time
|
|
107
|
-
- [ ] **Step 4 — Structure:** Query built graph, then graph file. Filters first: code only (source extensions; drop manifests and config); tests separated with repo's one test-path rule — do not type a shorter list. Test files cross boundaries; counting them as product hides shape. Views with/without test code can both be correct — record which. Dependency-shaped edges only (import, re-export, dynamic import). Nesting
|
|
86
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
87
|
+
- [ ] **Step 2 — Graph:** Build locally, code-only, credentials stripped, via project wrapper (never bare extract). Record tool version, `built_at_commit`, node count, edge count, cross-package edge count. Graph commit != reviewed `HEAD` → findings invalid; rebuild. Derived output untracked; clean rebuild deletes only that output. After path-alias change → clean rebuild — force flag that does not clear module-resolution cache keeps stale unresolved edges. Syntax-only graph (e.g. tree-sitter) does not consult language server: path aliases and manifest names are separate inputs; losing either drops edges with no error. Keep manifests in corpus so workspace imports resolve → drop manifest-to-manifest edges before matrix. Skip whole-repo render; use package and module rollups. Dated extractor backups (if the tool keeps them) accumulate; clean rebuild clears them. **Done when:** commit, counts, tool list in `Graph`, or absent tool in `Not Checked`.
|
|
88
|
+
- [ ] **Step 3 — Report:** Read extractor report. Every finding-like section checked against source before it counts. Import cycles: type-only edges erased at compile time != runtime cycle — check every edge. Cross-package edges: do not dismiss as impossible once aliases resolve; do dismiss manifest-to-manifest. God nodes: high degree = look, not defect. Community dump with numbered labels and near-zero cohesion → clustering found no structure — skip. **Done when:** each section dispositioned in `Graph`.
|
|
89
|
+
- [ ] **Step 4 — Structure:** Query built graph, then graph file. Filters first: code only (source extensions; drop manifests and config); tests separated with repo's one test-path rule — do not type a shorter list. Test files cross boundaries; counting them as product hides shape. Views with/without test code can both be correct — record which. Dependency-shaped edges only (import, re-export, dynamic import). Nesting != dependency. Name-matching edges (e.g. `indirect_call`) can invent links between unrelated files sharing a function name — exclude. Blast-radius under-reports: missed callers in anonymous callbacks, calls in module-level initialisers. Blast-radius set = starting set, never complete. Checks (each a series): (1) package dependency matrix, code-only, back-edges (library→app, leaf→consumer) — should be DAG; per workspace Ca, Ce, instability I = Ce/(Ca+Ce), abstractness (share of exported types and interfaces); flag package depending on less stable one. (2) File-level cycles (SCC over import edges); component >1 file = candidate → type-only check. (3) Fan-in: files everything imports. (4) Fan-out: most imports — barrels and god modules. (5) Duplicate symbol names: group callables by label across distinct non-test source files; >=3 definitions = prompt. False positives: per-directory handlers, platform splits (e.g. `.native` / `.web`). Signal = type/component duplicated where canonical exists. Same grouping over test code alone. Copies without shared name → text search. Confirmed hits → `bkit-audit-duplication`. **Done when:** matrix, cycles, rankings, duplicates in `Structure`.
|
|
108
90
|
- [ ] **Step 5 — Layers:** Back-edge hunt with no written model lets legal wrong dependency pass. Carry allowed package-layer matrix from previous report. No matrix → draft from recorded architecture decisions, mark proposed. Diff code-only matrix; every disallowed edge = candidate. Encode matrix as forbidden rules for compiler-resolving linter, config under repo-root `tmp/` only, type-only edges excluded; check extractor import cycles. Clean rule = fitness function to propose under `Process Improvements`. Run workspace boundary checker; record version; clean result = candidate for package-DAG gate, not proof. Native/restricted app: every package it imports transitively has no server-only or host-only module (e.g. `fs`, server-only import, service-role client) — forbidden rule so bundle break or client secret caught by structure. Public entry points: every workspace package declares them where the ecosystem supports it (e.g. Node `exports` map, Go `internal/`); deep imports past them = candidates. Name enforcing rule each would need. **Done when:** every disallowed edge in `Layers`, with rule that would forbid it.
|
|
109
91
|
- [ ] **Step 6 — Boundary:** List modules importing privileged data client, service-role secret, or non-public secret; confirm each imports guard that turns client import into build error (e.g. `server-only`), where the stack has one; none → reach check alone, say so. Confirm no client-entry module reaches one transitively — client entry pulls imports into client bundle. Text search → list; linter or blast-radius → reach; `Cross-Check` confirms. **Done when:** every privileged module in `Boundary` with guard, reach, verdict.
|
|
110
92
|
- [ ] **Step 7 — Cross-Check:** Language server answers from disk — no mid-edit staleness; resolves what tree-sitter graph cannot. Graph misses anonymous-callback callers; language server misses what project graph cannot reach. Confirm fan-in and blast-radius with references before write-up. Pace reference queries — back-to-back calls can return partial count indistinguishable from real; repeat surprising low count after pause. Empty = inconclusive. Blind spots neither tool sees: middleware guards, config-referenced files, runtime-registered handlers, mock-factory keys, packages outside language-server project graph. Text search for non-source files, string literals, unknown names. **Done when:** every load-bearing claim in `Cross-Check` names both tools, or the blind spot.
|
|
111
|
-
- [ ] **Step 8 — References:** Pick 2
|
|
93
|
+
- [ ] **Step 8 — References:** Pick 2-3 well-regarded OSS repos on same stack; compare shape: package boundaries, shared code location, config/env split, client code sharing. Record repo name, commit/tag, comparison. Difference = soft signal, not finding alone: report only with problem it would solve here, low-confidence, never rank above graph finding. **Done when:** repos, revisions, comparisons in `References`, or `none`.
|
|
112
94
|
- [ ] **Step 9 — Coupling:** Three couplings carry no import edge. Events/runtime wiring: every event sent vs handler registered, plus schedules, DB triggers, outbound DB HTTP, edge functions, inbound webhooks. Flag producer without consumer, consumer without producer, two packages coupled only via event. Data ownership: table and routine call sites per package and app. Flag table written from >1 module/app; table written via privileged client from >1 place. Change coupling: file pairs in commits since previous report, different packages or clients, co-change in >half commits with no import edge. Confirmed pairs → `bkit-audit-duplication`. **Done when:** events, tables, pairs in `Coupling`.
|
|
113
95
|
- [ ] **Step 10 — Judgment:** Four criteria. Decisions vs code: every architecture-scoped decision still honoured + what enforces it (lint, dependency rule, test). Unenforced decision = finding. Shape with no decision = undocumented architecture. Context/containers: C4 System Context and Container as Mermaid, from previous report corrected. Every external service in code and env schema appears; nothing retired on diagram. Capability register = package-level view only. Quality attributes: pick product-quality characteristics that matter; one scenario each (stimulus, environment, response, response measure); carry forward; judge shape meets each. Production checklists (quarterly): walk host checklists → route each gap to owning audit. **Done when:** decisions, views, scenarios, routed gaps in `Judgment`.
|
|
114
96
|
- [ ] **Step 11 — Verify:** No finding without opening file. Confirm: cycle is runtime not type-only; cross-package edge is real source import not shared manifest name; privileged call site unguarded not middleware-blind; duplicated name is real duplication not platform split/local handler. Cite `file:line`. Destinations (name; do not file): confirmed copies and change-coupled pairs → `bkit-audit-duplication`; reachability or event without producer/consumer → `bkit-audit-dead-code`; server-only from client or secret in native bundle → `bkit-audit-security`; table multi-writer → `bkit-audit-database`; production-checklist gap → owning audit (`bkit-audit-security`, `bkit-audit-app-performance`, `bkit-audit-database`, `bkit-audit-reliability`); else → slug this report names. **Done when:** every surviving candidate has `file:line`, tool, destination.
|
|
@@ -117,13 +99,11 @@ Verify only when applicable.
|
|
|
117
99
|
|
|
118
100
|
### 🔒 Gate 2: Probes Check
|
|
119
101
|
|
|
120
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
121
|
-
|
|
122
102
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
123
103
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
124
104
|
- [ ] **Presence only:** no finding rests on a missing edge alone.
|
|
125
105
|
- [ ] **Graph commit:** graph was built from the reviewed commit, or the mismatch is itself a finding.
|
|
126
|
-
- [ ] **Gate 2
|
|
106
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
127
107
|
|
|
128
108
|
## Findings
|
|
129
109
|
|
|
@@ -135,7 +115,7 @@ Verify only when applicable.
|
|
|
135
115
|
| `MEDIUM` | Architecture decision nothing enforces; confirmed duplicate where a canonical symbol exists; event with no producer or no consumer |
|
|
136
116
|
| `LOW` | Low-confidence shape difference versus a reference repo; diagram drift that changes no boundary |
|
|
137
117
|
|
|
138
|
-
|
|
118
|
+
Within a severity: boundary / secrets first.
|
|
139
119
|
|
|
140
120
|
<!-- prettier-ignore -->
|
|
141
121
|
| ID | Severity | Location | Evidence | Expected |
|
|
@@ -215,17 +195,13 @@ PENDING
|
|
|
215
195
|
|
|
216
196
|
### 🔒 Gate 3: Report Check
|
|
217
197
|
|
|
218
|
-
|
|
219
|
-
|
|
220
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
198
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
221
199
|
- [ ] **Summary:** names count per severity, tools available, and the graph commit.
|
|
222
200
|
- [ ] **Series:** node, edge, and cross-package counts, and the coupling table, beside previous report's numbers, or marked baseline.
|
|
223
|
-
- [ ] **Writes:** only this report
|
|
224
|
-
- [ ] **Process Improvements:** `Universal`
|
|
201
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway worktrees / remote targets removed.
|
|
202
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
225
203
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
226
|
-
- [ ] **Gate 3
|
|
227
|
-
|
|
228
|
-
> `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
|
|
204
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
229
205
|
|
|
230
206
|
<!-- bkit:end -->
|
|
231
207
|
|
|
@@ -11,14 +11,6 @@
|
|
|
11
11
|
>
|
|
12
12
|
> **Rules:**
|
|
13
13
|
>
|
|
14
|
-
> - Read-only audit; never edit code, config, or data.
|
|
15
|
-
> - `Universal Instructions` apply to all projects; `Project Instructions` apply only to this project.
|
|
16
|
-
> - Local audit instructions / overrides → `Project Instructions` below the bkit-managed block; universal instructions stay in-block.
|
|
17
|
-
> - Any tools mentioned in `Universal Instructions` are examples only; swap for actual tools in final output; drop inapplicable.
|
|
18
|
-
> - Use dense token-efficient phrasing; no filler / hedging / restating; tables > prose, bullets > paragraphs.
|
|
19
|
-
> - Read `.agents/docs.md` → load docs for workflow / step / task; skip missing; cite docs inline where required.
|
|
20
|
-
> - Every claim cites this run's evidence (`file:line`, or command / query and its output) and tool behind it; a previous report's figure, list, or status is a lead, not evidence.
|
|
21
|
-
> - Read this document once at session start; do not trust session memory; do not re-read on every loop iteration.
|
|
22
14
|
> - never dispatch, rerun, or cancel a workflow. A runner-class experiment is named, not run.
|
|
23
15
|
> - Billable rates are read this run from the billing pages. never copy a previous report's prices.
|
|
24
16
|
|
|
@@ -28,7 +20,7 @@
|
|
|
28
20
|
|
|
29
21
|
CI time gets re-argued from impressions. Two mistakes recur:
|
|
30
22
|
|
|
31
|
-
- Lane duration alone
|
|
23
|
+
- Lane duration alone != wall-clock savings — only finish time relative to the run shows whether trimming it helps.
|
|
32
24
|
- Cost and latency are different purchases: state which a change buys, every time.
|
|
33
25
|
- Target failure: effort on a lane that does not hold the run open, or a latency change reported as money saved.
|
|
34
26
|
|
|
@@ -36,7 +28,7 @@ CI time gets re-argued from impressions. Two mistakes recur:
|
|
|
36
28
|
|
|
37
29
|
**Cadence:** quarterly; extra pass when workflow topology changes (new lane, runner class, or cache).
|
|
38
30
|
|
|
39
|
-
**Anchor Standards:**
|
|
31
|
+
**Anchor Standards:**
|
|
40
32
|
|
|
41
33
|
- DORA software delivery performance: change lead time, deployment frequency, failed-deployment recovery time, change fail rate, and deployment rework rate.
|
|
42
34
|
- Host CI metrics (e.g. GitHub Actions usage and performance: job run time, queue time, failure rate). Living docs; record the date read.
|
|
@@ -73,23 +65,15 @@ CI time gets re-argued from impressions. Two mistakes recur:
|
|
|
73
65
|
|
|
74
66
|
### Pre-Flight / Dependencies
|
|
75
67
|
|
|
76
|
-
**Checkpoint:** Check off all core items. Check conditional items only when applicable. Each item: available → tool and version; missing → fallback, gap in `Not Checked`, fix in `Process Improvements`. Unnamed gap reads as passed. never abort for a missing capability.
|
|
77
|
-
|
|
78
|
-
**Credentials:** probe direnv before marking a token / env var missing: `direnv exec . sh -c '[ -n "${VAR}" ] && echo set || echo unset'`; `unset` = missing. Run credentialed CLIs as `direnv exec . <cmd>`. No direnv (cloud session) → plain env check. Report names, never values.
|
|
79
|
-
|
|
80
68
|
#### Core
|
|
81
69
|
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
- [ ] **
|
|
85
|
-
- [ ] **CI API:** Steps 2–6, 10–11 — read-only run and job metadata, e.g. `gh run view`, `gh api`. Fallback: workflow files only; timings `Not Checked`.
|
|
86
|
-
- [ ] **Workflow Files:** Steps 3, 7–10 — workflows, task graph, cache config readable. Fallback: none; those steps `Not Checked`.
|
|
70
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
71
|
+
- [ ] **CI API:** Steps 2-6, 10-11 — read-only run and job metadata, e.g. `gh run view`, `gh api`. Fallback: workflow files only; timings `Not Checked`.
|
|
72
|
+
- [ ] **Workflow Files:** Steps 3, 7-10 — workflows, task graph, cache config readable. Fallback: none; those steps `Not Checked`.
|
|
87
73
|
- [ ] **Web:** Step 12 — fetch anchor standards and current runner prices. Fallback: versions and prices unread. never reuse a previous report's prices.
|
|
88
74
|
|
|
89
75
|
#### Conditional
|
|
90
76
|
|
|
91
|
-
Verify only when applicable.
|
|
92
|
-
|
|
93
77
|
- [ ] **Host Metrics:** Host publishes queue time → Step 3 — e.g. Actions performance page. Fallback: queue from timestamps only.
|
|
94
78
|
- [ ] **Cache API:** Cache listing exists → Step 7 — e.g. `gh cache list`. Fallback: log lines only; eviction `Not Checked`.
|
|
95
79
|
- [ ] **Remote Builders:** Job only waits on external builder → Step 6 — builder API or log, e.g. EAS GraphQL. Fallback: wrapper-job duration only; worker time `Not Checked`.
|
|
@@ -97,14 +81,12 @@ Verify only when applicable.
|
|
|
97
81
|
|
|
98
82
|
### 🔒 Gate 1: Prerequisites Check
|
|
99
83
|
|
|
100
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
101
|
-
|
|
102
84
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
103
|
-
- [ ] **Gate 1
|
|
85
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
104
86
|
|
|
105
87
|
### Probe Steps
|
|
106
88
|
|
|
107
|
-
- [ ] **Step 1 — Previous Run:**
|
|
89
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
108
90
|
- [ ] **Step 2 — Reference:** Name reference run ids, event type, date. Push to integration branch vs pull request = different pipelines (some lanes push-only); never compare as one number without saying so. Record green/red per run — red lanes exit early and under-report duration. Runner classes and external queues drift; date matters. **Done when:** `Reference` holds ids, event types, conclusions, date.
|
|
109
91
|
- [ ] **Step 3 — Lanes:** Per job: conclusion, duration, start, column for holds-the-run-open (duration alone is not that column). Add queue time — duration start→completion hides runner wait. Queue = run created → job started; with `needs:` subtract upstream finish for runner wait; keep `needs:` wait for Step 5. Cross-check host average queue per job. e.g. GitHub Actions:
|
|
110
92
|
|
|
@@ -118,26 +100,24 @@ Verify only when applicable.
|
|
|
118
100
|
|
|
119
101
|
**Done when:** `Lanes` has duration, queue, finish, holding-the-run-open per job.
|
|
120
102
|
|
|
121
|
-
- [ ] **Step 4 — Distributions:** One run cannot separate regression from noise. Pull
|
|
103
|
+
- [ ] **Step 4 — Distributions:** One run cannot separate regression from noise. Pull >=20 recent CI workflow runs per event type; keep green and red apart. Report p50 and p90 for total wall clock and critical-path lane finish, per event type. Say how typical Step 2 runs are. Every job timeout ~1.5x its p99 (in this sample size, slowest run). No timeout → host default (e.g. GitHub Actions 360 minutes) and bills all of it. e.g. `gh api "repos/{owner}/{repo}/actions/workflows/<workflow>/runs?event=push&branch=<branch>&per_page=30"`. **Done when:** p50 and p90 in `Distributions`; each job within timeout rule or finding.
|
|
122
104
|
- [ ] **Step 5 — Lead Time:** Lane finish times = one segment. Report DORA change lead time for push to integration branch: push → all lanes green → deployed. Split queue (Step 3), critical-path execution, `needs:` waits, re-run time (Step 10). Name dominating segment — that is the one worth buying down. **Done when:** `Lead Time` names split and dominating segment.
|
|
123
|
-
- [ ] **Step 6 — Timings:** Inside lanes that hold the run open or that a proposal would trim: step timings; task-runner cache hit rate (zero cached on a lane that should cache = finding); test counts executed (wall clock per test compares runs better than wall clock alone); remote-builder jobs — record builder queue and build time separately from wrapper; shard balance — slowest/fastest >~1.
|
|
105
|
+
- [ ] **Step 6 — Timings:** Inside lanes that hold the run open or that a proposal would trim: step timings; task-runner cache hit rate (zero cached on a lane that should cache = finding); test counts executed (wall clock per test compares runs better than wall clock alone); remote-builder jobs — record builder queue and build time separately from wrapper; shard balance — slowest/fastest >~1.3x means one shard holds the lane; fixed cost per job (checkout, toolchain setup, install) x parallel jobs (splitting buys wall clock, pays setup again); artifact upload/download time and stored size (large reports every green run cost time and storage). e.g. `gh run view <id> --log --job=<jobId>` and grep cache and executed-count lines. **Done when:** `Timings` holds hit rate, counts, shard ratio or "not sharded", setup cost, artifact size per lane that matters.
|
|
124
106
|
- [ ] **Step 7 — Caches:** Every cache, not only task runner. Hit or miss and restore time: package-manager store, framework build cache, browser binaries, native build caches (e.g. Gradle, CocoaPods, hosted mobile builds), image layer caches. Compare restore vs cold install — restore slower than rebuild = finding. Cache usage vs eviction limit — full cache evicts entries that matter. **Done when:** `Caches` row per cache: hit or miss · restore vs cold · over limit, or absent with evidence.
|
|
125
107
|
- [ ] **Step 8 — Affected:** Do PR lanes run only what changed (affected graph or path filter)? For docs-only change and one-app-scoped change, read `on:` triggers, `paths` filters, job-level `if:` — which lanes each starts. Where `paths` filter is safe, propose it and say required-check interaction: workflow skipped by path filter leaves required checks pending; job skipped by `if` reports success. **Done when:** `Affected` says what each sample change starts and names any required-check trap.
|
|
126
108
|
- [ ] **Step 9 — Local:** Time local gate on whole tree, cache forced off — warm or affected-only numbers are meaningless. Record beside CI critical path. **Done when:** `Local` holds forced whole-tree time, command, whether on critical path.
|
|
127
109
|
- [ ] **Step 10 — Reruns:** Red lane costs full re-run. Read concurrency block before counting. If in-progress runs not cancelled on integration branch, fix-and-repush = two complete runs; if cancelled, count cancelled minutes separately from re-runs — neither is zero. Flakiest lane slowest lane compounds wall clock; minutes here, cause → `bkit-audit-flakes`. Over Step 4 window: runs attempt >1; jobs failed then passed same commit, per lane — both → minutes. Also commits under both push and PR; runs completing after newer run started. **Done when:** `Reruns` holds those minutes and what concurrency block does.
|
|
128
|
-
- [ ] **Step 11 — Cost:** For Step 4 window: billable minutes per lane
|
|
110
|
+
- [ ] **Step 11 — Cost:** For Step 4 window: billable minutes per lane x runner class current per-minute price, remote-builder minutes, mobile-build credits — read prices this run. Derive cost per successful merge to integration branch, re-runs included. Spend outside CI minutes → `bkit-audit-cost`. Before recommending runner class change for CPU-bound lane, name one-run experiment on larger/different-architecture runner comparing cost and duration (running it is next step — changes workflow). Every finding states whether it buys latency or cost. **Done when:** `Cost` holds minutes, current prices, cost per merge, experiment name or "none".
|
|
129
111
|
- [ ] **Step 12 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per DORA metric, host performance metric, caching/sharding/concurrency/billing practice in anchor list → checked (name step) / not applicable (why) / finding. Per bkit anchor (doc section, rule, or issue shape): one row → followed (name step or evidence) / not applicable (why) / finding; departure with no recorded reason (e.g. `docs/decisions.jsonl` row, accepted-divergence entry) = finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
|
|
130
112
|
- [ ] **Step 13 — Anything Else:** (a) Everything changed since previous report's commit touching pipeline (workflows and composite actions, jobs and `needs:`, runner classes, task-runner config and cache keys, shard settings, remote-build profiles, local pre-push gate) → one-line verdict each. (b) Bounded ~30 min pass: what senior CI engineer flags that no step asks; read since previous run (incidents, new `docs/failures.jsonl` rows) — what would no step catch? **Done when:** `Beyond the Steps` holds both passes, or `none`. Class seen on 2 runs → propose step in `Process Improvements`.
|
|
131
113
|
|
|
132
114
|
### 🔒 Gate 2: Probes Check
|
|
133
115
|
|
|
134
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
135
|
-
|
|
136
116
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
137
117
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
138
118
|
- [ ] **Event types:** push and pull request are never treated as one pipeline.
|
|
139
119
|
- [ ] **Prices current:** every rate was read this run, not copied from a prior report.
|
|
140
|
-
- [ ] **Gate 2
|
|
120
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
141
121
|
|
|
142
122
|
## Findings
|
|
143
123
|
|
|
@@ -149,7 +129,7 @@ Verify only when applicable.
|
|
|
149
129
|
| `MEDIUM` | Cache miss on a lane that should cache; shard imbalance holding a lane open; setup cost paid again on every split; re-run minutes that rival the critical path |
|
|
150
130
|
| `LOW` | A slow lane that does not hold the run open; artifact size that is not on the critical path |
|
|
151
131
|
|
|
152
|
-
|
|
132
|
+
Within a severity: critical path first. Every finding states whether it buys latency or cost.
|
|
153
133
|
|
|
154
134
|
<!-- prettier-ignore -->
|
|
155
135
|
| ID | Severity | Location | Evidence | Expected |
|
|
@@ -237,17 +217,13 @@ PENDING
|
|
|
237
217
|
|
|
238
218
|
### 🔒 Gate 3: Report Check
|
|
239
219
|
|
|
240
|
-
|
|
241
|
-
|
|
242
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
220
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
243
221
|
- [ ] **Summary:** names count per severity and the segment that dominates wall clock.
|
|
244
222
|
- [ ] **Series:** every series beside previous report's numbers, or marked baseline.
|
|
245
|
-
- [ ] **Writes:** only this report
|
|
246
|
-
- [ ] **Process Improvements:** `Universal`
|
|
223
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway worktrees / remote targets removed.
|
|
224
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
247
225
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
248
|
-
- [ ] **Gate 3
|
|
249
|
-
|
|
250
|
-
> `Project Instructions` below `bkit:end` are consumer-owned — `bkit install` never overwrites them, `bkit check` drift stays clean. Add project-specific tools, paths, commands, and checks there, keyed by section or step title; never results.
|
|
226
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
251
227
|
|
|
252
228
|
<!-- bkit:end -->
|
|
253
229
|
|