@cbartens/bkit 5.5.1 → 6.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.bkit/README.md +167 -154
- package/.bkit/core/.agents/context.md +95 -29
- package/.bkit/core/.agents/docs.md +18 -15
- package/.bkit/core/.agents/plugins/bkit/hooks/bkit-gateguard.cjs +1 -0
- package/.bkit/core/.agents/plugins/bkit/hooks/bkit-guardrails.cjs +6 -5
- package/.bkit/core/.agents/plugins/bkit/hooks/bkit-readguard.cjs +1 -0
- package/.bkit/core/.agents/plugins/bkit/hooks/bkit-rules.cjs +65 -0
- package/.bkit/core/.agents/rules.md +112 -102
- package/.bkit/core/.agents/skills.md +63 -15
- package/.bkit/core/.bkit/README.md +167 -154
- package/.bkit/core/.bkit/authoring.md +747 -0
- package/.bkit/core/.bkit/cli.md +407 -0
- package/.bkit/core/.bkit/cloud.md +283 -195
- package/.bkit/core/.bkit/comparison.md +45 -43
- package/.bkit/core/.bkit/install.md +166 -95
- package/.bkit/core/.bkit/jsonl.md +339 -196
- package/.bkit/core/.bkit/pipeline.md +142 -145
- package/.bkit/core/.bkit/prompts.md +295 -264
- package/.bkit/core/.bkit/providers.md +460 -277
- package/.bkit/core/.bkit/router.md +69 -0
- package/.bkit/core/.bkit/templates.md +530 -256
- package/.bkit/core/.bkit/trackers.md +116 -65
- package/.bkit/core/.bkit/workflows.md +742 -618
- package/.bkit/core/.claude/hooks/bkit-gateguard.cjs +2 -2
- package/.bkit/core/.claude/hooks/bkit-guardrails.cjs +3 -3
- package/.bkit/core/.claude/hooks/bkit-preflight.sh +45 -14
- package/.bkit/core/.codex/hooks/bkit-guardrails.cjs +3 -3
- package/.bkit/core/.codex/hooks/bkit-rules.cjs +57 -0
- package/.bkit/core/.cursor/hooks/bkit-guardrails.cjs +7 -7
- package/.bkit/core/.cursor/hooks/bkit-preflight.sh +47 -12
- package/.bkit/core/.opencode/plugin/bkit-rules.js +89 -0
- package/.bkit/core/AGENTS.md +6 -80
- package/.bkit/core/docs/templates/bkit-audit-accessibility.md +128 -130
- package/.bkit/core/docs/templates/bkit-audit-adoption.md +104 -94
- package/.bkit/core/docs/templates/bkit-audit-agents.md +96 -98
- package/.bkit/core/docs/templates/bkit-audit-aio-seo.md +100 -103
- package/.bkit/core/docs/templates/bkit-audit-analytics.md +141 -107
- package/.bkit/core/docs/templates/bkit-audit-annotations.md +99 -97
- package/.bkit/core/docs/templates/bkit-audit-app-performance.md +122 -121
- package/.bkit/core/docs/templates/bkit-audit-app-store.md +158 -101
- package/.bkit/core/docs/templates/bkit-audit-architecture.md +114 -96
- package/.bkit/core/docs/templates/bkit-audit-ci-performance.md +76 -97
- package/.bkit/core/docs/templates/bkit-audit-config.md +123 -101
- package/.bkit/core/docs/templates/bkit-audit-cost.md +86 -99
- package/.bkit/core/docs/templates/bkit-audit-coverage.md +76 -93
- package/.bkit/core/docs/templates/bkit-audit-database.md +102 -95
- package/.bkit/core/docs/templates/bkit-audit-dead-code.md +165 -108
- package/.bkit/core/docs/templates/bkit-audit-deferrals.md +115 -109
- package/.bkit/core/docs/templates/bkit-audit-dependencies.md +265 -113
- package/.bkit/core/docs/templates/bkit-audit-documentation.md +119 -118
- package/.bkit/core/docs/templates/bkit-audit-duplication.md +140 -111
- package/.bkit/core/docs/templates/bkit-audit-failures.md +111 -106
- package/.bkit/core/docs/templates/bkit-audit-flakes.md +100 -99
- package/.bkit/core/docs/templates/bkit-audit-gates.md +107 -103
- package/.bkit/core/docs/templates/bkit-audit-issues.md +105 -105
- package/.bkit/core/docs/templates/bkit-audit-llm.md +134 -85
- package/.bkit/core/docs/templates/bkit-audit-logs.md +124 -125
- package/.bkit/core/docs/templates/bkit-audit-models.md +99 -78
- package/.bkit/core/docs/templates/bkit-audit-privacy.md +56 -76
- package/.bkit/core/docs/templates/bkit-audit-prompts.md +63 -78
- package/.bkit/core/docs/templates/bkit-audit-red-team.md +125 -93
- package/.bkit/core/docs/templates/bkit-audit-reliability.md +97 -96
- package/.bkit/core/docs/templates/bkit-audit-repo.md +170 -98
- package/.bkit/core/docs/templates/bkit-audit-security.md +207 -121
- package/.bkit/core/docs/templates/bkit-audit-slop.md +78 -95
- package/.bkit/core/docs/templates/bkit-audit-testing.md +163 -139
- package/.bkit/core/docs/templates/bkit-audit-usability.md +114 -96
- package/.bkit/core/docs/templates/bkit-plan.md +158 -281
- package/.bkit/core/engine/checks/after/auth.ts +40 -37
- package/.bkit/core/engine/checks/after/ci-yml.ts +104 -31
- package/.bkit/core/engine/checks/after/github.ts +95 -17
- package/.bkit/core/engine/checks/after/index.ts +21 -8
- package/.bkit/core/engine/checks/after/suppression.ts +8 -5
- package/.bkit/core/engine/checks/after/tools.ts +125 -123
- package/.bkit/core/engine/checks/before/context-fetch.ts +227 -33
- package/.bkit/core/engine/checks/before/env.ts +3 -3
- package/.bkit/core/engine/checks/before/files.ts +5 -4
- package/.bkit/core/engine/checks/before/index.ts +25 -1
- package/.bkit/core/engine/checks/before/repo.ts +208 -2
- package/.bkit/core/engine/checks/status-holes.ts +916 -123
- package/.bkit/core/engine/checks/tips/catalogue.ts +82 -20
- package/.bkit/core/engine/checks/tips/detect.ts +66 -0
- package/.bkit/core/engine/checks/tips/index.ts +52 -11
- package/.bkit/core/engine/cli.ts +251 -130
- package/.bkit/core/engine/commands/analysis.ts +282 -199
- package/.bkit/core/engine/commands/ci/ci.ts +363 -29
- package/.bkit/core/engine/commands/ci/pins.ts +172 -0
- package/.bkit/core/engine/commands/ci/push-gate.ts +223 -0
- 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 +86 -55
- package/.bkit/core/engine/commands/install/upgrade.ts +32 -15
- package/.bkit/core/engine/commands/land.ts +139 -18
- package/.bkit/core/engine/commands/lib.ts +381 -22
- package/.bkit/core/engine/commands/registry.ts +10 -2
- package/.bkit/core/engine/commands/setup/setup.ts +8 -7
- package/.bkit/core/engine/commands/stats.ts +260 -0
- package/.bkit/core/engine/commands/tips.ts +10 -5
- package/.bkit/core/engine/commands/workflow/branches.ts +2215 -176
- package/.bkit/core/engine/commands/workflow/challenge.ts +748 -0
- package/.bkit/core/engine/commands/workflow/completeness.ts +109 -0
- package/.bkit/core/engine/commands/workflow/context.ts +1249 -47
- package/.bkit/core/engine/commands/workflow/counters.ts +483 -95
- package/.bkit/core/engine/commands/workflow/decisions.ts +585 -0
- package/.bkit/core/engine/commands/workflow/disk.ts +238 -56
- package/.bkit/core/engine/commands/workflow/fids.ts +811 -33
- package/.bkit/core/engine/commands/workflow/issues.ts +413 -64
- package/.bkit/core/engine/commands/workflow/ledgers.ts +1333 -36
- package/.bkit/core/engine/commands/workflow/locks.ts +28 -2
- package/.bkit/core/engine/commands/workflow/plan-blocks.ts +691 -0
- package/.bkit/core/engine/commands/workflow/plan-versions.ts +21 -0
- package/.bkit/core/engine/commands/workflow/plans.ts +257 -0
- package/.bkit/core/engine/commands/workflow/prs.ts +178 -33
- package/.bkit/core/engine/commands/workflow/repo.ts +66 -8
- package/.bkit/core/engine/commands/workflow/roadmap.ts +72 -22
- package/.bkit/core/engine/commands/workflow/run-facts.ts +492 -0
- package/.bkit/core/engine/commands/workflow/runs.ts +827 -79
- package/.bkit/core/engine/commands/workflow/runtime.ts +25 -1
- package/.bkit/core/engine/commands/workflow/skills.ts +1 -0
- package/.bkit/core/engine/commands/workflow/status.ts +329 -33
- package/.bkit/core/engine/commands/workflow/step-table.ts +381 -0
- package/.bkit/core/engine/commands/workflow/steps.ts +841 -105
- package/.bkit/core/engine/commands/workflow/summary-findings.ts +177 -0
- package/.bkit/core/engine/commands/workflow/summary.ts +544 -0
- package/.bkit/core/engine/commands/workflow/tasks.ts +409 -0
- package/.bkit/core/engine/commands/workflow/test-blocks.ts +254 -0
- package/.bkit/core/engine/commands/workflow/tests-changed.ts +201 -0
- package/.bkit/core/engine/commands/workflow/tests.ts +2124 -330
- package/.bkit/core/engine/commands/workflow/tracker.ts +1195 -0
- package/.bkit/core/engine/commands/workflow/workflows.ts +1197 -235
- package/.bkit/core/engine/commands/workflow/worktrees.ts +543 -24
- package/.bkit/core/engine/install/cloud-env.ts +251 -121
- package/.bkit/core/engine/install/context-ci-workflow.ts +102 -0
- package/.bkit/core/engine/install/manifest.ts +67 -17
- package/.bkit/core/engine/install/modules/antigravity.ts +3 -2
- package/.bkit/core/engine/install/modules/cloud.ts +24 -16
- package/.bkit/core/engine/install/modules/codex.ts +15 -2
- package/.bkit/core/engine/install/modules/core.ts +1196 -45
- package/.bkit/core/engine/install/modules/cursor.ts +6 -6
- package/.bkit/core/engine/install/modules/opencode.ts +18 -6
- package/.bkit/core/engine/install/template-notes.ts +130 -0
- package/.bkit/core/engine/install/version-file.ts +9 -4
- package/.bkit/core/engine/install/write.ts +5 -0
- package/.bkit/core/engine/ledgers/compact.ts +124 -0
- package/.bkit/core/engine/ledgers/journal.ts +291 -0
- package/.bkit/core/engine/ledgers/migrate.ts +92 -0
- package/.bkit/core/engine/ledgers/status.ts +249 -21
- package/.bkit/core/engine/ledgers/telemetry.ts +1397 -253
- package/.bkit/core/engine/render/hosts.ts +118 -14
- package/.bkit/core/engine/render/models.ts +12 -0
- package/.bkit/core/engine/shared/bkit-latest.ts +26 -4
- package/.bkit/core/engine/shared/branches.ts +4 -1
- package/.bkit/core/engine/shared/dep-updater.ts +60 -0
- package/.bkit/core/engine/shared/egress.ts +8 -1
- package/.bkit/core/engine/shared/json.ts +25 -7
- package/.bkit/core/engine/shared/package-manager.ts +9 -0
- package/.bkit/core/engine/shared/settings.ts +243 -31
- package/.bkit/core/engine/shared/text.ts +361 -0
- package/.bkit/core/engine/shared/timeouts.ts +2 -0
- package/.bkit/core/engine/tools/cli-doc.ts +111 -0
- package/.bkit/core/engine/tools/grammar-density.ts +215 -0
- package/.bkit/core/engine/tools/instructions-sources.ts +832 -0
- package/.bkit/core/engine/tools/instructions.ts +1802 -0
- package/.bkit/core/hooks/antigravity-hook.js +25 -10
- package/.bkit/core/hooks/gateguard-engine.js +54 -29
- package/.bkit/core/hooks/guardrails-shell.js +4 -5
- package/.bkit/core/hooks/guardrails-tiers.js +10 -4
- package/.bkit/core/hooks/preflight-linear.sh +9 -9
- package/.bkit/core/hooks/preflight-rules.sh +8 -0
- package/.bkit/core/hooks/readguard-engine.js +29 -10
- package/.bkit/core/hooks/session-rules-advisory.js +61 -0
- package/.bkit/core/prompts/bkit-audit-generate.md +202 -94
- package/.bkit/core/prompts/bkit-build-challenge-1.md +76 -34
- package/.bkit/core/prompts/bkit-build-challenge-2.md +85 -38
- package/.bkit/core/prompts/bkit-build-install-skills.md +50 -28
- package/.bkit/core/prompts/bkit-build-plan-convert.md +85 -0
- package/.bkit/core/prompts/bkit-build-plan-current.md +59 -36
- package/.bkit/core/prompts/bkit-build-plan-gaps-remediate.md +101 -36
- package/.bkit/core/prompts/bkit-build-plan-tasks.md +149 -0
- package/.bkit/core/prompts/bkit-build-plan-tests.md +120 -0
- package/.bkit/core/prompts/bkit-build-plan-verify.md +104 -43
- package/.bkit/core/prompts/bkit-debug-abort-handover.md +47 -32
- package/.bkit/core/prompts/bkit-debug-failure-diagnose.md +109 -57
- package/.bkit/core/prompts/bkit-debug-failure-remediate.md +65 -39
- package/.bkit/core/prompts/bkit-debug-failure-reproduce.md +53 -31
- package/.bkit/core/prompts/bkit-debug-failure-soak.md +65 -34
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-1.md +46 -31
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-2.md +45 -31
- package/.bkit/core/prompts/bkit-design-brainstorm-ideate-3.md +43 -30
- package/.bkit/core/prompts/bkit-design-generate.md +80 -46
- package/.bkit/core/prompts/bkit-design-organise.md +83 -32
- package/.bkit/core/prompts/bkit-design-review-1.md +70 -50
- package/.bkit/core/prompts/bkit-design-review-2.md +65 -46
- package/.bkit/core/prompts/bkit-design-spike.md +64 -40
- package/.bkit/core/prompts/bkit-design-update.md +53 -28
- package/.bkit/core/prompts/bkit-plan-generate.md +101 -29
- package/.bkit/core/prompts/bkit-plan-review-1.md +78 -41
- package/.bkit/core/prompts/bkit-plan-review-2.md +78 -35
- package/.bkit/core/prompts/bkit-plan-scope-check.md +116 -0
- package/.bkit/core/prompts/bkit-plan-update.md +86 -31
- package/.bkit/core/prompts/bkit-ship-conflict-resolve.md +94 -50
- package/.bkit/core/prompts/bkit-ship-deferred-sweep.md +91 -41
- package/.bkit/core/prompts/bkit-ship-update-docs.md +45 -24
- package/.bkit/core/prompts/bkit-utility-compress-markdown.md +65 -49
- package/.bkit/core/prompts/bkit-utility-update-decisions.md +87 -42
- package/.bkit/core/prompts/bkit-utility-update-deferrals.md +81 -37
- package/.bkit/core/prompts/bkit-utility-update-documentation.md +43 -25
- package/.bkit/core/prompts/bkit-utility-update-failures.md +84 -37
- package/.bkit/core/prompts/bkit-utility-update-knowledge.md +88 -42
- package/.bkit/core/prompts/bkit-utility-update-roadmap.md +92 -39
- package/.bkit/core/prompts/bkit-utility-update-tracker.md +159 -60
- package/.bkit/core/workflows/bkit-auto.md +89 -58
- package/.bkit/core/workflows/bkit-build.md +967 -517
- package/.bkit/core/workflows/bkit-debug.md +555 -387
- package/.bkit/core/workflows/bkit-design.md +319 -283
- package/.bkit/core/workflows/bkit-plan.md +319 -342
- package/.bkit/core/workflows/bkit-ship.md +525 -328
- package/.bkit/shared/.agents/plugins/bkit/hooks.json +10 -0
- package/.bkit/shared/.bkit/.env.example +2 -2
- package/.bkit/shared/.claude/bkit-cloud.md +12 -10
- package/.bkit/shared/.claude/settings.json +14 -0
- package/.bkit/shared/.codex/bkit-cloud.md +98 -0
- package/.bkit/shared/.codex/hooks.json +20 -0
- package/.bkit/shared/.cursor/bkit-cloud.md +3 -3
- 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 +12 -1
- package/.bkit/shared/CLAUDE.md +6 -2
- package/.bkit/shared/GEMINI.md +5 -2
- package/.bkit/shared/docs/architecture.md +4 -7
- package/.bkit/shared/docs/data-schema.md +4 -7
- package/.bkit/shared/docs/deployments.md +241 -168
- package/.bkit/shared/docs/design.md +11 -12
- package/.bkit/shared/docs/noise.md +8 -7
- package/.bkit/shared/docs/observability.md +5 -8
- package/.bkit/shared/docs/security.md +35 -17
- package/.bkit/shared/docs/setup.md +29 -18
- package/.bkit/shared/docs/technology.md +3 -6
- package/.bkit/shared/docs/testing.md +289 -174
- package/.bkit/shared/gitignore +6 -2
- package/.bkit/templates/.claude/hooks/bkit-cloud-bootstrap.sh +15 -16
- package/.bkit/templates/.cursor/Dockerfile +12 -8
- package/.bkit/templates/.cursor/environment.json +1 -1
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-bug.yml +10 -8
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-change.yml +45 -12
- package/.bkit/templates/.github/ISSUE_TEMPLATE/bkit-idea.yml +3 -3
- package/.bkit/templates/.github/renovate.json5 +34 -6
- package/.bkit/templates/.github/workflows/bkit-ci.yml +54 -51
- package/.bkit/templates/.github/workflows/bkit-cloud.yml +34 -33
- package/.bkit/templates/.github/workflows/bkit-health.yml +97 -0
- package/.bkit/templates/.github/workflows/bkit-renovate.yml +5 -4
- package/.bkit/templates/.github/workflows/bkit-trivy.yml +5 -4
- package/.bkit/templates/.husky/pre-commit +2 -2
- package/.bkit/templates/.husky/pre-push +96 -36
- package/.bkit/templates/.prettierignore +6 -0
- package/.bkit/templates/.vale.ini +27 -27
- package/.bkit/templates/context/bkit-cloudrun.md +23 -15
- package/.bkit/templates/context/bkit-expo.md +70 -52
- package/.bkit/templates/context/bkit-github.md +93 -56
- package/.bkit/templates/context/bkit-inngest.md +21 -15
- package/.bkit/templates/context/bkit-maestro.md +22 -16
- package/.bkit/templates/context/bkit-playwright.md +23 -17
- package/.bkit/templates/context/bkit-resend.md +12 -10
- package/.bkit/templates/context/bkit-sentry.md +30 -20
- package/.bkit/templates/context/bkit-serena.md +8 -7
- package/.bkit/templates/context/bkit-stripe.md +14 -13
- package/.bkit/templates/context/bkit-supabase.md +16 -13
- package/.bkit/templates/context/bkit-tavily.md +14 -11
- package/.bkit/templates/context/bkit-vercel.md +27 -18
- package/.bkit/templates/docs/capabilities.md +15 -14
- package/.bkit/templates/scripts/ci/{check-accepted-divergences.mjs → bkit-check-accepted-divergences.mjs} +6 -3
- package/.bkit/templates/scripts/ci/{check-accepted-divergences.test.mjs → bkit-check-accepted-divergences.test.mjs} +3 -3
- package/.bkit/templates/scripts/ci/{check-capstone.mjs → bkit-check-capstone.mjs} +2 -2
- package/.bkit/templates/scripts/ci/{check-capstone.test.mjs → bkit-check-capstone.test.mjs} +4 -4
- package/.bkit/templates/scripts/ci/{check-dependency-audit.mjs → bkit-check-dependency-audit.mjs} +103 -18
- package/.bkit/templates/scripts/ci/{check-dependency-audit.test.mjs → bkit-check-dependency-audit.test.mjs} +31 -3
- package/.bkit/templates/scripts/ci/bkit-machine-lock.sh +387 -0
- package/.bkit/templates/scripts/ci/bkit-test-awake.mjs +75 -0
- package/.bkit/templates/scripts/ci/bkit-test-awake.test.mjs +160 -0
- package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.mjs → bkit-resolve-push-base.mjs} +3 -3
- package/.bkit/templates/scripts/ci/lanes/{resolve-push-base.test.mjs → bkit-resolve-push-base.test.mjs} +4 -4
- package/.bkit/templates/scripts/cleanup/bkit-disk-prune.mjs +10 -2
- package/.bkit/templates/scripts/graphify/bkit-graph-drift.py +1 -1
- package/.bkit/templates/scripts/graphify/bkit-graph-eager.py +3 -3
- package/.bkit/templates/scripts/graphify/bkit-graph-embed.py +63 -0
- package/.bkit/templates/scripts/graphify/bkit-graph-imports.py +2 -2
- package/.bkit/templates/scripts/graphify/bkit-graph-pre-push.sh +69 -18
- package/.bkit/templates/scripts/graphify/bkit-graph-repair.py +3 -3
- package/.bkit/templates/scripts/graphify/bkit-graph-surface.py +1 -1
- package/.bkit/templates/scripts/graphify/bkit-graphify-graphml.py +1 -1
- package/.bkit/templates/scripts/graphify/bkit-graphify-rollup.py +197 -126
- package/.bkit/templates/scripts/graphify/bkit-graphify.sh +64 -41
- package/.bkit/templates/scripts/slop/bkit-slop-type-suppression.mjs +23 -7
- package/.bkit/templates/slop-scan.config.json +9 -2
- package/CHANGELOG.md +231 -0
- package/README.md +278 -89
- package/dist/checks/after/auth.js +36 -33
- package/dist/checks/after/ci-yml.js +91 -30
- package/dist/checks/after/github.js +91 -17
- package/dist/checks/after/index.js +22 -11
- package/dist/checks/after/suppression.js +8 -5
- package/dist/checks/after/tools.js +111 -114
- package/dist/checks/before/context-fetch.js +218 -33
- package/dist/checks/before/env.js +3 -3
- package/dist/checks/before/files.js +5 -3
- package/dist/checks/before/index.js +20 -3
- package/dist/checks/before/repo.js +197 -2
- package/dist/checks/status-holes.js +739 -114
- package/dist/checks/tips/catalogue.js +70 -19
- package/dist/checks/tips/detect.js +62 -0
- package/dist/checks/tips/index.js +51 -9
- package/dist/cli.js +234 -124
- package/dist/commands/analysis.js +174 -141
- package/dist/commands/ci/ci.js +302 -25
- package/dist/commands/ci/pins.js +142 -0
- package/dist/commands/ci/push-gate.js +194 -0
- 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 +82 -55
- package/dist/commands/install/upgrade.js +21 -11
- package/dist/commands/land.js +137 -17
- package/dist/commands/lib.js +295 -21
- package/dist/commands/registry.js +10 -2
- package/dist/commands/setup/setup.js +8 -7
- package/dist/commands/stats.js +175 -0
- package/dist/commands/tips.js +7 -3
- package/dist/commands/workflow/branches.js +1873 -152
- package/dist/commands/workflow/challenge.js +609 -0
- package/dist/commands/workflow/completeness.js +97 -0
- package/dist/commands/workflow/context.js +1045 -46
- package/dist/commands/workflow/counters.js +385 -86
- package/dist/commands/workflow/decisions.js +484 -0
- package/dist/commands/workflow/disk.js +214 -56
- package/dist/commands/workflow/fids.js +706 -33
- package/dist/commands/workflow/issues.js +349 -59
- package/dist/commands/workflow/ledgers.js +1123 -37
- package/dist/commands/workflow/locks.js +26 -2
- package/dist/commands/workflow/plan-blocks.js +501 -0
- package/dist/commands/workflow/plan-versions.js +22 -0
- package/dist/commands/workflow/plans.js +205 -0
- package/dist/commands/workflow/prs.js +154 -35
- package/dist/commands/workflow/repo.js +58 -8
- package/dist/commands/workflow/roadmap.js +58 -23
- package/dist/commands/workflow/run-facts.js +421 -0
- package/dist/commands/workflow/runs.js +670 -72
- package/dist/commands/workflow/runtime.js +15 -1
- package/dist/commands/workflow/skills.js +1 -0
- package/dist/commands/workflow/status.js +282 -34
- package/dist/commands/workflow/step-table.js +308 -0
- package/dist/commands/workflow/steps.js +703 -96
- package/dist/commands/workflow/summary-findings.js +117 -0
- package/dist/commands/workflow/summary.js +388 -0
- package/dist/commands/workflow/tasks.js +378 -0
- package/dist/commands/workflow/test-blocks.js +231 -0
- package/dist/commands/workflow/tests-changed.js +172 -0
- package/dist/commands/workflow/tests.js +1695 -305
- package/dist/commands/workflow/tracker.js +983 -0
- package/dist/commands/workflow/workflows.js +1014 -222
- package/dist/commands/workflow/worktrees.js +432 -26
- package/dist/install/cloud-env.js +233 -99
- package/dist/install/context-ci-workflow.js +85 -0
- package/dist/install/manifest.js +64 -17
- package/dist/install/modules/antigravity.js +3 -2
- package/dist/install/modules/cloud.js +25 -16
- package/dist/install/modules/codex.js +12 -2
- package/dist/install/modules/core.js +1090 -48
- package/dist/install/modules/cursor.js +6 -6
- package/dist/install/modules/opencode.js +13 -7
- package/dist/install/template-notes.js +116 -0
- package/dist/install/version-file.js +9 -4
- package/dist/ledgers/compact.js +87 -0
- package/dist/ledgers/journal.js +233 -0
- package/dist/ledgers/migrate.js +81 -0
- package/dist/ledgers/status.js +176 -13
- package/dist/ledgers/telemetry.js +1010 -125
- package/dist/render/hosts.js +104 -14
- package/dist/render/models.js +12 -0
- package/dist/shared/bkit-latest.js +26 -4
- package/dist/shared/branches.js +3 -1
- package/dist/shared/dep-updater.js +49 -0
- package/dist/shared/egress.js +8 -1
- package/dist/shared/json.js +20 -7
- package/dist/shared/package-manager.js +6 -0
- package/dist/shared/settings.js +181 -24
- package/dist/shared/text.js +333 -0
- package/dist/shared/timeouts.js +2 -0
- package/dist/tools/cli-doc.js +97 -0
- package/dist/tools/grammar-density.js +183 -0
- package/dist/tools/instructions-sources.js +720 -0
- package/dist/tools/instructions.js +1623 -0
- package/package.json +156 -51
- package/.bkit/core/.bkit/lite.md +0 -73
- package/.bkit/core/engine/commands/harvest.ts +0 -459
- package/.bkit/core/engine/commands/workflow/workstreams.ts +0 -166
- 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-plan-execute.md +0 -76
- 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/.bkit/templates/scripts/ci/bkit-local-stack-lock.sh +0 -194
- package/dist/commands/harvest.js +0 -353
- package/dist/commands/workflow/workstreams.js +0 -143
- package/dist/tools/wording.js +0 -680
- /package/.bkit/templates/.vale/styles/{House → Bkit}/Filler.yml +0 -0
- /package/.bkit/templates/.vale/styles/{House → Bkit}/Hedging.yml +0 -0
- /package/.bkit/templates/.vale/styles/{House → Bkit}/LLMSlop.yml +0 -0
- /package/.bkit/templates/.vale/styles/{House → Bkit}/Verbose.yml +0 -0
- /package/.bkit/templates/scripts/ci/{accepted-advisories.json → bkit-accepted-advisories.json} +0 -0
- /package/.bkit/templates/scripts/ci/{accepted-divergences.json → bkit-accepted-divergences.json} +0 -0
- /package/.bkit/templates/scripts/launchd/{launchd.env.example → bkit-launchd.env.example} +0 -0
- /package/.bkit/templates/scripts/launchd/{ai.bkit.launchd.plist → bkit-launchd.plist} +0 -0
|
@@ -1,57 +1,52 @@
|
|
|
1
|
-
<!-- Note: Reports live at `docs/audits/{YYYYMM}/{slug}.md`. `{YYYYMM}` = UTC month of this run. `{slug}` = template basename without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md` (`{TIMESTAMP}` = `date -u +%Y%m%dT%H%M%SZ`). Never overwrite. The report is stamped with a `bkit:anchor` block recording the audited commit (`baseSha`) and branch (`baseRef`); never hand-author or edit it. `@bkit-audit-generate` fills this template. -->
|
|
2
|
-
|
|
3
1
|
<!-- bkit:start -->
|
|
4
2
|
|
|
5
3
|
{{BKIT_MANAGED_MARKER}}
|
|
6
4
|
|
|
5
|
+
<!-- Note: @bkit-audit-generate fills this template. The report lives at `docs/audits/{YYYYMM}/{slug}.md`, where `{YYYYMM}` is the UTC month of the run and `{slug}` is this file's name without `bkit-audit-` and `.md`. **If** that month already has `{slug}.md` or `{slug}-{TIMESTAMP}.md` → write `{slug}-{TIMESTAMP}.md`, where `{TIMESTAMP}` is the output of `date -u +%Y%m%dT%H%M%SZ`. NEVER overwrite an earlier report. The report is stamped with a `bkit:anchor` block that records the audited commit (`baseSha`) and branch (`baseRef`). NEVER write or edit that block by hand. -->
|
|
6
|
+
|
|
7
7
|
# Prompt Audit
|
|
8
8
|
|
|
9
9
|
> [!CAUTION]
|
|
10
|
-
> **Purpose:** Each prompt the product sends to a model
|
|
10
|
+
> **Purpose:** Each prompt the product sends to a model is clear, well structured, and written for the model that runs it, per that model maker's current prompting guide.
|
|
11
11
|
>
|
|
12
12
|
> **Rules:**
|
|
13
13
|
>
|
|
14
|
-
> -
|
|
15
|
-
> -
|
|
16
|
-
> -
|
|
17
|
-
> -
|
|
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
|
-
> - Quote at most one line of prompt text per finding; never copy personal data or a model completion into the report.
|
|
23
|
-
> - never call a model to generate. Token counts use a local tokenizer or a provider count endpoint only.
|
|
14
|
+
> - Quote at most one line of prompt text per finding.
|
|
15
|
+
> - NEVER copy personal data or a model completion into the report.
|
|
16
|
+
> - Never call a model to generate.
|
|
17
|
+
> - Count tokens with a local tokenizer or a provider count endpoint only.
|
|
24
18
|
|
|
25
19
|
## Universal Instructions
|
|
26
20
|
|
|
27
21
|
### Context & Goals
|
|
28
22
|
|
|
29
|
-
A prompt is written against one model maker's advice at one point in time. The model behind it changes, the advice changes, and the prompt does not.
|
|
23
|
+
A prompt is written against one model maker's advice at one point in time. The model behind it changes, the advice changes, and the prompt does not. Examples: rules pile up without reasons, emphasis written for an older model makes a newer one over-apply a rule, and the output format drifts from the parser that reads it. Nothing fails a test: the model still answers, a little worse. The failure this audit targets is a prompt that the current guide for its model says will degrade results, which nobody re-read after the model or the guide changed.
|
|
30
24
|
|
|
31
|
-
**Applies when:** the product sends a prompt to a language model at runtime (system prompt, message template, few-shot examples, tool or output-schema descriptions). Coding-agent instruction files and bkit-managed files are not product prompts.
|
|
25
|
+
**Applies when:** the product sends a prompt to a language model at runtime (system prompt, message template, few-shot examples, tool or output-schema descriptions). Coding-agent instruction files and bkit-managed files are not product prompts. **If** the product sends none → write one `N/A` row with its evidence, and never report the surface as "clean".
|
|
32
26
|
|
|
33
|
-
**Cadence:**
|
|
27
|
+
**Cadence:** Run once a quarter. Run an extra pass after a model change at any call site (`bkit-audit-models`), a new prompt set, or a maker guide update.
|
|
34
28
|
|
|
35
|
-
**Anchor Standards:** record URL, last-updated date or date read, and the model generation
|
|
29
|
+
**Anchor Standards:** For each guide, record the URL, the last-updated date or the date it was read, and the model generation it targets.
|
|
36
30
|
|
|
37
31
|
- Anthropic prompt engineering docs and the prompting best-practices page for current Claude models.
|
|
38
|
-
- OpenAI prompt engineering guide and the model-specific prompting guide for each model in use (e.g
|
|
32
|
+
- OpenAI prompt engineering guide and the model-specific prompting guide for each model in use (e.g., the cookbook guide per model generation).
|
|
39
33
|
- Google Gemini API prompt design strategies.
|
|
40
|
-
- Every other maker whose model runs a prompt (e.g
|
|
34
|
+
- Every other maker whose model runs a prompt (e.g., xAI, Mistral, Meta, DeepSeek, Qwen): its own prompting guide, or `Not Checked` when it publishes none; its model parameter docs either way.
|
|
41
35
|
- Each maker's tool-use and structured-output docs, for tool and schema descriptions.
|
|
36
|
+
- bkit's authoring rules: `.bkit/authoring.md` § All Agent-Read Files, § Prompts and Workflows and § Prompts Only, read at the installed bkit version (`.bkit/version`).
|
|
42
37
|
|
|
43
|
-
Guides disagree. The guide for the model that runs the prompt wins. A prompt that runs on models from more than one maker (fallback chain, router, several hosts)
|
|
38
|
+
Guides disagree. The guide for the model that runs the prompt wins. A prompt that runs on models from more than one maker (fallback chain, router, several hosts) follows the current guides of the makers whose models run it day to day. A fallback model's guide counts only where it does not conflict with them.
|
|
44
39
|
|
|
45
40
|
### Scope
|
|
46
41
|
|
|
47
|
-
-
|
|
48
|
-
-
|
|
49
|
-
-
|
|
50
|
-
-
|
|
51
|
-
-
|
|
52
|
-
-
|
|
53
|
-
-
|
|
54
|
-
- Deliberate departures from a guide
|
|
42
|
+
- Read every runtime prompt: system prompt, message template, few-shot set, prefill, tool descriptions and output-schema descriptions.
|
|
43
|
+
- Name the model and the guide for each prompt.
|
|
44
|
+
- Check clarity: the task, success, the context and reason behind each rule, definitions, contradictions and dead instructions.
|
|
45
|
+
- Check structure: sections, delimiters, ordering, examples, and the output format against its parser.
|
|
46
|
+
- Check model fit: emphasis, reasoning and verbosity controls, sampling parameters, prefill, and workarounds from an older model.
|
|
47
|
+
- Check tool and output-schema descriptions.
|
|
48
|
+
- Measure token cost, duplication and cache-friendly ordering.
|
|
49
|
+
- Deliberate departures from a guide are recorded once, and are not re-raised.
|
|
55
50
|
|
|
56
51
|
### Out of Scope
|
|
57
52
|
|
|
@@ -60,7 +55,7 @@ Guides disagree. The guide for the model that runs the prompt wins. A prompt tha
|
|
|
60
55
|
| --- | --- | --- |
|
|
61
56
|
| Injection boundary, tool capability, output validators, call limits, job-scope bound, evals / golden sets | LLM sweep | `bkit-audit-llm` |
|
|
62
57
|
| Model choice, deprecation, catalogue, fallback-chain membership | Model sweep | `bkit-audit-models` |
|
|
63
|
-
| Coding-agent instruction files (e.g
|
|
58
|
+
| Coding-agent instruction files (e.g., `AGENTS.md`, `CLAUDE.md`, agent definitions, skills): loading, permissions, untrusted input | Agent config sweep | `bkit-audit-agents` |
|
|
64
59
|
| Contradictions between instruction files; always-loaded size | Documentation sweep | `bkit-audit-documentation` |
|
|
65
60
|
| bkit-managed prompts and templates (`.bkit/`, `bkit-*` host agent mirrors, `bkit:start` / `bkit:end` blocks) | Fixed upstream in bkit | bkit's own run of this audit |
|
|
66
61
|
| Live hostile probes | Red team | `bkit-audit-red-team` |
|
|
@@ -69,55 +64,46 @@ Guides disagree. The guide for the model that runs the prompt wins. A prompt tha
|
|
|
69
64
|
|
|
70
65
|
### Pre-Flight / Dependencies
|
|
71
66
|
|
|
72
|
-
**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.
|
|
73
|
-
|
|
74
|
-
**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.
|
|
75
|
-
|
|
76
67
|
#### Core
|
|
77
68
|
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
- [ ] **
|
|
81
|
-
- [ ] **Code Search:** Steps 2, 4–9 — text search and language server for call sites (e.g. ripgrep, Serena, `tsserver`). Prompts often markdown or string literals; tool descriptions often strings in schema files. Language-server hits under-report; empty inconclusive → corroborate with text search and name the tool. Fallback: text search only; name it per claim.
|
|
82
|
-
- [ ] **Web:** Steps 3, 10 — each maker's prompting guide (e.g. WebFetch, WebSearch). Fallback: guide practice recorded as unread; Steps 4–7 cite the previous report's guide version and say so.
|
|
69
|
+
- [ ] **Permissions:** every blocked call is recorded.
|
|
70
|
+
- [ ] **Code Search:** Steps 2, 4-9 — text search, and the language server for call sites (e.g., ripgrep, Serena, `tsserver`). Prompts are often markdown or string literals, and tool descriptions are often strings in schema files. Language-server hits under-report. **If** a result is empty → treat it as inconclusive, corroborate it with text search, and name the tool. Fallback: text search only, and name the tool for each claim.
|
|
71
|
+
- [ ] **Web:** Steps 3, 10 — each maker's prompting guide (e.g., WebFetch, WebSearch). Fallback: record guide practice as unread; Steps 4-7 cite the previous report's guide version and say so.
|
|
83
72
|
|
|
84
73
|
#### Conditional
|
|
85
74
|
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
- [ ] **
|
|
89
|
-
- [ ] **Token Counter:** Step 8 — local tokenizer or provider count endpoint (no generation). Fallback: character count ÷ 4, labelled estimate.
|
|
75
|
+
- [ ] **LLM Report:** **If** a `bkit-audit-llm` report exists → Steps 2, 9 — its `Inventory` and `Evals`. Fallback: build the inventory from code, and mark eval coverage `Not Checked`.
|
|
76
|
+
- [ ] **Authoring Rules:** **If** `.bkit/authoring.md` exists → Step 5 — its principles. Fallback: mark the authoring rows `Not Checked`, never as a pass.
|
|
77
|
+
- [ ] **Token Counter:** Step 8 — a local tokenizer or a provider count endpoint (no generation). Fallback: use character count ÷ 4, labelled as an estimate.
|
|
90
78
|
|
|
91
79
|
### 🔒 Gate 1: Prerequisites Check
|
|
92
80
|
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
96
|
-
- [ ] **Gate 1 - Verified:** All Core items checked. All applicable Conditional items checked.
|
|
81
|
+
- [ ] **Gaps named:** every missing item names its fallback and its `Not Checked` entry.
|
|
82
|
+
- [ ] **Gate 1 — Verified:** every item above, every Core item and every applicable Conditional item is checked.
|
|
97
83
|
|
|
98
84
|
### Probe Steps
|
|
99
85
|
|
|
100
|
-
- [ ] **Step 1 — Previous Run:**
|
|
101
|
-
- [ ] **Step 2 — Inventory:** Start from code: every model call site outside tests
|
|
102
|
-
- [ ] **Step 3 — Guides:**
|
|
103
|
-
- [ ] **Step 4 — Clarity:**
|
|
104
|
-
- [ ] **Step 5 — Structure:**
|
|
105
|
-
- [ ] **Step 6 — Model Fit:**
|
|
106
|
-
- [ ] **Step 7 — Tools and Schemas:**
|
|
107
|
-
- [ ] **Step 8 — Efficiency:**
|
|
108
|
-
- [ ] **Step 9 — Deliberate Choices:**
|
|
109
|
-
- [ ] **Step 10 — Standards:** Confirm current version
|
|
110
|
-
- [ ] **Step 11 — Anything Else:** (a)
|
|
86
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** `Previous Run` holds the closure rate, or the run is marked baseline.
|
|
87
|
+
- [ ] **Step 2 — Inventory:** Start from the code: every model call site outside tests, with the newest `bkit-audit-llm` `Inventory` as a cross-check, not as the source. For each prompt, record: the file and call sites · the model(s) that run it — every model in the fallback chain, resolved at the call site (choice and lifecycle belong to `bkit-audit-models`, and are not scored here) · the maker guide that applies · the task (extract, classify, write, converse, tool-calling) · the output consumer (parser, schema, human) · the eval set covering it (`bkit-audit-llm` `Evals`) · the last-changed commit · whether the model or guide changed since. Exclude bkit-managed files and coding-agent instruction files. Diff against the previous run, and read each new prompt or new model first. **Done when:** `Inventory` has a row per prompt, or `N/A` is recorded → **STOP**.
|
|
88
|
+
- [ ] **Step 3 — Guides:** For each maker in `Inventory`, read the current prompting guide and the model-specific page for each model generation in use. Record the URL, the last-updated date or the date read, and the generation targeted. Build `Guidance`: practice · source · makers it applies to · which conflict. **If** makers conflict → note which prompts run on both. **If** there is no guide, **or** its URL is dead → still read the maker's model parameter docs per generation (e.g., reasoning-effort values, rejected sampling parameters), so the Step 6 parameter checks run. **If** the parameter docs are missing → mark that generation's parameter checks `Not Checked`. **If** a guide is unread → mark it `Not Checked`, and use the previous report's reading, labelled, for that maker in Steps 4-7. **Done when:** `Guidance` has a row per practice used in Steps 4-7, and every row is sourced.
|
|
89
|
+
- [ ] **Step 4 — Clarity:** For each prompt, check that: the task and what a good answer looks like are stated up front; the audience and context are given; each constraint carries its reason where the guide asks for one; it says what to do, not only what to avoid; the terms the output depends on are defined (e.g., date format, "recent", allowed labels, "out-of-scope" in a redirect rule); a conversational prompt states its job and the reply to off-topic asks (wording only — enforcement belongs to `bkit-audit-llm` `Job Scope`); there is no contradiction within the prompt, or between the system prompt and the template; and no dead instruction names a removed field, tool or format. **Done when:** `Clarity` has a row per prompt: a verdict per check, with each failure cited.
|
|
90
|
+
- [ ] **Step 5 — Structure:** For each prompt, check that: sections and inputs are delimited the way the guide recommends (e.g., XML tags, markdown headings); instructions are kept apart from inserted data (layout only — injection belongs to `bkit-audit-llm`); long inputs sit where the guide says (e.g., documents first, question last); the output format is stated and matches its consumer, so read the parser or schema and compare field names, types and enums, and mark a human consumer `N/A`; every parsed field has an instruction (or schema description) that sets it and says what it counts; every field the instructions ask for appears in the output format; a structured-output or tool schema is used where the provider supports it and the guide prefers it; and examples are present where format or judgment matters, varied, consistent with the instructions, and not copied verbatim into output. Then check each prompt against the principles of `.bkit/authoring.md`, one row per principle. **Done when:** `Structure` has a row per prompt: a verdict per check, with the format-vs-parser and field-to-instruction diffs recorded, and a row per `.bkit/authoring.md` principle.
|
|
91
|
+
- [ ] **Step 6 — Model Fit:** For each prompt x model running it, check against that maker's current guide. Check the emphasis level (all-caps, "CRITICAL", "must", alarm emoji), because some current guides say forceful wording now makes the model over-apply a rule. First sort each capitalised absolute (or bold / emoji emphasis), by the rule it governs, into invariant (safety, permission, required field, irreversible action) or judgement call, and judge only the judgement calls. Then check: reasoning controls (the effort or thinking setting at the call site, against a hand-written "think step by step" on a model with built-in reasoning); verbosity and length controls; sampling parameters the model ignores or rejects (e.g., temperature on a reasoning model); prefill used where the model or API no longer supports it; and a workaround written for an older model that is still present after a model change. **If** a prompt runs on models from several makers → it uses a practice every guide supports, or it is a finding. **Done when:** `Model Fit` has a row per prompt x model: check · guide line · verdict.
|
|
92
|
+
- [ ] **Step 7 — Tools and Schemas:** For each tool or output schema a prompt offers, check that: the description says what it does, when to use it and when not to; each parameter's meaning, unit, format and allowed values are given; the names are unambiguous; no two tools are ones a model could confuse; and error text returned to the model says how to recover. Capability and bounds belong to `bkit-audit-llm`. **If** there are no tools or schemas → skip with evidence. **Done when:** `Tools and Schemas` has a row per tool / schema, or the skip.
|
|
93
|
+
- [ ] **Step 8 — Efficiency:** For each prompt, record: the token count of the fixed part (naming the tool); text duplicated across prompts that one shared fragment could hold; whether fixed content comes before variable content where the provider caches prompt prefixes; and text that no instruction or example needs. Spend beyond the per-call count belongs to `bkit-audit-cost`. **Done when:** `Efficiency` has a row per prompt: tokens · duplication · cache order · dead text.
|
|
94
|
+
- [ ] **Step 9 — Deliberate Choices:** For every departure from a guide found in Steps 4-8, check `docs/decisions.jsonl`, prompt comments, and the previous reports' `Deliberate Choices`. **If** it is recorded with a reason → list it once, not as a finding. Re-raise it only when the guide changed after that reason was written. **If** it is unrecorded → mark it adopt (a finding), reject (saying why, and proposing a `docs/decisions.jsonl` row under `Process Improvements`) or not applicable. Each finding names the eval that would confirm the rewrite (`bkit-audit-llm` `Evals`). **If** there is none → write `unverified`, and propose the golden case to `bkit-audit-llm`. **Done when:** `Deliberate Choices` has a row per departure: practice · decision source or verdict.
|
|
95
|
+
- [ ] **Step 10 — Standards:** Confirm the current version of each anchor guide, and read what changed since the previous report's version. Give `Standards Coverage` one row per guide recommendation that applies to a prompt in `Inventory`, each marked checked (naming the step), not applicable (saying why) or finding. Mark each recommended practice the project does not apply as adopt (with a proposed step), reject (saying why) or not applicable. **Done when:** no row is empty.
|
|
96
|
+
- [ ] **Step 11 — Anything Else:** (a) Give a one-line verdict on each change since the previous report's commit that touches prompts, call-site model settings, tool or schema descriptions, or parsers of model output. (b) In a bounded pass of about 30 minutes, note what a senior prompt engineer would flag that no step asks about. Read the maker changelogs and model release notes since the previous run, and ask what no step would catch. **Done when:** `Beyond the Steps` holds both passes, or says `none`. **If** one class of issue is seen on 2 runs → propose a step for it in `Process Improvements`.
|
|
111
97
|
|
|
112
98
|
### 🔒 Gate 2: Probes Check
|
|
113
99
|
|
|
114
|
-
**
|
|
115
|
-
|
|
116
|
-
- [ ] **
|
|
117
|
-
- [ ] **
|
|
118
|
-
- [ ] **
|
|
119
|
-
- [ ] **
|
|
120
|
-
- [ ] **Gate 2
|
|
100
|
+
- [ ] **Steps complete:** every step is `[x]`, or skipped with evidence that its surface is absent.
|
|
101
|
+
- [ ] **Evidence:** every finding cites `file:line`, the guide line it departs from (URL and date read), and the tool behind it.
|
|
102
|
+
- [ ] **No payloads:** each finding quotes at most one line of prompt text.
|
|
103
|
+
- [ ] **No personal data:** no personal data or model completion is in the report.
|
|
104
|
+
- [ ] **Read-only:** no model generation call was made.
|
|
105
|
+
- [ ] **Prompts unchanged:** no prompt or config changed.
|
|
106
|
+
- [ ] **Gate 2 — Verified:** every item above holds.
|
|
121
107
|
|
|
122
108
|
## Findings
|
|
123
109
|
|
|
@@ -129,14 +115,14 @@ Verify only when applicable.
|
|
|
129
115
|
| `MEDIUM` | Rule with no reason where the guide asks for one; examples missing where format matters, or contradicting instructions; prompt on several makers' models relying on one maker's behaviour; fixed content after variable content where the provider caches; text duplicated across prompts; dead instruction; departure from a guide not recorded |
|
|
130
116
|
| `LOW` | Wording; token waste with no behaviour change; non-write tool description gaps |
|
|
131
117
|
|
|
132
|
-
|
|
118
|
+
Within a severity, list write paths first, then prompts whose model changed. A departure recorded in `docs/decisions.jsonl` with a reason is not a finding.
|
|
133
119
|
|
|
134
120
|
<!-- prettier-ignore -->
|
|
135
121
|
| ID | Severity | Prompt | Location | Evidence | Expected | Verify |
|
|
136
122
|
| --- | --- | --- | --- | --- | --- | --- |
|
|
137
123
|
| PENDING | PENDING | PENDING | PENDING | PENDING | PENDING | PENDING |
|
|
138
124
|
|
|
139
|
-
|
|
125
|
+
**If** the run finds nothing → write one row: `None`. `Verify` = the eval that confirms the fix, or `unverified`.
|
|
140
126
|
|
|
141
127
|
## Report
|
|
142
128
|
|
|
@@ -209,18 +195,17 @@ PENDING
|
|
|
209
195
|
|
|
210
196
|
### 🔒 Gate 3: Report Check
|
|
211
197
|
|
|
212
|
-
**
|
|
213
|
-
|
|
214
|
-
- [ ] **
|
|
215
|
-
- [ ] **
|
|
216
|
-
- [ ] **Series:** `Inventory` and `Deliberate Choices` diffed against previous report's, or marked baseline.
|
|
217
|
-
- [ ] **Guides:** every `Model Fit` verdict names the guide and date it was judged against.
|
|
218
|
-
- [ ] **Writes:** only this report
|
|
219
|
-
- [ ] **Process Improvements:** `Universal`
|
|
220
|
-
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one
|
|
221
|
-
- [ ] **
|
|
222
|
-
|
|
223
|
-
> `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.
|
|
198
|
+
- [ ] **No placeholders:** no `PENDING` is left.
|
|
199
|
+
- [ ] **Summary:** `Summary` gives the count per severity.
|
|
200
|
+
- [ ] **Prompts read:** `Summary` names the prompts read.
|
|
201
|
+
- [ ] **Guide versions:** `Summary` gives the guide versions read.
|
|
202
|
+
- [ ] **Series:** `Inventory` and `Deliberate Choices` are diffed against the previous report's, or the run is marked baseline.
|
|
203
|
+
- [ ] **Guides:** every `Model Fit` verdict names the guide and the date it was judged against.
|
|
204
|
+
- [ ] **Writes:** this run changed only this report, the template's `Project Instructions` and its own `docs/failures.jsonl` rows.
|
|
205
|
+
- [ ] **Process Improvements:** `Universal` and `Project` are both filled.
|
|
206
|
+
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID is in exactly one `Suggested Issues` row.
|
|
207
|
+
- [ ] **Next Step:** every `Suggested Issues` row has a `Next Step`.
|
|
208
|
+
- [ ] **Gate 3 — Verified:** every item above holds.
|
|
224
209
|
|
|
225
210
|
<!-- bkit:end -->
|
|
226
211
|
|