@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
package/.bkit/core/AGENTS.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
{{BKIT_MANAGED_MARKER}}
|
|
6
6
|
|
|
7
|
-
- **Rules:** Read `.agents/rules.md` → follow all rules.
|
|
7
|
+
- **Rules file:** Read `.agents/rules.md` → follow all rules.
|
|
8
8
|
|
|
9
9
|
> [!CAUTION]
|
|
10
10
|
> This file is a **workflow router only**. It does not execute workflows.
|
|
@@ -13,42 +13,36 @@
|
|
|
13
13
|
|
|
14
14
|
## Route
|
|
15
15
|
|
|
16
|
-
### Step 1 —
|
|
16
|
+
### Step 1 — Find issue ID in prompt
|
|
17
17
|
|
|
18
|
-
**If** prompt contains `<LINEAR_ISSUE>` XML block (Linear integration)
|
|
19
|
-
|
|
20
|
-
- `ISSUE_ID` ← `<id>` tag value (e.g. `LIN-123` or team-specific prefix)
|
|
21
|
-
- `DESCRIPTION` ← `<description>` tag content
|
|
22
|
-
- `LABELS` ← all `<label name="...">` values in `<labels>` block
|
|
23
|
-
- `COMMENTS` ← all `<comment>` entries from `<comment_thread>` + `<other_comment_threads>`, sorted newest-first by `created` attribute
|
|
18
|
+
**If** prompt contains `<LINEAR_ISSUE>` XML block (Linear integration) → `ISSUE_ID` ← `<id>` tag value (e.g. `LIN-123` or team-specific prefix).
|
|
24
19
|
|
|
25
20
|
**Else** scan entire session prompt for issue ID — try patterns in order, first match wins:
|
|
26
21
|
|
|
27
|
-
1. `#\d+` → GitHub issue number (e.g. `#123`); strip `#`, set `ISSUE_ID` = `123`
|
|
28
|
-
2. `[A-Z][A-Z0-9]*-\d+` → prefixed issue ID (e.g. Linear `LIN-123`, Jira `PROJ-123
|
|
29
|
-
3. bare `\d+` → numeric fallback (GitHub provider only; ambiguous — prefer `#\d+`)
|
|
22
|
+
1. `#\d+`, `owner/repo#\d+` or a GitHub issue URL (`…/{owner}/{repo}/issues/\d+`) into this repo (`owner/repo` of the `origin` remote) → GitHub issue number (e.g. `#123`); strip `#`, set `ISSUE_ID` = `123`
|
|
23
|
+
2. `[A-Z][A-Z0-9]*-\d+` carrying the `package.json` `bkit.tracker.linear.team` / `bkit.tracker.jira.project` prefix, a Linear issue URL (`linear.app/…/issue/ID`) with that prefix, or a Jira browse URL (`…/browse/ID`) on the `bkit.tracker.jira.site` host with that prefix → prefixed issue ID (e.g. Linear `LIN-123`, Jira `PROJ-123`)
|
|
30
24
|
|
|
31
|
-
|
|
25
|
+
A bare number with no `#` is not an issue ID; neither is a bare key with no team / project set, nor a tracker URL into another repo, team or site; the run is issue-less (same rule as `bkit fids parse`).
|
|
32
26
|
|
|
33
|
-
|
|
27
|
+
Set `LABELS`, `DESCRIPTION` = empty.
|
|
34
28
|
|
|
35
|
-
|
|
29
|
+
**If** no `ISSUE_ID` → keep `ISSUE_ID` empty → Step 2.
|
|
36
30
|
|
|
37
|
-
|
|
31
|
+
### Step 2 — Route from user message
|
|
38
32
|
|
|
39
|
-
|
|
33
|
+
In the bottom-most `USER:` entry in `# Message history` scan for commands (case-insensitive: Ship, Debug, Build, Plan, Design) → first match → `COMMAND`. **If** matched → skip Step 3.
|
|
40
34
|
|
|
41
|
-
|
|
35
|
+
### Step 3 — Route from issue labels
|
|
42
36
|
|
|
43
|
-
|
|
37
|
+
Only if `ISSUE_ID` non-empty: read current issue labels and description via the configured tracker MCP (GitHub: `mcp__github__issue_read({ method: "get", ... })`; Linear: `mcp__linear__get_issue({ id: "{ISSUE_ID}" })`; Jira: `mcp__jira__getJiraIssue({ cloudId: "<package.json bkit.tracker.jira.site>", issueIdOrKey: "{ISSUE_ID}", view: "evidence" })` → `fields.labels`) → `LABELS`, `DESCRIPTION`. **If** the MCP read fails and the prompt holds a `<LINEAR_ISSUE>` block → fallback: `LABELS` ← all `<label name="...">` values in its `<labels>` block, `DESCRIPTION` ← its `<description>` tag content.
|
|
44
38
|
|
|
45
|
-
|
|
39
|
+
Scan `LABELS` for commands (Ship, Debug, Build, Plan, Design) → first match → `COMMAND`.
|
|
46
40
|
|
|
47
|
-
### Step
|
|
41
|
+
### Step 4 — No match
|
|
48
42
|
|
|
49
|
-
Emit: `Workflow not found for issue {ISSUE_ID}. Valid commands: Design / Plan / Build / Debug / Ship.`
|
|
43
|
+
Emit: `Workflow not found for issue {ISSUE_ID}. Valid commands: Design / Plan / Build / Debug / Ship.` (drop `for issue {ISSUE_ID}` when `ISSUE_ID` empty) → **STOP**; do not post a tracker comment.
|
|
50
44
|
|
|
51
|
-
### Step
|
|
45
|
+
### Step 5 — Execute command
|
|
52
46
|
|
|
53
47
|
Read and execute the matched command file for the current IDE.
|
|
54
48
|
|
|
@@ -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 widen, narrow, or edit the CI accessibility gate or its allowlists; full-rule and platform audits are report-only.
|
|
23
15
|
> - never record an assistive-technology participant's name, contact, or health detail.
|
|
24
16
|
|
|
@@ -34,7 +26,7 @@ Target failure: **a gate that stays green while the unchecked surface is where t
|
|
|
34
26
|
|
|
35
27
|
**Cadence:** quarterly. Extra pass when palette, shared control, or route layout changes. Assistive-technology user sessions: once a year, own date; record next due.
|
|
36
28
|
|
|
37
|
-
**Anchor Standards:**
|
|
29
|
+
**Anchor Standards:**
|
|
38
30
|
|
|
39
31
|
- WCAG 2.2 (W3C Recommendation; same text ISO/IEC 40500). Record dated update.
|
|
40
32
|
- EN 301 549. Record version procurement regime cites.
|
|
@@ -65,23 +57,15 @@ Target failure: **a gate that stays green while the unchecked surface is where t
|
|
|
65
57
|
|
|
66
58
|
### Pre-Flight / Dependencies
|
|
67
59
|
|
|
68
|
-
**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.
|
|
69
|
-
|
|
70
|
-
**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.
|
|
71
|
-
|
|
72
60
|
#### Core
|
|
73
61
|
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
- [ ] **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.
|
|
62
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
77
63
|
- [ ] **Gate Source:** Steps 2, 4, 13 — automated-gate files readable. Fallback: no gate while UI exists = finding; later steps run without snapshot.
|
|
78
64
|
- [ ] **Checker:** Steps 5, 6 — full rule set, e.g. axe-core, pa11y, Accessibility Insights. Fallback: manual steps only; automated rows `Not Checked`.
|
|
79
65
|
- [ ] **Web:** Step 15 — fetch anchor standards. Fallback: versions recorded as unread.
|
|
80
66
|
|
|
81
67
|
#### Conditional
|
|
82
68
|
|
|
83
|
-
Verify only when applicable.
|
|
84
|
-
|
|
85
69
|
- [ ] **Browser Runner:** Web UI → Steps 5, 6, 8, 11 — e.g. Playwright, Cypress. Fallback: manual on named route sample; rest `Not Checked`.
|
|
86
70
|
- [ ] **Assistive Tech:** Manual pass → Step 8 — e.g. NVDA, JAWS, VoiceOver, TalkBack, Voice Control, Voice Access, Switch Control. Fallback: each missing pair → `Not Checked`.
|
|
87
71
|
- [ ] **Native Audits:** Native UI → Step 12 — e.g. Xcode Accessibility Inspector, `performAccessibilityAudit()`, Android Accessibility Scanner, Espresso Accessibility Test Framework. Fallback: `Not Checked`.
|
|
@@ -90,14 +74,12 @@ Verify only when applicable.
|
|
|
90
74
|
|
|
91
75
|
### 🔒 Gate 1: Prerequisites Check
|
|
92
76
|
|
|
93
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
94
|
-
|
|
95
77
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
96
|
-
- [ ] **Gate 1
|
|
78
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
97
79
|
|
|
98
80
|
### Probe Steps
|
|
99
81
|
|
|
100
|
-
- [ ] **Step 1 — Previous Run:**
|
|
82
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
101
83
|
- [ ] **Step 2 — Gate:** Open gate specs and helpers. Record in `Gate`: checker rule set; route list + ready/settle selectors per route; each allowlist; gate-pinned vs audit-run checker version; rules checker changelog adds since previous report version (pinned old version under-reports newer WCAG 2.2 rules). Scope everything below against snapshot. **Done when:** snapshot in `Gate`, or no gate recorded.
|
|
102
84
|
- [ ] **Step 3 — Laws:** Which laws apply = owner decision; record or unmade (`Project Instructions` names questions). Law requiring public accessibility statement, service info, feedback channel → check they exist. Statement wording vs behaviour → `bkit-audit-privacy`. **Done when:** `Laws` row per regime: applies · why · statement.
|
|
103
85
|
- [ ] **Step 4 — Allowlists:** Per-offender keys, never runtime hash, never rule downgrade or route exclusion. Honest only if each entry re-read. Per entry: offender still there, reason still true, fixable now? No expiry/owner = permanent exemption = finding. Policy "new entry = finding, not fix" (`Project Instructions`) → new entry = finding. Stale (offender gone, key remains) = finding. **Done when:** `Allowlists` row per entry: still present · reason true · expiry or owner · verdict. Empty → one row `none`, key shape noted.
|
|
@@ -113,10 +95,10 @@ Verify only when applicable.
|
|
|
113
95
|
- Status messages (4.1.3): toasts, async state, save confirmations, form errors via `aria-live` or `role="status"` without moving focus; self-dismissing toast readable duration or pausable (2.2.1).
|
|
114
96
|
- Page structure: skip link to main (2.4.1); unique title per route/locale (2.4.2); link text names destination (2.4.4).
|
|
115
97
|
- Colour alone (1.4.1): colour-only distinction also has initials, icon, or pattern — contrast tools miss this.
|
|
116
|
-
- Non-text contrast (1.4.11): every theme — focus, borders, outlines, toggles, icons
|
|
98
|
+
- Non-text contrast (1.4.11): every theme — focus, borders, outlines, toggles, icons >=3:1 vs adjacent; tools often skip.
|
|
117
99
|
- Forced colours / increased contrast: `forced-colors: active`, platform Increase Contrast — custom controls and focus rings usual failures.
|
|
118
100
|
- Zoom/reflow: 200% zoom, 320px viewport — no horizontal scroll or lost content (1.4.10).
|
|
119
|
-
- Text spacing (1.4.12): line-height 1.5, paragraph spacing
|
|
101
|
+
- Text spacing (1.4.12): line-height 1.5, paragraph spacing 2x, letter 0.12em, word 0.16em — nothing clipped/overlapping.
|
|
120
102
|
- Content on hover/focus (1.4.13): Esc dismiss, hover without vanish, persist until dismissed.
|
|
121
103
|
- Orientation/text size: no orientation lock unless essential (1.3.4); text 200% without loss (1.4.4), separate from 320px reflow.
|
|
122
104
|
- Reduced motion: `prefers-reduced-motion` on animation surfaces.
|
|
@@ -124,7 +106,7 @@ Verify only when applicable.
|
|
|
124
106
|
|
|
125
107
|
**Done when:** `Manual` row per pass: met / finding / not checked (which pair).
|
|
126
108
|
|
|
127
|
-
- [ ] **Step 9 — Sessions:** Yearly, 3
|
|
109
|
+
- [ ] **Step 9 — Sessions:** Yearly, 3-5 daily assistive-technology users on primary flow. Expert review misses their strategies; many screen-reader users navigate by headings first (WebAIM survey — record figure). Record last session date and next due. None yet → due now, not pass. **Done when:** `Sessions` holds last date, next due, barriers, or `due now`.
|
|
128
110
|
- [ ] **Step 10 — Additions:** WCAG 2.2 likeliest gaps:
|
|
129
111
|
- 2.5.7 Dragging Movements — every drag has single-pointer alternative.
|
|
130
112
|
- 2.4.11 Focus Not Obscured — sticky headers/footers can cover focus.
|
|
@@ -145,7 +127,7 @@ Verify only when applicable.
|
|
|
145
127
|
|
|
146
128
|
**Done when:** `Layout` row per check: met / finding.
|
|
147
129
|
|
|
148
|
-
- [ ] **Step 12 — Native:** Native UI → shared controls: name, role, state (e.g. `accessibilityLabel`, `accessibilityRole`, `accessibilityState`). Screen reader on same primary flow. Platform-split files (e.g. RN `.native`/`.web`) not diverged in labelling. Shared component fixed web bug → confirm native twin (consumer refs both ways; text search — language server under-reports). Platform automated audits report-only per primary-flow screen: iOS Accessibility Inspector or `performAccessibilityAudit()` in XCUITest; Android Accessibility Scanner or Espresso Accessibility Test Framework. Text scaling: largest accessibility text size + 200% font max (large-text scaling non-linear, e.g. Android 14+). Content not clipped/overlapped. Search text-scaling opt-outs on content text (e.g. RN `allowFontScaling={false}`, low `maxFontSizeMultiplier`; SwiftUI capped `dynamicTypeSize`; Android text sized in `dp` not `sp`) — finding unless reason recorded. Map to platform nutrition-label criteria (`Project Instructions`); declare only if common tasks completable with that feature; larger text needs
|
|
130
|
+
- [ ] **Step 12 — Native:** Native UI → shared controls: name, role, state (e.g. `accessibilityLabel`, `accessibilityRole`, `accessibilityState`). Screen reader on same primary flow. Platform-split files (e.g. RN `.native`/`.web`) not diverged in labelling. Shared component fixed web bug → confirm native twin (consumer refs both ways; text search — language server under-reports). Platform automated audits report-only per primary-flow screen: iOS Accessibility Inspector or `performAccessibilityAudit()` in XCUITest; Android Accessibility Scanner or Espresso Accessibility Test Framework. Text scaling: largest accessibility text size + 200% font max (large-text scaling non-linear, e.g. Android 14+). Content not clipped/overlapped. Search text-scaling opt-outs on content text (e.g. RN `allowFontScaling={false}`, low `maxFontSizeMultiplier`; SwiftUI capped `dynamicTypeSize`; Android text sized in `dp` not `sp`) — finding unless reason recorded. Map to platform nutrition-label criteria (`Project Instructions`); declare only if common tasks completable with that feature; larger text needs >=200%. Record honest labels; declaring → `bkit-audit-app-store`. **Done when:** `Native` holds label parity, audit rows, scaling, label map, or no native UI in `Checked`.
|
|
149
131
|
- [ ] **Step 13 — Gate Proof:** Vacuous-assertion class: checker on unmounted subtree passes; unmatched locator can pass assertion. Confirm gate self-checks fail closed — injected failure reported, injected undersize proves rule ran (not merely no violation when alternatives pass isolated node). Each route settle selector resolves after guarded content renders, including post-skeleton mount. Refactored route may measure skeleton again. **Done when:** self-check results in `Gate`, or no gate recorded.
|
|
150
132
|
- [ ] **Step 14 — Criteria:** Automated rules cover minority of WCAG success criteria; `Manual` + `Additions` = chosen subset. Primary flows web + native: pass/fail/N/A every WCAG 2.2 Level A and AA criterion. Reuse earlier steps (name step); hand-check rest. Each fail = finding. **Done when:** `Criteria` has no empty criterion.
|
|
151
133
|
- [ ] **Step 15 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: row per anchor + per WCAG 2.2 A/AA criterion → checked (name step; reuse `Criteria`) / 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.
|
|
@@ -153,13 +135,11 @@ Verify only when applicable.
|
|
|
153
135
|
|
|
154
136
|
### 🔒 Gate 2: Probes Check
|
|
155
137
|
|
|
156
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
157
|
-
|
|
158
138
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
159
139
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
160
140
|
- [ ] **Gate untouched:** checker invocation, route list, and allowlists byte-identical to committed.
|
|
161
141
|
- [ ] **No participants:** no name, contact, or health detail of an assistive-technology user.
|
|
162
|
-
- [ ] **Gate 2
|
|
142
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
163
143
|
|
|
164
144
|
## Findings
|
|
165
145
|
|
|
@@ -171,7 +151,7 @@ Verify only when applicable.
|
|
|
171
151
|
| `MEDIUM` | A or AA fail off the primary flows; email defect; native name, role, or state missing on a shared control; text clipped at 200%, at 320px, or in a long locale; allowlist entry whose reason is stale or has no expiry |
|
|
172
152
|
| `LOW` | Meets AA and misses a house convention (e.g. 44px where 2.5.8's 24px holds); wording drift that changes no criterion |
|
|
173
153
|
|
|
174
|
-
|
|
154
|
+
Within a severity: blocked primary tasks first.
|
|
175
155
|
|
|
176
156
|
<!-- prettier-ignore -->
|
|
177
157
|
| ID | Severity | Location | Evidence | Expected |
|
|
@@ -267,17 +247,13 @@ PENDING
|
|
|
267
247
|
|
|
268
248
|
### 🔒 Gate 3: Report Check
|
|
269
249
|
|
|
270
|
-
|
|
271
|
-
|
|
272
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
250
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
273
251
|
- [ ] **Summary:** names count per severity and the checker version.
|
|
274
252
|
- [ ] **Sessions:** states the date of the last assistive-technology session and when the next is due.
|
|
275
|
-
- [ ] **Writes:** only this report
|
|
276
|
-
- [ ] **Process Improvements:** `Universal`
|
|
253
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway worktrees / remote targets removed.
|
|
254
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
277
255
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
278
|
-
- [ ] **Gate 3
|
|
279
|
-
|
|
280
|
-
> `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.
|
|
256
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
281
257
|
|
|
282
258
|
<!-- bkit:end -->
|
|
283
259
|
|
|
@@ -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 print or copy a token, key, or secret value; names and presence only.
|
|
23
15
|
> - never run `bkit install` / `bkit upgrade`; bkit commands = `bkit check`, `bkit doctor` only.
|
|
24
16
|
> - NEVER run a hook, script, or tool that writes, commits, pushes, or calls a remote write API; syntax checks and read-only modes only.
|
|
@@ -43,7 +35,7 @@ bkit ships three folders. Path inside a folder = path it lands at in the repo.
|
|
|
43
35
|
|
|
44
36
|
**Cadence:** monthly. Extra pass after `bkit upgrade`, after adopting or dropping a template, and after adding an agent host.
|
|
45
37
|
|
|
46
|
-
**Anchor Standards:** record bkit version and date read.
|
|
38
|
+
**Anchor Standards:** record bkit version and date read.
|
|
47
39
|
|
|
48
40
|
- bkit, at the installed version: `.bkit/templates.md` (Contract, placeholders, Context-fetch blocks), `.bkit/README.md` § File ownership and § Ongoing CLI, `.bkit/install.md`; release notes since pinned version.
|
|
49
41
|
- Config reference of each tool behind an adopted template (e.g. Husky, lint-staged, Vale, Prettier, Renovate, Dependabot, Trivy, GitHub Actions workflow syntax, direnv); record version read.
|
|
@@ -74,58 +66,46 @@ bkit ships three folders. Path inside a folder = path it lands at in the repo.
|
|
|
74
66
|
|
|
75
67
|
### Pre-Flight / Dependencies
|
|
76
68
|
|
|
77
|
-
**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.
|
|
78
|
-
|
|
79
|
-
**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.
|
|
80
|
-
|
|
81
69
|
#### Core
|
|
82
70
|
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
- [ ] **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.
|
|
86
|
-
- [ ] **Checkout:** Steps 2–11 — repo with `.bkit/version`. Fallback: none; absent → `N/A` and STOP.
|
|
71
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
72
|
+
- [ ] **Checkout:** Steps 2-11 — repo with `.bkit/version`. Fallback: none; absent → `N/A` and STOP.
|
|
87
73
|
- [ ] **Package:** Step 2 — installed package root (e.g. `node_modules/@cbartens/bkit/.bkit/`, resolved via the package manager). Fallback: unpack the pinned version (e.g. `npm pack @cbartens/bkit@<pinnedVersion>` into a throwaway dir); else inventory from `.bkit/templates/` + `canonicalHashes` only, `core/` + `shared/` unwritten files `Not Checked`.
|
|
88
74
|
- [ ] **bkit CLI:** Steps 4, 5 — `bkit check`, `bkit doctor` (or `pnpm bkit …`). Fallback: hash written files against `canonicalHashes` by hand; advisories `Not Checked`.
|
|
89
75
|
- [ ] **Registry:** Step 3 — latest version and release notes (e.g. `npm view @cbartens/bkit version`, release page). Fallback: pinned vs installed only; currency `Not Checked`.
|
|
90
76
|
|
|
91
77
|
#### Conditional
|
|
92
78
|
|
|
93
|
-
Verify only when applicable.
|
|
94
|
-
|
|
95
79
|
- [ ] **CI Host Read:** Repo has CI → Steps 8, 9 — workflow list, job names, recent runs, artifact names (e.g. `gh workflow list`, `gh run list`, `gh run view --json jobs`). Fallback: workflow files only; lane matching `Not Checked`.
|
|
96
|
-
- [ ] **Template Tools:**
|
|
80
|
+
- [ ] **Template Tools:** >=1 adopted template → Step 9 — each tool behind one, installed version (e.g. `npx husky --version`, `vale --version`, `npx lint-staged --version`). Fallback: version from lockfile; runs `Not Checked`.
|
|
97
81
|
- [ ] **Machine Config:** Audit runs on a developer machine → Step 9 — local git config (e.g. `git config core.hooksPath`), direnv allow state. Fallback: repo-level only; machine wiring `Not Checked`.
|
|
98
82
|
|
|
99
83
|
### 🔒 Gate 1: Prerequisites Check
|
|
100
84
|
|
|
101
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
102
|
-
|
|
103
85
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
104
|
-
- [ ] **Gate 1
|
|
86
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
105
87
|
|
|
106
88
|
### Probe Steps
|
|
107
89
|
|
|
108
|
-
- [ ] **Step 1 — Previous Run:**
|
|
90
|
+
- [ ] **Step 1 — Previous Run:** Carry each `Adoption` verdict forward with its age. **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
109
91
|
- [ ] **Step 2 — Inventory:** List every file in the package's `core/`, `shared/`, `templates/`. Landing path = path inside the folder; `core/engine/`, `core/workflows/`, `core/prompts/` → no landing (workflows + prompts → Step 5 host copies). Join: package file · landing path present · in `canonicalHashes` · repo `.bkit/templates/` copy matches package `templates/`. Kind per file: whole file / managed block / owned keys / template. Findings: `core/` or `shared/` file with landing path absent; `canonicalHashes` entry the package no longer ships; repo `.bkit/templates/` differing from package. Group a folder into one row only when every file shares one verdict. **Done when:** `Inventory` row per shipped file or uniform folder: folder · landing path · kind · present · recorded.
|
|
110
|
-
- [ ] **Step 3 — Version:** `pinnedVersion` vs installed package vs registry latest; pinned
|
|
92
|
+
- [ ] **Step 3 — Version:** `pinnedVersion` vs installed package vs registry latest; pinned != installed = package bumped without `bkit upgrade`. Behind → release count; release-note changes touching this repo; template paths changed since pinned version. **Done when:** `Version` names all three versions and every relevant release-note change.
|
|
111
93
|
- [ ] **Step 4 — Check and Doctor:** `bkit check`: exit code, each drift line → cause. `bkit doctor`: each advisory → adopt / reject (why) / not applicable; previous report's reject carried forward, re-raised only when the advisory text changed. **Done when:** `Check and Doctor` row per drift line and advisory.
|
|
112
94
|
- [ ] **Step 5 — Hosts:** Agent hosts in use (repo config dirs, team use; newest `bkit-audit-agents` `Hosts` as cross-check, not source) vs bkit hosts installed. Per installed host: one agent copy per `core/prompts/` source, one command copy per `core/workflows/` source, every `core/` hook file present, executable, and wired in that host's settings. Findings: host in use with no bkit install (agents there run without bkit gates); missing or extra copy; hook file present but unwired, or wired but absent. Whether hooks fire and agree across hosts → `bkit-audit-agents`. **Done when:** `Hosts` row per host: in use · installed · agent copies · command copies · hooks wired.
|
|
113
95
|
- [ ] **Step 6 — Written Files:** (a) Every `bkit:start` / `bkit:end` block and owned key: untouched (Step 4 drift). Hand edit → move below `bkit:end` / to `Project Instructions`; bkit-shipped defect → upstream bkit fix. (b) Files bkit shares with you (`shared/docs/*.md`, `AGENTS.md`, `CLAUDE.md`, `.agents/*.md`, `.gitignore`, `.gitattributes`, settings, tool-server config): your part present for every block that expects one — a doc holding only bkit's block is unadopted. `.bkit/.env.example` → `.bkit/.env` present, git-ignored, every listed key set (names only). Tracker or tool-server entry bkit wrote → credential env var it names is set. Whether your part is true → `bkit-audit-documentation`. **Done when:** `Written Files` row per shared file: block untouched · your part present · verdict.
|
|
114
96
|
- [ ] **Step 7 — Audits:** Per `docs/templates/bkit-audit-*.md`: `**Applies when:**` met yes / no (evidence); `**Cadence:**`; newest report under `docs/audits/` by commit date (never run = due; same rule as `bkit-utility-update-roadmap`). `N/A` report with evidence = run. Findings: applies and never run; overdue past one cadence; `Process Improvements` `Project` edits proposed in a report and absent from that template's `Project Instructions`. **Done when:** `Audits` row per template: applies · cadence · last run · overdue by · verdict.
|
|
115
|
-
- [ ] **Step 8 — Adoption:** Per file in package `templates/`, joined to `.bkit/templates.md` § Contract (file missing from Contract → upstream bkit doc fix): adopted (copy at landing path, or at the destination the Contract names) / not adopted. Not adopted → `gap` (fits this stack, nothing else does the job) / `covered` (name the tool that does) / `not applicable` (evidence, e.g. no GitHub Actions, no markdown docs). Two templates for one job (e.g. Renovate and Dependabot) → one adopted, or `bkit.
|
|
116
|
-
- [ ] **Step 9 — Templates:** Per adopted template: (a) Filled: no raw `{{…}}` placeholder; default branch and runner real; no stub sentinel left. (b) Reconciled: `diff .bkit/templates/<path> <path>` → each difference adopt / reject (why); placeholder lines differ by design. (c) Merged: package changed the template after the copy's last change (Step 3, `git log` on `.bkit/templates/<path>`) → merged / rejected (why) / pending. (d) Wired: tool behind it installed, and invoked where the template expects — e.g. hook manager installed by a `prepare` script, hooks executable, `core.hooksPath` set; `pre-commit` calls lint-staged; prose linter styles synced and its config loads them; scanner plugin path resolves; tool-server snippet merged into the host's server config; secrets config names real stores; cloud workflow waits on a workflow `name:` that exists; CI template's job names are the ones the repo requires. (e) Runs: one read-only invocation where one exists (e.g. `sh -n` on a hook, `prettier --check`, `vale` on one doc, `actionlint` on a workflow). (f) Ignored: every repo-wide gate (formatter, prose linter, scanner, linter, type checker) skips `.bkit/templates/`. Context-fetch block → job regex and artifact name match exactly the lane it names (CI Host Read); widened regex catching another lane = finding. **Done when:** `Templates` row per adopted template: (a)
|
|
97
|
+
- [ ] **Step 8 — Adoption:** Per file in package `templates/`, joined to `.bkit/templates.md` § Contract (file missing from Contract → upstream bkit doc fix): adopted (copy at landing path, or at the destination the Contract names) / not adopted. Not adopted → `gap` (fits this stack, nothing else does the job) / `covered` (name the tool that does) / `not applicable` (evidence, e.g. no GitHub Actions, no markdown docs). Two templates for one job (e.g. Renovate and Dependabot) → one adopted, or `bkit.dependencies.updater` recorded. Context-fetch: per context (`ci`, `diff`, `e2e`, `runtime`, `web`) the repo has a lane or provider for → block below `bkit:end` in `.agents/context.md`, or `<!-- context-fetch:none … -->` naming it; provider in use (dependency, config, CI step) with a shipped `templates/context/` file and no block → `gap`. Re-list every row each run; diff vs previous report: newly adopted, newly dropped, unchanged with age. **Done when:** `Adoption` row per template file and per context: adopted · verdict · evidence · age.
|
|
98
|
+
- [ ] **Step 9 — Templates:** Per adopted template: (a) Filled: no raw `{{…}}` placeholder; default branch and runner real; no stub sentinel left. (b) Reconciled: `diff .bkit/templates/<path> <path>` → each difference adopt / reject (why); placeholder lines differ by design. (c) Merged: package changed the template after the copy's last change (Step 3, `git log` on `.bkit/templates/<path>`) → merged / rejected (why) / pending. (d) Wired: tool behind it installed, and invoked where the template expects — e.g. hook manager installed by a `prepare` script, hooks executable, `core.hooksPath` set; `pre-commit` calls lint-staged; prose linter styles synced and its config loads them; scanner plugin path resolves; tool-server snippet merged into the host's server config; secrets config names real stores; cloud workflow waits on a workflow `name:` that exists; CI template's job names are the ones the repo requires. (e) Runs: one read-only invocation where one exists (e.g. `sh -n` on a hook, `prettier --check`, `vale` on one doc, `actionlint` on a workflow). (f) Ignored: every repo-wide gate (formatter, prose linter, scanner, linter, type checker) skips `.bkit/templates/`. Context-fetch block → job regex and artifact name match exactly the lane it names (CI Host Read); widened regex catching another lane = finding. **Done when:** `Templates` row per adopted template: (a)-(f) verdict each.
|
|
117
99
|
- [ ] **Step 10 — Standards:** Confirm anchor versions; read changes since previous report's version. `Standards Coverage`: one row per Contract row, per context-fetch file, and per tool reference read → checked (name step) / not applicable (why) / finding. Deprecated key or option in an adopted config per its tool reference → finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
|
|
118
100
|
- [ ] **Step 11 — Anything Else:** (a) Everything changed since previous report's commit touching bkit-written files, `.bkit/templates/`, adopted copies, `.agents/context.md`, or `package.json` `bkit.*` → one-line verdict each. (b) Bounded ~30 min pass: what a senior engineer adopting bkit flags that no step asks; read what happened since previous run (`bkit upgrade` output, new `docs/failures.jsonl` rows, `.bkit/friction.jsonl`) — 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`.
|
|
119
101
|
|
|
120
102
|
### 🔒 Gate 2: Probes Check
|
|
121
103
|
|
|
122
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
123
|
-
|
|
124
104
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
125
105
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
126
106
|
- [ ] **No secrets:** no token, key, or secret value anywhere in the report.
|
|
127
107
|
- [ ] **Repo untouched:** no template copied or edited, no bkit-written file changed, no `bkit install` / `bkit upgrade` run, no writing hook or script run.
|
|
128
|
-
- [ ] **Gate 2
|
|
108
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
129
109
|
|
|
130
110
|
## Findings
|
|
131
111
|
|
|
@@ -133,11 +113,11 @@ Verify only when applicable.
|
|
|
133
113
|
| Severity | Use |
|
|
134
114
|
| --- | --- |
|
|
135
115
|
| `CRITICAL` | Secret value in a tracked adopted copy or a tracked `.bkit/.env` (rotation → `bkit-audit-security`) |
|
|
136
|
-
| `HIGH` | `bkit check` failing; pinned
|
|
116
|
+
| `HIGH` | `bkit check` failing; pinned != installed; host in use with no bkit install; adopted template whose tool is not installed or never invoked; raw placeholder in an executed file (workflow, hook); cloud workflow waiting on a workflow name that does not exist; context-fetch block matching the wrong lane |
|
|
137
117
|
| `MEDIUM` | Template `gap`; edits inside a bkit managed block; unaddressed `bkit doctor` advisory; package change to an adopted template unmerged; unreviewed difference from the template; written doc holding only bkit's block; `.bkit/.env` key unset; audit that applies never run or overdue; repo-wide gate scanning `.bkit/templates/`; context with a lane and no block or opt-out; bkit behind with relevant fix |
|
|
138
118
|
| `LOW` | bkit behind, no relevant fix; shipped file missing from the Contract; two updaters adopted with one idle; naming drift, no behaviour change |
|
|
139
119
|
|
|
140
|
-
|
|
120
|
+
Within a severity: missing gates, then unwired copies, then drift.
|
|
141
121
|
|
|
142
122
|
<!-- prettier-ignore -->
|
|
143
123
|
| ID | Severity | Folder | Location | Evidence | Expected |
|
|
@@ -217,17 +197,13 @@ PENDING
|
|
|
217
197
|
|
|
218
198
|
### 🔒 Gate 3: Report Check
|
|
219
199
|
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
200
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
223
201
|
- [ ] **Summary:** names count per severity, bkit version, hosts, and templates adopted / `gap` / `covered` / `not applicable`.
|
|
224
202
|
- [ ] **Series:** `Adoption` diffed against previous report's, or marked baseline.
|
|
225
|
-
- [ ] **Writes:** only this report
|
|
226
|
-
- [ ] **Process Improvements:** `Universal`
|
|
203
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway package unpack removed.
|
|
204
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
227
205
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
228
|
-
- [ ] **Gate 3
|
|
229
|
-
|
|
230
|
-
> `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.
|
|
206
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
231
207
|
|
|
232
208
|
<!-- bkit:end -->
|
|
233
209
|
|
|
@@ -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 print or copy a token, key, or secret value; names, scopes, and presence only.
|
|
23
15
|
> - never run `bkit install` / `bkit upgrade`.
|
|
24
16
|
> - never call a tool-server tool; listing its tools only.
|
|
@@ -30,13 +22,13 @@
|
|
|
30
22
|
|
|
31
23
|
Each agent host reads its own permissions, hooks, tool servers, model picks; nobody reviews them as config. Broad allow rule lands in a one-line diff; local override lives on one laptop; tool server holds a write token nobody scoped. Target failure: **an agent does something one host's config would have blocked, because the host it ran in was configured differently** — e.g. force-push denied in one host, allowed in another; tool server with admin token where read suffices; hook wired but script not executable, never fires; issue body tells an agent with push rights to push, and nothing but prompt text stops it.
|
|
32
24
|
|
|
33
|
-
**Applies when:** repo carries config for
|
|
25
|
+
**Applies when:** repo carries config for >=1 coding agent (e.g. `AGENTS.md`, `.claude/`, `.cursor/`, `.codex/`, `.opencode/`, `.mcp.json`), or anyone works on it with one. None → one `N/A` row with evidence, never "clean".
|
|
34
26
|
|
|
35
27
|
**Cadence:** monthly. Extra pass after new agent host or tool server, bkit upgrade, or permission / hook / tool-server file change.
|
|
36
28
|
|
|
37
|
-
**Anchor Standards:**
|
|
29
|
+
**Anchor Standards:**
|
|
38
30
|
|
|
39
|
-
- OWASP Top 10 for Agentic Applications, 2026 (ASI01
|
|
31
|
+
- OWASP Top 10 for Agentic Applications, 2026 (ASI01-ASI10).
|
|
40
32
|
- Tool-server specification authorization and security best practices (e.g. Model Context Protocol); record the specification date read.
|
|
41
33
|
- OpenSSF Security-Focused Guide for AI Code Assistant Instructions.
|
|
42
34
|
- Each host's settings, permission, sandbox, and hook reference (e.g. Claude Code, Cursor, Codex, opencode); record date read.
|
|
@@ -73,58 +65,46 @@ Each agent host reads its own permissions, hooks, tool servers, model picks; nob
|
|
|
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
|
-
- [ ] **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.
|
|
85
|
-
- [ ] **Checkout:** Steps 2–10 — repo-level agent config. Fallback: none; no checkout → `N/A` and STOP.
|
|
70
|
+
- [ ] **Permissions:** blocked calls recorded
|
|
71
|
+
- [ ] **Checkout:** Steps 2-10 — repo-level agent config. Fallback: none; no checkout → `N/A` and STOP.
|
|
86
72
|
- [ ] **Effective Config:** Steps 2, 4, 6 — host's merged-config view where offered (e.g. `claude mcp list`, a host's permissions or MCP panel). Fallback: files + documented precedence by hand; effective state = hypothesis.
|
|
87
73
|
- [ ] **Web:** Steps 7, 11 — anchor standards, host references, live model catalogues. Fallback: versions recorded as unread; model pins `Not Checked`.
|
|
88
74
|
|
|
89
75
|
#### Conditional
|
|
90
76
|
|
|
91
|
-
Verify only when applicable.
|
|
92
|
-
|
|
93
77
|
- [ ] **Machine Config:** Audit runs on a developer machine → Steps 2, 4, 6, 8 — user-level and local-override files (e.g. `~/.claude/settings.json`, `.claude/settings.local.json`, `~/.cursor/mcp.json`, `~/.codex/config.toml`). Fallback: repo-level only; machine layers `Not Checked`.
|
|
94
78
|
- [ ] **Managed Policy:** Org-managed agent policy → Step 2 — policy file or admin console, read-only. Fallback: `Not Checked`; name who holds it.
|
|
95
79
|
- [ ] **Token Scopes:** Tool servers or hooks use credentials → Step 6 — scopes, value never printed (e.g. `gh auth status`, the `X-OAuth-Scopes` response header, provider token introspection). Fallback: scopes `Not Checked`.
|
|
96
80
|
|
|
97
81
|
### 🔒 Gate 1: Prerequisites Check
|
|
98
82
|
|
|
99
|
-
**Checkpoint.** Verify and check `[x]` all applicable boxes above, then continue to `Probe Steps` without asking.
|
|
100
|
-
|
|
101
83
|
- [ ] **Gaps named:** every missing item names its fallback and `Not Checked` entry.
|
|
102
|
-
- [ ] **Gate 1
|
|
84
|
+
- [ ] **Gate 1 — Verified:** All Core items checked. All applicable Conditional items checked.
|
|
103
85
|
|
|
104
86
|
### Probe Steps
|
|
105
87
|
|
|
106
|
-
- [ ] **Step 1 — Previous Run:**
|
|
107
|
-
- [ ] **Step 2 — Hosts and Layers:** Name machine and checkout. Hosts with repo config or in team use (e.g. Claude Code, Cursor, Codex, opencode). Per host: config file per layer (managed policy, user, repo shared, repo local override, flags / env); documented precedence. Findings: config for unused host; host in use with no repo config; local-override file tracked or not ignored. Fresh cloud checkout: no user / local layer → say so, not clean. **Done when:** `Hosts` row per host
|
|
88
|
+
- [ ] **Step 1 — Previous Run:** **Done when:** closure rate in `Previous Run`, or run marked baseline.
|
|
89
|
+
- [ ] **Step 2 — Hosts and Layers:** Name machine and checkout. Hosts with repo config or in team use (e.g. Claude Code, Cursor, Codex, opencode). Per host: config file per layer (managed policy, user, repo shared, repo local override, flags / env); documented precedence. Findings: config for unused host; host in use with no repo config; local-override file tracked or not ignored. Fresh cloud checkout: no user / local layer → say so, not clean. **Done when:** `Hosts` row per host x layer: file, present, tracked / ignored, precedence.
|
|
108
90
|
- [ ] **Step 3 — Instructions:** Per host: instruction files loaded at session start (e.g. `AGENTS.md`, `CLAUDE.md`, always-applied IDE rule files, per-directory files, imports). Findings: host reaching no shared rules; rule file / import → missing path. Contradictions, size → `bkit-audit-documentation`. **Done when:** `Instructions` row per host: files loaded, shared rules reached yes / no.
|
|
109
|
-
- [ ] **Step 4 — Permissions:** Per host
|
|
91
|
+
- [ ] **Step 4 — Permissions:** Per host x layer: allow / ask / deny, default approval mode, sandbox mode, fetch / network allowlist. Findings: wildcard shell allow; arbitrary-text interpreter allow (e.g. `bash -c`, `node -e`, `python -c`); deny overridden by broader higher-precedence allow; approval-bypass mode in shared config outside a sandbox; fetch allowlist wider than needed per host matching rules (e.g. apex vs subdomain). `Parity` matrix: action x host → blocker: deny rule / hook / sandbox / prompt prose only / nothing. Minimum actions: force push, history rewrite, branch delete, hook skip (e.g. `--no-verify`), merge or push to protected branch, publish / release, delete outside the working tree, credential-file read (e.g. `.env*`), fetch to unlisted host, tool-server write to a shared or production system. Findings: blocked in one host, open in another; blocked by prompt prose only. **Done when:** `Permissions` row per host x layer; `Parity` matrix with no empty cell.
|
|
110
92
|
- [ ] **Step 5 — Hooks:** Per host, each wired hook: event, matcher, command. Script exists, executable, interpreter present. Fire test: synthetic tool-call payload on stdin → record exit code / decision. Hook writing anything (telemetry, logs, state) → read, do not run. Findings: sole blocker for a `Parity` row fails open on crash / timeout / missing dependency; matcher misses a tool doing the same action (e.g. a tool server's shell tool). **Done when:** `Hooks` row per hook: wired, runnable, fires on fixture, fail mode.
|
|
111
|
-
- [ ] **Step 6 — Tool Servers:** Per host, each tool server (e.g. MCP): layer, transport (local command / remote URL), package pinned or floating (e.g. `npx -y pkg@latest`), publisher, credential source (env var name vs literal), credential scope vs need, toolsets enabled vs used, write tools pre-approved. List tools → hash names + descriptions. Findings: floating package; same server differing across hosts (token, toolsets, URL); server no workflow uses; hash changed since previous run with no version change. **Done when:** `Tool Servers` row per server
|
|
112
|
-
- [ ] **Step 7 — Agents and Models:** Per host: agent definitions, commands, skills / plugins. Per agent: tool allowlist vs role; model pin vs provider's live catalogue (never inferred from version digits). Per skill / plugin: source, pinned version, ships scripts. Findings: write tools on read-only role; dead pin; floating alias; same agent on different model classes across hosts, undocumented; unknown-source skill with scripts. **Done when:** `Agents` row per agent
|
|
93
|
+
- [ ] **Step 6 — Tool Servers:** Per host, each tool server (e.g. MCP): layer, transport (local command / remote URL), package pinned or floating (e.g. `npx -y pkg@latest`), publisher, credential source (env var name vs literal), credential scope vs need, toolsets enabled vs used, write tools pre-approved. List tools → hash names + descriptions. Findings: floating package; same server differing across hosts (token, toolsets, URL); server no workflow uses; hash changed since previous run with no version change. **Done when:** `Tool Servers` row per server x host, hashes recorded.
|
|
94
|
+
- [ ] **Step 7 — Agents and Models:** Per host: agent definitions, commands, skills / plugins. Per agent: tool allowlist vs role; model pin vs provider's live catalogue (never inferred from version digits). Per skill / plugin: source, pinned version, ships scripts. Findings: write tools on read-only role; dead pin; floating alias; same agent on different model classes across hosts, undocumented; unknown-source skill with scripts. **Done when:** `Agents` row per agent x host; skills listed.
|
|
113
95
|
- [ ] **Step 8 — Secrets:** Agent config + env files agents load (e.g. `.envrc`, tool-server env files, agent-tooling env file). Findings: literal token in tracked file (file and line, never value); env file not ignored; app credential in agent-tooling env. Agent read of credential files → Step 4 `Parity`. **Done when:** `Secrets` row per file.
|
|
114
96
|
- [ ] **Step 9 — Untrusted Input:** Per agent, command, skill, and automated agent run (CI job, scheduled or comment-triggered session) from Step 7: (a) text it reads that someone outside the team can write (e.g. issue / PR body and comments, fork commit messages, PR checkout files, CI logs, fetched pages, dependency READMEs and changelogs, tool-server results, inbound mail); (b) what it can do in the same session (shell, file write, push, merge, publish, tracker or tool-server write, outbound fetch), from Steps 4, 6, 7; (c) what stops a planted instruction: deny rule / hook / sandbox / human approval / read-only agent handing a summary to a separate writer / prompt prose only / nothing; (d) who can start the run (e.g. issue label, `@`-mention, comment command, `pull_request_target`). Read how prompts fence and label untrusted text as data; prose is defence-in-depth, never the stop. Exfiltration: same session holds a secret or private data and reaches a host or surface an outsider reads (fetch allowlist, tracker comment, PR body, public commit). Findings: (a) + write / push / shell with stop = prompt prose only or nothing (ASI01, LLM01); (a) + secret or private data + outsider-readable outbound; outsider can start a run that holds write credentials. Product model calls → `bkit-audit-llm`. **Done when:** `Untrusted Input` row per agent: untrusted sources · capabilities · who starts it · stop · verdict.
|
|
115
|
-
- [ ] **Step 10 — bkit Gates:** `.bkit/version` absent → explicit skip with evidence. Else per installed bkit host: every permission and hook bkit writes (`.bkit/README.md` § File ownership) appears in Steps 4
|
|
116
|
-
- [ ] **Step 11 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per agentic risk (ASI01
|
|
97
|
+
- [ ] **Step 10 — bkit Gates:** `.bkit/version` absent → explicit skip with evidence. Else per installed bkit host: every permission and hook bkit writes (`.bkit/README.md` § File ownership) appears in Steps 4-5 and in `Parity`; same bkit gate enforced in one host, open in another → upstream bkit fix. Version, drift, hosts with no bkit install, managed blocks, templates → `bkit-audit-adoption`. **Done when:** `bkit` section lists bkit gates per host with verdict, or skip with evidence.
|
|
98
|
+
- [ ] **Step 11 — Standards:** Confirm current version per anchor standard; read changes since previous report's version. `Standards Coverage`: one row per agentic risk (ASI01-ASI10), per tool-server security best practice, and per assistant-instructions guide recommendation this audit touches → checked (name step) / not applicable (why) / finding. Unapplied recommended practice → adopt (propose step) / reject (why) / not applicable. **Done when:** no empty row.
|
|
117
99
|
- [ ] **Step 12 — Anything Else:** (a) Everything changed since previous report's commit touching agent config (settings, hooks, tool-server files, agent definitions, skills, instruction load paths, bkit version) → one-line verdict each. (b) Bounded ~30 min pass: what a senior platform engineer flags that no step asks; read what happened since previous run (agent incidents, new `docs/failures.jsonl` rows, friction logs) — 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`.
|
|
118
100
|
|
|
119
101
|
### 🔒 Gate 2: Probes Check
|
|
120
102
|
|
|
121
|
-
**Checkpoint.** Verify and check `[x]` all boxes below, then continue to `Findings` without asking.
|
|
122
|
-
|
|
123
103
|
- [ ] **Steps complete:** every step `[x]`, or explicit skip with evidence the surface is absent.
|
|
124
104
|
- [ ] **Evidence:** every finding cites re-checkable evidence and the tool behind it.
|
|
125
105
|
- [ ] **No secrets:** no token, key, or secret value anywhere in the report.
|
|
126
106
|
- [ ] **Config untouched:** no agent config, hook, tool-server file, agent definition, or bkit-managed file changed; no `bkit install` / `bkit upgrade` run; no tool-server tool called.
|
|
127
|
-
- [ ] **Gate 2
|
|
107
|
+
- [ ] **Gate 2 — Verified:** Every checkbox above independently verified and checked off.
|
|
128
108
|
|
|
129
109
|
## Findings
|
|
130
110
|
|
|
@@ -136,7 +116,7 @@ Verify only when applicable.
|
|
|
136
116
|
| `MEDIUM` | Unused host config or tool server; tool description changed, no version change; dead or cross-host-inconsistent model pin; tracked local override; agent tools beyond role |
|
|
137
117
|
| `LOW` | Naming drift, no behaviour change; doc wrong about agent config while config right |
|
|
138
118
|
|
|
139
|
-
|
|
119
|
+
Within a severity: production writes, credentials, then parity gaps.
|
|
140
120
|
|
|
141
121
|
<!-- prettier-ignore -->
|
|
142
122
|
| ID | Severity | Host | Location | Evidence | Expected |
|
|
@@ -224,17 +204,13 @@ PENDING
|
|
|
224
204
|
|
|
225
205
|
### 🔒 Gate 3: Report Check
|
|
226
206
|
|
|
227
|
-
|
|
228
|
-
|
|
229
|
-
- [ ] **No placeholders:** Findings table and every `Report` section have no `PENDING`.
|
|
207
|
+
- [ ] **No placeholders:** no `PENDING` left
|
|
230
208
|
- [ ] **Summary:** names count per severity, machine, and hosts read.
|
|
231
209
|
- [ ] **Series:** `Parity` and tool-server hashes diffed against previous report's, or marked baseline.
|
|
232
|
-
- [ ] **Writes:** only this report
|
|
233
|
-
- [ ] **Process Improvements:** `Universal`
|
|
210
|
+
- [ ] **Writes:** only this report, template `Project Instructions`, and ledger rows changed; throwaway worktrees / remote targets removed.
|
|
211
|
+
- [ ] **Process Improvements:** `Universal` and `Project` filled
|
|
234
212
|
- [ ] **Suggested Issues:** every `MEDIUM`+ finding ID in exactly one row; every row has a `Next Step`.
|
|
235
|
-
- [ ] **Gate 3
|
|
236
|
-
|
|
237
|
-
> `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.
|
|
213
|
+
- [ ] **Gate 3 — Verified:** Every checkbox above independently verified and checked off.
|
|
238
214
|
|
|
239
215
|
<!-- bkit:end -->
|
|
240
216
|
|