@lifeaitools/rdc-skills 0.24.42 → 0.25.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (198) hide show
  1. package/.claude/settings.json +15 -15
  2. package/.claude-plugin/marketplace.json +21 -21
  3. package/.claude-plugin/plugin.json +1518 -1371
  4. package/.github/workflows/publish.yml +34 -34
  5. package/.github/workflows/self-test.yml +58 -58
  6. package/CHANGELOG.md +310 -310
  7. package/LICENSE +21 -21
  8. package/MANIFEST.md +221 -221
  9. package/README.md +375 -376
  10. package/README.sandbox.md +3 -3
  11. package/assets/watcher/viewer.html +164 -164
  12. package/bin/rdc-skills-mcp.mjs +316 -316
  13. package/commands/build.md +183 -183
  14. package/commands/collab.md +180 -180
  15. package/commands/deploy.md +152 -152
  16. package/commands/design.md +31 -31
  17. package/commands/edit.md +28 -28
  18. package/commands/fixit.md +150 -124
  19. package/commands/handoff.md +173 -173
  20. package/commands/help.md +95 -95
  21. package/commands/overnight.md +220 -220
  22. package/commands/plan.md +158 -158
  23. package/commands/preplan.md +131 -131
  24. package/commands/prototype.md +145 -145
  25. package/commands/release.md +49 -49
  26. package/commands/report.md +99 -99
  27. package/commands/review.md +120 -120
  28. package/commands/self-test.md +113 -113
  29. package/commands/status.md +86 -86
  30. package/commands/watch.md +98 -98
  31. package/commands/workitems.md +137 -137
  32. package/git-sha.json +1 -1
  33. package/guides/agent-bootstrap.md +295 -295
  34. package/guides/agents/backend.md +104 -104
  35. package/guides/agents/content.md +94 -94
  36. package/guides/agents/cs2.md +56 -56
  37. package/guides/agents/data.md +87 -87
  38. package/guides/agents/design.md +77 -77
  39. package/guides/agents/frontend.md +92 -92
  40. package/guides/agents/infrastructure.md +81 -81
  41. package/guides/agents/setup.md +281 -281
  42. package/guides/agents/verify.md +151 -151
  43. package/guides/agents/viz.md +106 -106
  44. package/guides/backend.md +146 -146
  45. package/guides/content.md +147 -147
  46. package/guides/cs2.md +190 -190
  47. package/guides/data.md +123 -123
  48. package/guides/design.md +116 -116
  49. package/guides/engineering-behavior.md +43 -43
  50. package/guides/escalation-protocol.md +125 -125
  51. package/guides/frontend.md +151 -151
  52. package/guides/history-md-spec.md +297 -297
  53. package/guides/infrastructure.md +179 -179
  54. package/guides/lessons-learned-spec.md +145 -151
  55. package/guides/output-contract.md +108 -108
  56. package/guides/publish-md-spec.md +289 -289
  57. package/guides/rdc-skills-startup.md +30 -30
  58. package/guides/verify.md +11 -11
  59. package/hooks/check-cwd.js +31 -31
  60. package/hooks/check-rdc-environment.js +164 -164
  61. package/hooks/check-services.js +6 -6
  62. package/hooks/check-stale-work-items.js +19 -19
  63. package/hooks/foreground-process-gate.js +128 -128
  64. package/hooks/gate-watchdog-selfcheck.js +257 -257
  65. package/hooks/hook-logger.js +25 -25
  66. package/hooks/lib/run-evidence-gate.mjs +241 -241
  67. package/hooks/no-stop-open-epics.js +127 -127
  68. package/hooks/post-tool-batch-gate.js +203 -203
  69. package/hooks/post-work-check.js +21 -21
  70. package/hooks/postcompact-log.js +13 -13
  71. package/hooks/precompact-log.js +13 -13
  72. package/hooks/rate-limit-retry.js +46 -46
  73. package/hooks/rdc-invocation-marker.js +157 -157
  74. package/hooks/rdc-output-contract-gate.js +94 -94
  75. package/hooks/require-work-item-on-commit.js +294 -294
  76. package/hooks/restart-brief.js +19 -19
  77. package/hooks/run-hidden-hook.ps1 +47 -47
  78. package/hooks/task-completed-gate.js +274 -274
  79. package/hooks/work-item-exit-gate.js +944 -944
  80. package/lib/catalog.mjs +236 -236
  81. package/lib/cloud-rewrite.mjs +155 -155
  82. package/package.json +57 -57
  83. package/rules/work-items-rpc.md +520 -520
  84. package/scaffold/templates/HISTORY.md.template +39 -39
  85. package/scaffold/templates/PUBLISH.md.template +21 -21
  86. package/scaffold/templates/brochure-studio-default.html +70 -70
  87. package/scripts/acceptance.mjs +502 -502
  88. package/scripts/fixtures/guides/bad-guide.md +15 -15
  89. package/scripts/fixtures/guides-clean/good-guide.md +16 -16
  90. package/scripts/install-rdc-skills.js +1289 -1289
  91. package/scripts/install.ps1 +202 -202
  92. package/scripts/install.sh +132 -132
  93. package/scripts/lib/assertions.mjs +287 -287
  94. package/scripts/lib/manifest-schema.mjs +754 -754
  95. package/scripts/lib/runner.mjs +465 -465
  96. package/scripts/lib/sandbox.mjs +435 -435
  97. package/scripts/prepack.mjs +32 -32
  98. package/scripts/rdc-brochure.mjs +482 -482
  99. package/scripts/rdc-design-cli.mjs +134 -134
  100. package/scripts/rebuild-mcp.mjs +107 -107
  101. package/scripts/self-test.mjs +1460 -1460
  102. package/scripts/stamp-git-sha.mjs +29 -29
  103. package/scripts/test-guide-validator.mjs +196 -196
  104. package/scripts/test-rdc-hooks.mjs +145 -145
  105. package/scripts/uninstall.ps1 +77 -77
  106. package/scripts/uninstall.sh +69 -69
  107. package/scripts/update.ps1 +43 -43
  108. package/scripts/update.sh +43 -43
  109. package/scripts/validate-place-histories.js +461 -461
  110. package/scripts/validate-publish-manifests.js +502 -424
  111. package/scripts/watch-init.mjs +100 -100
  112. package/skills/brochure/SKILL.md +107 -107
  113. package/skills/build/SKILL.md +563 -563
  114. package/skills/channel-formatter/SKILL.md +538 -533
  115. package/skills/co-develop/SKILL.md +196 -196
  116. package/skills/collab/SKILL.md +239 -239
  117. package/skills/convert/SKILL.md +167 -140
  118. package/skills/deploy/SKILL.md +541 -541
  119. package/skills/design/SKILL.md +211 -211
  120. package/skills/design/reference/ownership.md +16 -16
  121. package/skills/design/reference/rampa.md +92 -92
  122. package/skills/design/reference/studio-model.md +153 -153
  123. package/skills/edit/SKILL.md +98 -98
  124. package/skills/fixit/SKILL.md +203 -165
  125. package/skills/fs-mcp/SKILL.md +148 -148
  126. package/skills/handoff/SKILL.md +236 -236
  127. package/skills/help/SKILL.md +143 -143
  128. package/skills/housekeeping/SKILL.md +160 -219
  129. package/skills/lifeai-brochure-author/SKILL.md +340 -340
  130. package/skills/onramp/SKILL.md +248 -0
  131. package/skills/overnight/SKILL.md +251 -251
  132. package/skills/plan/SKILL.md +345 -345
  133. package/skills/preplan/SKILL.md +90 -90
  134. package/skills/prototype/SKILL.md +150 -150
  135. package/skills/rdc-brochurify/SKILL.md +245 -245
  136. package/skills/rdc-extract-verifier-rules/SKILL.md +191 -191
  137. package/skills/release/SKILL.md +140 -140
  138. package/skills/report/SKILL.md +100 -100
  139. package/skills/review/SKILL.md +152 -152
  140. package/skills/rpms-filemap/SKILL.cloud.md +111 -111
  141. package/skills/rpms-filemap/SKILL.md +111 -111
  142. package/skills/self-test/SKILL.md +132 -132
  143. package/skills/status/SKILL.md +99 -99
  144. package/skills/terminal-config/SKILL.md +62 -62
  145. package/skills/tests/MATRIX.md +54 -54
  146. package/skills/tests/README.md +47 -47
  147. package/skills/tests/onramp.test.json +87 -0
  148. package/skills/tests/rdc-brochure.test.json +34 -34
  149. package/skills/tests/rdc-build.test.json +36 -36
  150. package/skills/tests/rdc-channel-formatter.test.json +45 -45
  151. package/skills/tests/rdc-co-develop.test.json +29 -29
  152. package/skills/tests/rdc-collab.test.json +29 -29
  153. package/skills/tests/rdc-convert.test.json +35 -35
  154. package/skills/tests/rdc-deploy.test.json +30 -30
  155. package/skills/tests/rdc-design.test.json +27 -27
  156. package/skills/tests/rdc-edit.test.json +29 -29
  157. package/skills/tests/rdc-fixit.test.json +36 -36
  158. package/skills/tests/rdc-fs-mcp.test.json +36 -36
  159. package/skills/tests/rdc-handoff.test.json +28 -28
  160. package/skills/tests/rdc-help.test.json +29 -29
  161. package/skills/tests/rdc-housekeeping.test.json +28 -32
  162. package/skills/tests/rdc-lifeai-brochure-author.test.json +35 -35
  163. package/skills/tests/rdc-overnight.test.json +37 -37
  164. package/skills/tests/rdc-plan.test.json +27 -27
  165. package/skills/tests/rdc-preplan.test.json +31 -31
  166. package/skills/tests/rdc-prototype.test.json +28 -28
  167. package/skills/tests/rdc-rdc-brochurify.test.json +23 -23
  168. package/skills/tests/rdc-rdc-extract-verifier-rules.test.json +34 -34
  169. package/skills/tests/rdc-release.test.json +29 -29
  170. package/skills/tests/rdc-report.test.json +28 -28
  171. package/skills/tests/rdc-review.test.json +29 -29
  172. package/skills/tests/rdc-rpms-filemap.test.json +28 -28
  173. package/skills/tests/rdc-self-test.test.json +24 -24
  174. package/skills/tests/rdc-status.test.json +29 -29
  175. package/skills/tests/rdc-terminal-config.test.json +29 -29
  176. package/skills/tests/rdc-watch.test.json +24 -24
  177. package/skills/tests/rdc-workitems.test.json +27 -27
  178. package/skills/watch/SKILL.md +97 -97
  179. package/skills/workitems/SKILL.md +151 -151
  180. package/tests/acceptance.test.mjs +59 -59
  181. package/tests/channel-formatter.contract.test.mjs +251 -251
  182. package/tests/curl-surface.test.mjs +289 -289
  183. package/tests/harness-gates.test.mjs +325 -325
  184. package/tests/help-surface.test.mjs +61 -61
  185. package/tests/install-rdc-skills.test.mjs +49 -49
  186. package/tests/manifest-contract-fields.test.mjs +78 -78
  187. package/tests/mcp.test.mjs +271 -271
  188. package/tests/rdc-brochure.test.mjs +125 -125
  189. package/tests/require-work-item-on-commit.test.mjs +162 -162
  190. package/tests/run-evidence-gate.test.mjs +82 -82
  191. package/tests/skill-test-matrix.test.mjs +66 -66
  192. package/tests/validate-skills.js +27 -27
  193. package/tests/work-item-exit-gate-l2.test.mjs +368 -368
  194. package/tests/work-item-exit-gate-l3.test.mjs +197 -197
  195. package/RELEASE.md +0 -42
  196. package/tests/housekeeping-lessons-triage.test.mjs +0 -49
  197. package/tests/lessons-pipeline-contract.test.mjs +0 -27
  198. package/tests/release-contract.test.mjs +0 -16
@@ -1,152 +1,152 @@
1
- ---
2
- name: rdc:review
3
- description: "Usage `rdc:review [--unattended]` — Post-build quality gate: tsc, tests, stale docs, export conflicts, and a mandatory pr-review-toolkit:code-reviewer pass across modified packages. Fixes what it can automatically, escalates the rest. Call after rdc:build and before merging to main."
4
- ---
5
-
6
- > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
7
- > Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
8
- > One checklist upfront, updated in place, shown again at end with a 1-line verdict.
9
-
10
- > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`), then `{PROJECT_ROOT}/.rdc/guides/engineering-behavior.md` (fallback: `{PROJECT_ROOT}/.rdc/guides/engineering-behavior.md`).
11
-
12
- > **Sandbox contract:** This skill honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag.
13
-
14
-
15
- # rdc:review — Quality Gate
16
-
17
- ## When to Use
18
- - After a build session (especially overnight builds)
19
- - Before merging development → main/production
20
- - Project lead asks "review the work", "is everything clean"
21
- - Before any production deployment
22
- - Called by `rdc:overnight` after each epic build completes
23
-
24
- ## Arguments
25
- - `rdc:review` — interactive review, pauses on issues needing judgment
26
- - `rdc:review --unattended` — silent mode, auto-fixes everything fixable
27
-
28
- ## Procedure
29
-
30
- 1. **Identify modified packages:**
31
- ```bash
32
- git diff --name-only origin/main...HEAD | grep "^packages/" | cut -d/ -f2 | sort -u
33
- ```
34
-
35
- 2. **Run tests for each modified package:**
36
- ```bash
37
- cd packages/<name> && npx vitest run 2>&1 | tail -10
38
- ```
39
- Report: package → test count → pass/fail → new tests added
40
-
41
- **IMPORTANT:** `pnpm build` must NEVER be run (crashes system). Use `npx tsc --noEmit --project <path>/tsconfig.json` for typecheck instead. For packages without tests, typecheck is the verification method. Do NOT run vitest across the entire monorepo — check only modified packages individually.
42
-
43
- 3. **Check test coverage delta:**
44
- ```bash
45
- git diff origin/main...HEAD -- packages/*/src/ | grep -c "^+" | head -5
46
- git diff origin/main...HEAD -- packages/*/test* packages/*/src/**/*.test.* packages/*/src/**/*.spec.* 2>/dev/null | grep -c "^+" || echo 0
47
- ```
48
- Flag any package where implementation lines added > 50 but test lines added = 0.
49
-
50
- 4. **Check for export conflicts:**
51
- - Read `packages/*/src/index.ts` for any package with new exports
52
- - Look for duplicate export names across the barrel
53
- - Verify aliased exports don't shadow each other
54
-
55
- 5. **Check for TODO/FIXME/HACK:**
56
- ```bash
57
- grep -rn "TODO\|FIXME\|HACK\|XXX" packages/*/src/ --include="*.ts" --include="*.tsx"
58
- ```
59
-
60
- 6. **Check package versions:**
61
- - Any package with significant new code should have a version bump
62
- - Compare package.json versions to what's in `docs/SYSTEM-STATE.md`
63
-
64
- 7. **Check for stale CLAUDE.md:**
65
- - If new modules were added to a package, does its CLAUDE.md mention them?
66
- - Flag any package where exports grew by >10 lines but CLAUDE.md wasn't updated
67
-
68
- 8. **Orphan work item audit:**
69
- ```sql
70
- SELECT id, title, item_type, status, source, created_at::date
71
- FROM work_items
72
- WHERE parent_id IS NULL
73
- AND item_type NOT IN ('epic', 'bug')
74
- AND status NOT IN ('done', 'archived')
75
- ORDER BY created_at DESC;
76
- ```
77
- For each orphaned task found:
78
- - If it clearly belongs to an open epic → **do not run raw SQL**. No RPC exists for re-parenting. Create a work item: `SELECT insert_work_item(p_title := 'Re-parent orphaned task <task-id> to epic <epic-id>', p_priority := 'normal', p_source := 'agent')` and flag for supervisor to re-parent manually.
79
- - If unclear → report (interactive) or flag in REVIEW_STATUS (unattended)
80
- - Never silently leave orphaned tasks
81
- - **⛔ Raw `UPDATE work_items SET parent_id = ...` is forbidden** — bypasses RLS and all constraint checks
82
-
83
- 8b. **Mandatory code-review gate — dispatch pr-review-toolkit:code-reviewer:**
84
-
85
- ⛔ **No CLEAN verdict without a code-review pass.** This is the second half of the quality gate; tsc/vitest catch type and behavior errors, code-reviewer catches logic, security, and convention drift.
86
-
87
- Dispatch ONE `pr-review-toolkit:code-reviewer` agent on the full diff under review:
88
-
89
- ```
90
- Agent({
91
- subagent_type: "pr-review-toolkit:code-reviewer",
92
- description: "rdc:review code-review pass",
93
- prompt: "Review `git diff origin/main...HEAD` on the development branch.
94
- Focus on: bugs, logic errors, security vulnerabilities, project-convention
95
- adherence (.claude/rules/*, CLAUDE.md, engineering-behavior.md).
96
- Confidence-based filtering — high-confidence findings only.
97
- Return CODE_REVIEW_COMPLETE with: { critical_count, high_count, medium_count,
98
- low_count, findings: [{severity, file:line, issue, suggested_fix}] }."
99
- })
100
- ```
101
-
102
- **Severity gate:**
103
- - `critical` or `high` → verdict cannot be CLEAN. Interactive: report and pause. Unattended: auto-fix if mechanical (rename, missing await, obvious null check), otherwise escalate via advisor and mark HAS_ISSUES.
104
- - `medium` or `low` → record in the review report's "Issues" section; verdict can still be CLEAN.
105
- - Zero findings → log `CODE_REVIEW: CLEAN` and continue.
106
-
107
- Under `RDC_TEST=1`: echo `[RDC_TEST] skipping code-review dispatch` and continue.
108
-
109
- 9. **Verification gate — dispatch the verify agent:**
110
- After any fixes land, run the verify gate on every touched package. See `guides/agents/verify.md`.
111
- Apply `guides/engineering-behavior.md` while reviewing: flag unnecessary abstraction, drive-by refactors, missing assumptions, hidden uncertainty, out-of-scope edits, and prose-only verification.
112
- **Iron Law: no CLEAN verdict without fresh evidence.** Quote the checklist decomposition verdict, vitest output, and tsc output in the report.
113
- The verify agent must reject any work item that lacks passed `decomp-*` checklist rows, whose rows are too coarse to prove one observable behavior at a time, OR whose checklist falls below the per-surface completeness floor (a feature WP with 5-6 rows where its surfaces demand 12-20 attested rows is a REJECT).
114
- If verify fails → do NOT emit CLEAN. Loop back, fix, re-run verify.
115
-
116
- 10. **Fix issues found:**
117
- - Failing tests → fix and commit
118
- - Export conflicts → resolve and commit
119
- - Missing version bumps → bump and commit
120
- - All fixes as separate commits with descriptive messages
121
-
122
- **Judgment calls:**
123
- - Interactive: report — don't guess
124
- - Unattended: escalate via advisor tool with: error message, surrounding context,
125
- two most likely fix paths. Resume with advisor's recommendation.
126
- If advisor unavailable: take the most conservative path, flag in status block.
127
-
128
- 11. **Report:**
129
- - Interactive:
130
- ```
131
- ## Review Results
132
- | Package | Tests | Pass/Fail | New Tests | Issues |
133
- ## Fixed
134
- ## Remaining Issues
135
- ## Verdict: CLEAN / HAS ISSUES
136
- ```
137
- - Unattended: emit status block only:
138
- ```
139
- REVIEW_STATUS: { verdict: "CLEAN|HAS_ISSUES", packages_checked, tests_passed, tests_failed, new_tests_added, fixes_applied, escalations }
140
- ```
141
-
142
- ## Rules
143
- - Do NOT run `pnpm build` (crashes system) — vitest only
144
- - Interactive: fix what you can, flag what needs decision
145
- - Unattended: fix everything fixable; escalate judgment calls to advisor
146
- - Each fix is a separate commit (not batched)
147
- - Always push fixes to origin after committing *(skip if `$RDC_TEST=1` — echo `[RDC_TEST] skipping git push` instead)*
148
- - Unattended: NEVER pause for input
149
-
150
- ## Capture lessons (exit step)
151
-
152
- Before the final verdict line, follow `.rdc/guides/lessons-learned-spec.md` § Capture procedure. If this run taught something non-obvious — a first root-cause theory that turned out wrong, the documented/standard path not working, a missing gate or check that cost a round, or a surprising tool/infra behavior — write one `.rdc/lessons/<YYYY-MM-DD>-review-<short-slug>.md` per lesson using the schema in that spec. Set `scope` (`simple` | `architectural`) and `lesson_status: open`; weekly triage alone records a final lesson outcome. Commit the lesson file(s) on `develop` alongside the run's other commits, and note "N lessons captured" in your verdict/summary. A run that taught nothing writes nothing — absence is the default.
1
+ ---
2
+ name: rdc:review
3
+ description: "Usage `rdc:review [--unattended]` — Post-build quality gate: tsc, tests, stale docs, export conflicts, and a mandatory pr-review-toolkit:code-reviewer pass across modified packages. Fixes what it can automatically, escalates the rest. Call after rdc:build and before merging to main."
4
+ ---
5
+
6
+ > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
7
+ > Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
8
+ > One checklist upfront, updated in place, shown again at end with a 1-line verdict.
9
+
10
+ > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`), then `{PROJECT_ROOT}/.rdc/guides/engineering-behavior.md` (fallback: `{PROJECT_ROOT}/.rdc/guides/engineering-behavior.md`).
11
+
12
+ > **Sandbox contract:** This skill honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag.
13
+
14
+
15
+ # rdc:review — Quality Gate
16
+
17
+ ## When to Use
18
+ - After a build session (especially overnight builds)
19
+ - Before merging development → main/production
20
+ - Project lead asks "review the work", "is everything clean"
21
+ - Before any production deployment
22
+ - Called by `rdc:overnight` after each epic build completes
23
+
24
+ ## Arguments
25
+ - `rdc:review` — interactive review, pauses on issues needing judgment
26
+ - `rdc:review --unattended` — silent mode, auto-fixes everything fixable
27
+
28
+ ## Procedure
29
+
30
+ 1. **Identify modified packages:**
31
+ ```bash
32
+ git diff --name-only origin/main...HEAD | grep "^packages/" | cut -d/ -f2 | sort -u
33
+ ```
34
+
35
+ 2. **Run tests for each modified package:**
36
+ ```bash
37
+ cd packages/<name> && npx vitest run 2>&1 | tail -10
38
+ ```
39
+ Report: package → test count → pass/fail → new tests added
40
+
41
+ **IMPORTANT:** `pnpm build` must NEVER be run (crashes system). Use `npx tsc --noEmit --project <path>/tsconfig.json` for typecheck instead. For packages without tests, typecheck is the verification method. Do NOT run vitest across the entire monorepo — check only modified packages individually.
42
+
43
+ 3. **Check test coverage delta:**
44
+ ```bash
45
+ git diff origin/main...HEAD -- packages/*/src/ | grep -c "^+" | head -5
46
+ git diff origin/main...HEAD -- packages/*/test* packages/*/src/**/*.test.* packages/*/src/**/*.spec.* 2>/dev/null | grep -c "^+" || echo 0
47
+ ```
48
+ Flag any package where implementation lines added > 50 but test lines added = 0.
49
+
50
+ 4. **Check for export conflicts:**
51
+ - Read `packages/*/src/index.ts` for any package with new exports
52
+ - Look for duplicate export names across the barrel
53
+ - Verify aliased exports don't shadow each other
54
+
55
+ 5. **Check for TODO/FIXME/HACK:**
56
+ ```bash
57
+ grep -rn "TODO\|FIXME\|HACK\|XXX" packages/*/src/ --include="*.ts" --include="*.tsx"
58
+ ```
59
+
60
+ 6. **Check package versions:**
61
+ - Any package with significant new code should have a version bump
62
+ - Compare package.json versions to what's in `docs/SYSTEM-STATE.md`
63
+
64
+ 7. **Check for stale CLAUDE.md:**
65
+ - If new modules were added to a package, does its CLAUDE.md mention them?
66
+ - Flag any package where exports grew by >10 lines but CLAUDE.md wasn't updated
67
+
68
+ 8. **Orphan work item audit:**
69
+ ```sql
70
+ SELECT id, title, item_type, status, source, created_at::date
71
+ FROM work_items
72
+ WHERE parent_id IS NULL
73
+ AND item_type NOT IN ('epic', 'bug')
74
+ AND status NOT IN ('done', 'archived')
75
+ ORDER BY created_at DESC;
76
+ ```
77
+ For each orphaned task found:
78
+ - If it clearly belongs to an open epic → **do not run raw SQL**. No RPC exists for re-parenting. Create a work item: `SELECT insert_work_item(p_title := 'Re-parent orphaned task <task-id> to epic <epic-id>', p_priority := 'normal', p_source := 'agent')` and flag for supervisor to re-parent manually.
79
+ - If unclear → report (interactive) or flag in REVIEW_STATUS (unattended)
80
+ - Never silently leave orphaned tasks
81
+ - **⛔ Raw `UPDATE work_items SET parent_id = ...` is forbidden** — bypasses RLS and all constraint checks
82
+
83
+ 8b. **Mandatory code-review gate — dispatch pr-review-toolkit:code-reviewer:**
84
+
85
+ ⛔ **No CLEAN verdict without a code-review pass.** This is the second half of the quality gate; tsc/vitest catch type and behavior errors, code-reviewer catches logic, security, and convention drift.
86
+
87
+ Dispatch ONE `pr-review-toolkit:code-reviewer` agent on the full diff under review:
88
+
89
+ ```
90
+ Agent({
91
+ subagent_type: "pr-review-toolkit:code-reviewer",
92
+ description: "rdc:review code-review pass",
93
+ prompt: "Review `git diff origin/main...HEAD` on the development branch.
94
+ Focus on: bugs, logic errors, security vulnerabilities, project-convention
95
+ adherence (.claude/rules/*, CLAUDE.md, engineering-behavior.md).
96
+ Confidence-based filtering — high-confidence findings only.
97
+ Return CODE_REVIEW_COMPLETE with: { critical_count, high_count, medium_count,
98
+ low_count, findings: [{severity, file:line, issue, suggested_fix}] }."
99
+ })
100
+ ```
101
+
102
+ **Severity gate:**
103
+ - `critical` or `high` → verdict cannot be CLEAN. Interactive: report and pause. Unattended: auto-fix if mechanical (rename, missing await, obvious null check), otherwise escalate via advisor and mark HAS_ISSUES.
104
+ - `medium` or `low` → record in the review report's "Issues" section; verdict can still be CLEAN.
105
+ - Zero findings → log `CODE_REVIEW: CLEAN` and continue.
106
+
107
+ Under `RDC_TEST=1`: echo `[RDC_TEST] skipping code-review dispatch` and continue.
108
+
109
+ 9. **Verification gate — dispatch the verify agent:**
110
+ After any fixes land, run the verify gate on every touched package. See `guides/agents/verify.md`.
111
+ Apply `guides/engineering-behavior.md` while reviewing: flag unnecessary abstraction, drive-by refactors, missing assumptions, hidden uncertainty, out-of-scope edits, and prose-only verification.
112
+ **Iron Law: no CLEAN verdict without fresh evidence.** Quote the checklist decomposition verdict, vitest output, and tsc output in the report.
113
+ The verify agent must reject any work item that lacks passed `decomp-*` checklist rows, whose rows are too coarse to prove one observable behavior at a time, OR whose checklist falls below the per-surface completeness floor (a feature WP with 5-6 rows where its surfaces demand 12-20 attested rows is a REJECT).
114
+ If verify fails → do NOT emit CLEAN. Loop back, fix, re-run verify.
115
+
116
+ 10. **Fix issues found:**
117
+ - Failing tests → fix and commit
118
+ - Export conflicts → resolve and commit
119
+ - Missing version bumps → bump and commit
120
+ - All fixes as separate commits with descriptive messages
121
+
122
+ **Judgment calls:**
123
+ - Interactive: report — don't guess
124
+ - Unattended: escalate via advisor tool with: error message, surrounding context,
125
+ two most likely fix paths. Resume with advisor's recommendation.
126
+ If advisor unavailable: take the most conservative path, flag in status block.
127
+
128
+ 11. **Report:**
129
+ - Interactive:
130
+ ```
131
+ ## Review Results
132
+ | Package | Tests | Pass/Fail | New Tests | Issues |
133
+ ## Fixed
134
+ ## Remaining Issues
135
+ ## Verdict: CLEAN / HAS ISSUES
136
+ ```
137
+ - Unattended: emit status block only:
138
+ ```
139
+ REVIEW_STATUS: { verdict: "CLEAN|HAS_ISSUES", packages_checked, tests_passed, tests_failed, new_tests_added, fixes_applied, escalations }
140
+ ```
141
+
142
+ ## Rules
143
+ - Do NOT run `pnpm build` (crashes system) — vitest only
144
+ - Interactive: fix what you can, flag what needs decision
145
+ - Unattended: fix everything fixable; escalate judgment calls to advisor
146
+ - Each fix is a separate commit (not batched)
147
+ - Always push fixes to origin after committing *(skip if `$RDC_TEST=1` — echo `[RDC_TEST] skipping git push` instead)*
148
+ - Unattended: NEVER pause for input
149
+
150
+ ## Capture lessons (exit step)
151
+
152
+ Before the final verdict line, follow `.rdc/guides/lessons-learned-spec.md` § Capture procedure. If this run taught something non-obvious — a first root-cause theory that turned out wrong, the documented/standard path not working, a missing gate or check that cost a round, or a surprising tool/infra behavior — write one `.rdc/lessons/<YYYY-MM-DD>-review-<short-slug>.md` per lesson using the schema in that spec. Set `scope` (`simple` | `architectural`) and `status` (`open`, or `applied` if you shipped the fix in this same run, with the commit linked). Commit the lesson file(s) on `develop` alongside the run's other commits, and note "N lessons captured" in your verdict/summary. A run that taught nothing writes nothing — absence is the default.
@@ -1,111 +1,111 @@
1
- ---
2
- name: rpms-filemap
3
- description: "Generated RPMS file map — RULE #1, canonical homes, and Context Export pointers served from regen-root manifest."
4
- slash: "rdc:rpms-filemap"
5
- category: "tooling"
6
- usage: "rdc:rpms-filemap"
7
- requires: []
8
- triggers:
9
- - "rpms file map"
10
- - "rule #1"
11
- - "context export"
12
- - "where does this file belong"
13
- - "where should pm artifacts go"
14
- ---
15
- # RPMS File Map
16
- > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
17
- > Return the requested file-map guidance directly; do not dump raw manifests or logs.
18
-
19
- > GENERATED FILE - DO NOT HAND-EDIT.
20
- > Source of truth: `docs/architecture/rpms.locations.json`
21
- > Regenerate: `pnpm rpms:gen-filemap`
22
-
23
- ## RULE #1
24
-
25
- **Name the entity -> read its `_context.md` -> you are oriented.**
26
-
27
- The operational door is pinned in `docs/architecture/CONTEXT-EXPORT.md` and in RPMS section 8.1.
28
- If you are touching an entity, read its generated `_context.md` before any local reasoning, and never hand-edit that projection.
29
-
30
- ## Pointers
31
-
32
- - RPMS section 6a: Asset lens and branch-store split
33
- - RPMS section 6b: Corpus disk layout
34
- - RPMS section 8.1: Session-start ritual and locked-decision read order
35
-
36
- ## Canonical Map
37
-
38
- ### Canonical Sources
39
-
40
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
41
- |----------|------|----|-----|-------------|-------|--------|
42
- | `canon.rpms.architecture` | `docs/architecture/regenerative-project-management-system.md` | `read_only` | One Home Per Fact, One Door | `block_wrong_home`<br />`path_conformance` | docs/architecture/regenerative-project-management-system.md | `active` |
43
- | `canon.context-export.single-door` | `docs/architecture/CONTEXT-EXPORT.md` | `read_only` | One Direction, One Door | `block_wrong_home`<br />`path_conformance` | docs/architecture/CONTEXT-EXPORT.md | `active` |
44
-
45
- ### Session Start
46
-
47
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
48
- |----------|------|----|-----|-------------|-------|--------|
49
- | `session-start.claude-ai.root` | `CLAUDE.ai.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | repo-root | `active` |
50
- | `session-start.claude.root` | `CLAUDE.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | repo-root | `active` |
51
- | `session-start.decision.spine-lock` | `.rdc/plans/project-relationship-graph-approval.md` | `read_only` | One Spine, One Door | `block_wrong_home`<br />`path_conformance` | .rdc/plans/project-relationship-graph-approval.md | `active` |
52
- | `session-start.decision.cs2-lock` | `.rdc/plans/mdk-knowledge-decisions-and-workitems-2026-06-02.md` | `read_only` | One Direction, One Door | `block_wrong_home`<br />`path_conformance` | .rdc/plans/mdk-knowledge-decisions-and-workitems-2026-06-02.md | `active` |
53
- | `session-start.glossary.layer-model` | `docs/systems/cs2/LAYER-MODEL-AND-VOCABULARY.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | docs/systems/cs2/LAYER-MODEL-AND-VOCABULARY.md | `active` |
54
-
55
- ### Database Gates
56
-
57
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
58
- |----------|------|----|-----|-------------|-------|--------|
59
- | `session-start.work-items.queue` | `table:work_items via rpc:get_open_epics` | `rpc_only` | One Home Per Fact, One Door | `rpc_only`<br />`rpc_contract`<br />CRUD stays behind insert_work_item/update_work_item_status/update_checklist_item/submit_implementation_report. | public.work_items + RPC gate | `active` |
60
-
61
- ### Place Corpus
62
-
63
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
64
- |----------|------|----|-----|-------------|-------|--------|
65
- | `session-start.entity-context.place` | `places/*/_context.md`<br />created_by: `apps/studio/src/lib/context-export-writer.ts` | `generated` | One Direction, One Door | `block_manual_edit`<br />`projection_drift` | context-export writer | `active` |
66
- | `place.identity.place-md` | `places/*/PLACE.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | place stewards | `active` |
67
- | `place.history.history-md` | `places/*/HISTORY.md` | `append_only` | One Direction, One Home Per Fact | `allow_declared_home`<br />`path_conformance` | place stewards | `active` |
68
- | `place.corpus.index` | `places/*/corpus/INDEX.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | place corpus | `active` |
69
- | `place.corpus.documents` | `places/*/corpus/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban`<br />Text and markdown live here; binaries route to branch stores. | place corpus | `active` |
70
- | `place.artifacts.outputs` | `places/*/artifacts/**` | `generated` | One Direction | `allow_declared_home`<br />`path_conformance` | render pipelines | `active` |
71
- | `place.legacy.asset-bundles` | `places/*/*.assets/**` | `legacy_frozen` | One Direction, One Home Per Fact | `block_manual_edit`<br />`path_conformance`<br />Bridge-state allowlist for current repo reality; no new writes here. | legacy bridge until asset-lens migration | `active` |
72
- | `place.tracker.pm-docs` | `places/*/tracker/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | place operators | `active` |
73
-
74
- ### Shared Corpus
75
-
76
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
77
- |----------|------|----|-----|-------------|-------|--------|
78
- | `session-start.entity-context.project-node` | `corpus/_shared/*/_context.md`<br />created_by: `apps/studio/src/lib/context-export-writer.ts` | `generated` | One Direction, One Door | `block_manual_edit`<br />`projection_drift` | context-export writer | `active` |
79
- | `shared.index` | `corpus/_shared/*/INDEX.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | shared corpus | `active` |
80
- | `shared.framework.documents` | `corpus/_shared/*/framework/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | shared corpus | `active` |
81
- | `shared.research.documents` | `corpus/_shared/*/research/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | shared corpus | `active` |
82
- | `shared.legacy.design-assets` | `corpus/_shared/*/design/**/assets/**` | `legacy_frozen` | One Direction, One Home Per Fact | `block_manual_edit`<br />`path_conformance`<br />Bridge-state allowlist for current repo reality; no new writes here. | legacy bridge until asset-lens migration | `active` |
83
- | `shared.corpus.documents` | `corpus/_shared/` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban`<br />Generated _context.md remains separately governed by projection drift. | shared corpus | `active` |
84
-
85
- ### Asset Lens
86
-
87
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
88
- |----------|------|----|-----|-------------|-------|--------|
89
- | `asset-lens.entity-assets.registry` | `table:entity_assets` | `deferred` | One Spine, One Home Per Fact | `deferred`<br />`deferred`<br />Manifest records the canonical home now; implementation remains deferred per plan section 6a E7. | RPMS E7 | `deferred` |
90
-
91
- ### Operational Door
92
-
93
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
94
- |----------|------|----|-----|-------------|-------|--------|
95
- | `operational-door.rdc.plans` | `.rdc/plans/**` | `authored` | One Home Per Fact, One Direction | `allow_declared_home`<br />`path_conformance` | RDC planning workflow | `active` |
96
- | `operational-door.rdc.reports` | `.rdc/reports/**` | `generated` | One Direction | `allow_declared_home`<br />`path_conformance` | rdc:report | `active` |
97
- | `operational-door.rdc.lessons` | `.rdc/lessons/**` | `append_only` | One Direction, One Home Per Fact | `allow_declared_home`<br />`path_conformance` | RDC lesson capture workflow | `active` |
98
- | `operational-door.rpms-filemap.rule` | `.claude/rules/rpms-filemap.md`<br />created_by: `scripts/rpms/gen-filemap.ts` | `generated` | One Home Per Fact, One Direction, One Door | `block_manual_edit`<br />`projection_drift` | scripts/rpms/gen-filemap.ts | `active` |
99
-
100
- ### App Guides
101
-
102
- | Artifact | Home | RW | Law | Enforcement | Owner | Status |
103
- |----------|------|----|-----|-------------|-------|--------|
104
- | `session-start.app-guide` | `apps/*/CLAUDE.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | app-local architecture guides | `active` |
105
-
106
- ## Projection Contract
107
-
108
- - Generated projections (`_context.md`, this rule) are never hand-edited.
109
- - Authored markdown stays in its declared home; do not create second homes elsewhere.
110
- - `work_items` stays RPC-only even when the location is documented here.
111
- - Corpus homes are text-first; binaries route to branch stores, not git under `places/` or `corpus/`.
1
+ ---
2
+ name: rpms-filemap
3
+ description: "Generated RPMS file map — RULE #1, canonical homes, and Context Export pointers served from regen-root manifest."
4
+ slash: "rdc:rpms-filemap"
5
+ category: "tooling"
6
+ usage: "rdc:rpms-filemap"
7
+ requires: []
8
+ triggers:
9
+ - "rpms file map"
10
+ - "rule #1"
11
+ - "context export"
12
+ - "where does this file belong"
13
+ - "where should pm artifacts go"
14
+ ---
15
+ # RPMS File Map
16
+ > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
17
+ > Return the requested file-map guidance directly; do not dump raw manifests or logs.
18
+
19
+ > GENERATED FILE - DO NOT HAND-EDIT.
20
+ > Source of truth: `docs/architecture/rpms.locations.json`
21
+ > Regenerate: `pnpm rpms:gen-filemap`
22
+
23
+ ## RULE #1
24
+
25
+ **Name the entity -> read its `_context.md` -> you are oriented.**
26
+
27
+ The operational door is pinned in `docs/architecture/CONTEXT-EXPORT.md` and in RPMS section 8.1.
28
+ If you are touching an entity, read its generated `_context.md` before any local reasoning, and never hand-edit that projection.
29
+
30
+ ## Pointers
31
+
32
+ - RPMS section 6a: Asset lens and branch-store split
33
+ - RPMS section 6b: Corpus disk layout
34
+ - RPMS section 8.1: Session-start ritual and locked-decision read order
35
+
36
+ ## Canonical Map
37
+
38
+ ### Canonical Sources
39
+
40
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
41
+ |----------|------|----|-----|-------------|-------|--------|
42
+ | `canon.rpms.architecture` | `docs/architecture/regenerative-project-management-system.md` | `read_only` | One Home Per Fact, One Door | `block_wrong_home`<br />`path_conformance` | docs/architecture/regenerative-project-management-system.md | `active` |
43
+ | `canon.context-export.single-door` | `docs/architecture/CONTEXT-EXPORT.md` | `read_only` | One Direction, One Door | `block_wrong_home`<br />`path_conformance` | docs/architecture/CONTEXT-EXPORT.md | `active` |
44
+
45
+ ### Session Start
46
+
47
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
48
+ |----------|------|----|-----|-------------|-------|--------|
49
+ | `session-start.claude-ai.root` | `CLAUDE.ai.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | repo-root | `active` |
50
+ | `session-start.claude.root` | `CLAUDE.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | repo-root | `active` |
51
+ | `session-start.decision.spine-lock` | `.rdc/plans/project-relationship-graph-approval.md` | `read_only` | One Spine, One Door | `block_wrong_home`<br />`path_conformance` | .rdc/plans/project-relationship-graph-approval.md | `active` |
52
+ | `session-start.decision.cs2-lock` | `.rdc/plans/mdk-knowledge-decisions-and-workitems-2026-06-02.md` | `read_only` | One Direction, One Door | `block_wrong_home`<br />`path_conformance` | .rdc/plans/mdk-knowledge-decisions-and-workitems-2026-06-02.md | `active` |
53
+ | `session-start.glossary.layer-model` | `docs/systems/cs2/LAYER-MODEL-AND-VOCABULARY.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | docs/systems/cs2/LAYER-MODEL-AND-VOCABULARY.md | `active` |
54
+
55
+ ### Database Gates
56
+
57
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
58
+ |----------|------|----|-----|-------------|-------|--------|
59
+ | `session-start.work-items.queue` | `table:work_items via rpc:get_open_epics` | `rpc_only` | One Home Per Fact, One Door | `rpc_only`<br />`rpc_contract`<br />CRUD stays behind insert_work_item/update_work_item_status/update_checklist_item/submit_implementation_report. | public.work_items + RPC gate | `active` |
60
+
61
+ ### Place Corpus
62
+
63
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
64
+ |----------|------|----|-----|-------------|-------|--------|
65
+ | `session-start.entity-context.place` | `places/*/_context.md`<br />created_by: `apps/studio/src/lib/context-export-writer.ts` | `generated` | One Direction, One Door | `block_manual_edit`<br />`projection_drift` | context-export writer | `active` |
66
+ | `place.identity.place-md` | `places/*/PLACE.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | place stewards | `active` |
67
+ | `place.history.history-md` | `places/*/HISTORY.md` | `append_only` | One Direction, One Home Per Fact | `allow_declared_home`<br />`path_conformance` | place stewards | `active` |
68
+ | `place.corpus.index` | `places/*/corpus/INDEX.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | place corpus | `active` |
69
+ | `place.corpus.documents` | `places/*/corpus/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban`<br />Text and markdown live here; binaries route to branch stores. | place corpus | `active` |
70
+ | `place.artifacts.outputs` | `places/*/artifacts/**` | `generated` | One Direction | `allow_declared_home`<br />`path_conformance` | render pipelines | `active` |
71
+ | `place.legacy.asset-bundles` | `places/*/*.assets/**` | `legacy_frozen` | One Direction, One Home Per Fact | `block_manual_edit`<br />`path_conformance`<br />Bridge-state allowlist for current repo reality; no new writes here. | legacy bridge until asset-lens migration | `active` |
72
+ | `place.tracker.pm-docs` | `places/*/tracker/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | place operators | `active` |
73
+
74
+ ### Shared Corpus
75
+
76
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
77
+ |----------|------|----|-----|-------------|-------|--------|
78
+ | `session-start.entity-context.project-node` | `corpus/_shared/*/_context.md`<br />created_by: `apps/studio/src/lib/context-export-writer.ts` | `generated` | One Direction, One Door | `block_manual_edit`<br />`projection_drift` | context-export writer | `active` |
79
+ | `shared.index` | `corpus/_shared/*/INDEX.md` | `authored` | One Home Per Fact, One Door | `allow_declared_home`<br />`path_conformance` | shared corpus | `active` |
80
+ | `shared.framework.documents` | `corpus/_shared/*/framework/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | shared corpus | `active` |
81
+ | `shared.research.documents` | `corpus/_shared/*/research/**` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban` | shared corpus | `active` |
82
+ | `shared.legacy.design-assets` | `corpus/_shared/*/design/**/assets/**` | `legacy_frozen` | One Direction, One Home Per Fact | `block_manual_edit`<br />`path_conformance`<br />Bridge-state allowlist for current repo reality; no new writes here. | legacy bridge until asset-lens migration | `active` |
83
+ | `shared.corpus.documents` | `corpus/_shared/` | `authored` | One Home Per Fact | `block_binary_commit`<br />`binary_ban`<br />Generated _context.md remains separately governed by projection drift. | shared corpus | `active` |
84
+
85
+ ### Asset Lens
86
+
87
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
88
+ |----------|------|----|-----|-------------|-------|--------|
89
+ | `asset-lens.entity-assets.registry` | `table:entity_assets` | `deferred` | One Spine, One Home Per Fact | `deferred`<br />`deferred`<br />Manifest records the canonical home now; implementation remains deferred per plan section 6a E7. | RPMS E7 | `deferred` |
90
+
91
+ ### Operational Door
92
+
93
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
94
+ |----------|------|----|-----|-------------|-------|--------|
95
+ | `operational-door.rdc.plans` | `.rdc/plans/**` | `authored` | One Home Per Fact, One Direction | `allow_declared_home`<br />`path_conformance` | RDC planning workflow | `active` |
96
+ | `operational-door.rdc.reports` | `.rdc/reports/**` | `generated` | One Direction | `allow_declared_home`<br />`path_conformance` | rdc:report | `active` |
97
+ | `operational-door.rdc.lessons` | `.rdc/lessons/**` | `append_only` | One Direction, One Home Per Fact | `allow_declared_home`<br />`path_conformance` | RDC lesson capture workflow | `active` |
98
+ | `operational-door.rpms-filemap.rule` | `.claude/rules/rpms-filemap.md`<br />created_by: `scripts/rpms/gen-filemap.ts` | `generated` | One Home Per Fact, One Direction, One Door | `block_manual_edit`<br />`projection_drift` | scripts/rpms/gen-filemap.ts | `active` |
99
+
100
+ ### App Guides
101
+
102
+ | Artifact | Home | RW | Law | Enforcement | Owner | Status |
103
+ |----------|------|----|-----|-------------|-------|--------|
104
+ | `session-start.app-guide` | `apps/*/CLAUDE.md` | `read_only` | One Door | `block_wrong_home`<br />`path_conformance` | app-local architecture guides | `active` |
105
+
106
+ ## Projection Contract
107
+
108
+ - Generated projections (`_context.md`, this rule) are never hand-edited.
109
+ - Authored markdown stays in its declared home; do not create second homes elsewhere.
110
+ - `work_items` stays RPC-only even when the location is documented here.
111
+ - Corpus homes are text-first; binaries route to branch stores, not git under `places/` or `corpus/`.