메뉴
Audit architecture and system docs for staleness, inaccuracy, and drift from actual codebase state. Grouped into 7 tiers for thorough coverage. Complement to /md-audit (existence-staleness — when that ships).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Baylight Authority Director Keisha Ramos. Generates construction updates, milestone announcements, development progress reports, and civic documents (deliverable filings, TIF reports, workforce agreements) for the $2.1B Baylight District project.
Phase 39.1 capability reviewer wrapper. Runs the deterministic editorial assertions against a compiled edition, surfaces blocking failures that should halt publish, and writes a markdown summary alongside the JSON.
Prepare all inputs for city-hall voice agents. Reads tracker, approvals, world summary, engine review, coverage ratings, previous log, canon, Mara directive. Writes pending decisions per voice.
Senior Photographer for The Cycle Pulse. Generates image prompts and photo selection for editions. Reads compiled edition + canon rules + institutions, produces 5-8 storyline-tied prompts.
Letters to the Editor desk agent for The Cycle Pulse. Writes citizen voice letters responding to cycle events. Use when producing letters section of an edition.
Close the feedback loop. Canonize to Supermemory, update world-data, write ratings to sheets, grade reporters, update criteria files, update newsroom memory. Type-aware — edition, interview, supplemental, dispatch all converge here.
| name | doc-audit |
| description | Audit architecture and system docs for staleness, inaccuracy, and drift from actual codebase state. Grouped into 7 tiers for thorough coverage. Complement to /md-audit (existence-staleness — when that ships). |
| version | 2.1 |
| updated | "2026-06-16T00:00:00.000Z" |
| tags | ["engine","active"] |
| effort | high |
/doc-audit [group] — Audit one group thoroughly
/doc-audit — Audits the group that hasn't been audited longest (check the tracker below)
7 groups, 5-12 docs each. Small enough to audit thoroughly.
| Doc | What to verify |
|---|---|
SESSION_CONTEXT.md | On-demand post-ADR-0009 (S248) — NOT read at boot. Live span reasonable size (hard close snapshots to docs/session-context/S<##>.md + resets to thin header)? STATUS line current? No duplicated content from ROLLOUT? (The old "under 300 lines / last 5 sessions" criterion predates ADR-0009 — it's a span model now, not a rolling-5 file.) |
CLAUDE.md | Quick commands still work? Session lifecycle refs current? Rules index matches actual rules files? Wiki-layer reference present and pointing to existing files? Canon files referenced if relevant? |
docs/mags-corliss/CHARACTER.md | Identity-only (governance.5 partial close S228): The Principle / Who I Am / My Family / Off the Clock. NO session counter (lives in SESSION_CONTEXT.md line 5). NO infrastructure refs (live in STACK.md / SUPERMEMORY.md). NO Compact Recovery (lives in .claude/skills/boot/SKILL.md). Audit: family POPIDs match ledger? No drift back to operational content? |
.claude/rules/identity.md | Rules still match actual behavior? No contradictions with CLAUDE.md? |
.claude/rules/newsroom.md | Cycle-rule reversal still documented (S146)? Citizen-creation rules current? 2041 birth-year anchor present? |
.claude/rules/engine.md | Engine code rules current? Determinism guidance reflects safeRand_ pattern post-S156? |
.claude/rules/dashboard.md | Dashboard rules current? Endpoint conventions match server code? |
MEMORY.md (auto-memory) | Under 24.4KB (S147 limit per CLAUDE.md, NOT 200 lines). Dead memory file references? Stale session memories? Population numbers current? Index entries one-line under ~150 chars? |
docs/SCHEMA.md | Folder map matches actual docs/ layout (now includes docs/canon/ per S174)? Tag taxonomy reflects what's actually in use? Page types still match what we're creating? Frontmatter example valid YAML? |
docs/index.md | Every active docs/**.md (excluding archive/, drive-files/, papers PDFs) appears exactly once? No broken [[wikilinks]]? Renamed/deleted files reflected? Folder section headers match SCHEMA folder map? docs/canon/ and docs/research/ sections present? |
docs/canon/CANON_RULES.md | Three-tier framework intact? Per-agent template still matches what generators use? Reviewer-variant template still matches Rhea/city-clerk/final-arbiter usage? Sports-history carveout (S175) referenced correctly? |
docs/canon/INSTITUTIONS.md | Tier-organized; row-statuses (canon/proposed/TBD) tracked? New tier-2 entities surfaced in editions added? Construction/architecture firm rows still TBD or progressed? |
docs/BOOT_ARCHITECTURE.md | S165 boot architecture intact? Skill split (boot/session-startup) accurate? Per-terminal persona levels match TERMINAL.md files? |
docs/POST_MORTEM_C92_CONTAMINATION.md | Historical record intact? S173 reframe note present (this is the failure that motivated canon/CANON_RULES)? |
| Doc | What to verify |
|---|---|
docs/engine/ROLLOUT_PLAN.md | Open items — any completed but not marked? Stale priorities? Line count reasonable? Halt banner accuracy (S172)? Off-spine items reflect plan-file status? |
docs/engine/ENGINE_MAP.md | Function list matches actual godWorldEngine2.js call order? |
docs/engine/ENGINE_STUB_MAP.md | Field dependencies — run node scripts/ctxMap.js and compare. Auto-regenerated by /stub-engine. |
docs/engine/ENGINE_REPAIR.md | Active tracker — P0/P1/P2/P3 rows current? Items closed by recent commits removed? |
docs/engine/ENGINE_CONNECTIVITY_ROLLOUT.md | Phase 34 — 7 of 10 done per S136 audit; verify count current. |
docs/engine/SHEETS_MANIFEST.md | Sheet names match actual spreadsheet tabs? |
docs/engine/PHASE_DATA_AUDIT.md | ctx.summary fields match current code? |
docs/engine/REVIEWER_LANE_SCHEMA.md | Four-field contract (process/outcome/controllable/uncontrollable) still matches what Rhea/cycle-review/Mara/capability emit? Four-quadrant interpretation cross-references PHASE_39_PLAN §17.3? |
docs/engine/INSTITUTIONAL_VOICE_AGENTS.md | Voice-agent count + IDENTITY+RULES+SKILL pattern still accurate post-S174 (now IDENTITY+LENS+RULES+SKILL for civic voices)? |
docs/engine/CYCLE_SEPARATION.md | S113 architecture notes still relevant given subsequent phases? |
docs/engine/phase19_agent_personas.md | Three administrative-agent personas (City Clerk + others) — match current .claude/agents/ directories? |
docs/engine/PHASE_24_PLAN.md | Citizen life engine plan — status updated? Sub-items reflect current progress? |
docs/engine/PHASE_33_PLAN.md | Riley integration — 12 of 19 remaining per S152; verify count + status. |
docs/engine/PHASE_38_PLAN.md | Engine auditor — sub-phases 38.1-38.8 status accurate? Measurement loop (38.5) DONE S156? |
docs/engine/PHASE_39_PLAN.md | Reviewer chain — 39.1-39.10 all DONE S148? |
docs/engine/PHASE_40_PLAN.md | 5 of 6 done (40.1, 40.3, 40.4, 40.5, 40.6); only 40.2 remains? |
docs/engine/DOCUMENTATION_LEDGER.md | SUNSET-FLAG — folding into docs/index.md per its own header. Audit only for cross-check; do not maintain. |
docs/engine/LEDGER_HEAT_MAP.md | engine-sheet handoff (S156) — extremely stale C81/S30/2026-02-16. Defer to engine-sheet terminal for refresh. |
docs/engine/LEDGER_REPAIR.md | engine-sheet handoff (S156) — RECOVERY COMPLETE S94, dating language stale but "DO NOT re-analyze" intact. Audit-light. |
docs/engine/LEDGER_AUDIT.md | engine-sheet handoff (S156) — pre-recovery counts (658/639) stale. Defer. |
docs/engine/ROLLOUT_ARCHIVE.md | Frozen archive — read on demand only; verify no active items leaked back in. |
| Doc | What to verify |
|---|---|
docs/EDITION_PIPELINE.md | Terminal count, step count, reporter list, civic voice list match current skill files? Inputs table current? Post-S174 four-file agent structure reflected? |
docs/EDITION_PIPELINE_v1_archive.md | Archive — verify no active items leaked in. |
docs/media/AGENT_NEWSROOM.md | Reporter count, names, desk assignments match .claude/agents/ directories (currently 27)? Canon-fidelity rollout (S174-S175) reflected — all 25 generative + reviewer agents have four-file structure? |
docs/media/DESK_PACKET_PIPELINE.md | SUPERSEDED — canonical is EDITION_PIPELINE.md. Do not maintain; archive when archive/ move happens. |
docs/media/MEDIA_ROOM_HANDOFF.md | Engine→Media Room handoff guide current? |
docs/media/MEDIA_INTAKE_V2.2_HANDOFF.md | Media Room markdown parsing structure current? |
docs/media/MEDIA_ROOM_STYLE_GUIDE.md | Voice rules, data treatment, continuity, clock rules current? Cycle-allowed (S146 reversal) reflected? |
docs/media/TIME_CANON_ADDENDUM.md | Dual-clock system (sports time vs city time) current? |
docs/media/REAL_NAMES_BLOCKLIST.md | Active — Rhea reads this every verification. Real-world sports figures listed; sync with canon Athletics/Bulls rosters. Sports-history carveout (S175) — historical players now permitted; reflect carveout in scope notes. |
docs/media/CITIZEN_NARRATIVE_MEMORY.md | Supermemory + Richmond Archive + Ledger integration current? |
docs/media/JOURNALISM_AI_OPTIMIZATIONS.md | AP/Reuters/Bloomberg patterns — version current? v1.2 complete per S147. |
docs/media/GOOGLE_DRIVE_INTEGRATION.md + docs/media/DRIVE_MANIFEST.md | Drive folder + file IDs current? |
docs/media/podcast/SHOW_FORMATS.md | Podcast formats match /podcast skill? Host assignments current? |
docs/media/story_evaluation.md | Changelog growing each cycle (expected: one entry per post-publish run). Front page scoring section present. If no new entries in 3+ cycles, post-publish Step 10 isn't running — flag. |
docs/media/brief_template.md | Changelog growing. Structure section intact. Good/bad brief examples present. If stale, flag. |
docs/media/citizen_selection.md | Changelog growing. MCP lookup rule (citizens vs A's players) current. Name collision warning still needed (check if ledger cleanup happened). |
docs/media/intake.md | Edition intake section reference current? |
docs/media/CANON_ARCHIVE_LEDGER.md | Every published edition + supplemental indexed with metadata? Latest entry covers most recent shipped edition? |
docs/media/RICHMOND_ARCHIVE_INDEX.md | Hal Richmond's archive index — entry count current? Sports-history carveout reflected if archive entries reference real historical figures? |
docs/media/ANTHONY_RAINES_PORTFOLIO_INDEX.md + docs/media/P_SLAYER_JOURNEY_INDEX.md | Portfolio entry counts current? |
docs/media/CITIZENS_BY_ARTICLE.md + docs/media/ARTICLE_INDEX_BY_POPID.md | Cross-reference indexes current? Updated post-publish? |
docs/media/PAULSON_CARPENTERS_LINE.md | Mike Paulson backstory by Hal Richmond — canon-permanent, audit-light. |
docs/media/2041_athletics_roster.md + docs/media/PLAYER_CARD_INDEX.md | Roster set in 2041 — verify against truesource_reference.json. Player cards match A's roster? |
output/DISK_MAP.md | Directory structure matches actual output/ layout? Naming conventions match scripts? |
| Doc | What to verify |
|---|---|
docs/OPERATIONS.md | PM2 processes match pm2 list? Cron jobs match crontab -l? Mobile access instructions current? |
docs/STACK.md | All components exist? Versions current? Process names match? Endpoint/skill/agent counts match (currently 27 agents, 41 skills)? |
docs/DASHBOARD.md | Endpoint count matches actual server/*.js routes? Frontend tabs current? |
docs/DISCORD.md | Bot name, model, knowledge sources, Supermemory integration current? |
docs/SUPERMEMORY.md | 6 containers listed? Isolation rules match config? Access matrix current? Skills table matches actual commands? |
docs/CLAUDE-MEM.md | Bun daemon (NOT PM2)? Port 37777? SQLite + Chroma still the stack? AutoDream config matches /root/.claude-mem/settings.json (Gemini 2.5 Pro free tier per S141)? |
docs/FOUR_COMPONENT_MAP.md | Terminal count matches .claude/terminals/ subdirs (5: civic/engine-sheet/mags/media/research-build)? Skill count matches ls .claude/skills/ | wc -l (currently 41)? Agent count matches ls .claude/agents/ | wc -l (currently 27)? Models per role current? Cron inventory matches crontab -l? §7 seam map reflects current Phase 40 status (5/6 DONE)? |
docs/MIGRATION_OFF_CLAUDE.md | S154 desk-agent migration — DeepSeek V3.1 via OpenRouter results current? Test script + next-steps + survives-list accurate? |
docs/ACTION_MANAGED_AGENTS.md | Anthropic Managed Agents research — still ready to evaluate? Status changed? |
docs/CANCELLATION.md | Monthly costs current? Cancellation paths still valid? New paid services added (Supermemory P N at $9/mo confirmed)? |
docs/WORKFLOWS.md | 7 workflow patterns — match actual session usage? Post-S165 reframe (workflow reference, not boot file) reflected? |
docs/RESEARCH.md | Findings log current? Recent evaluations recorded (DeepSeek S154, Sandcastle/Daytona S156, outside-AI reviews S170)? |
docs/research4_1.md + docs/research4_2.md | Engineering patterns + Ryan dissertation — still load-bearing reference? Cross-references in current plans? |
docs/research/briefing_bloat_audit_2026-04-17.md | Audit findings still accurate? Trim plan ([[archive/plans/2026-04-17-briefing-bundle-trim]]) status? |
| Doc | What to verify |
|---|---|
docs/SIMULATION_LEDGER.md | Citizen count, column count (47 — A-AU per S156 SCHEMA_HEADERS, NOT 46), column numbers match live sheet? ClockMode/Tier/Status/Flag sub-counts updated since S140? |
docs/SPREADSHEET.md | Tab count matches actual spreadsheet (53 visible + 6 hidden + utility ≈ 65)? Per-tab row counts — defer to SCHEMA_HEADERS as authoritative. |
schemas/SCHEMA_HEADERS.md | Auto-generated by utilities/exportSchemaHeaders.js — verify it's been regenerated recently (S156 added frontmatter that survives regeneration). Header counts authoritative for all tabs. |
docs/engine/LEDGER_HEAT_MAP.md | engine-sheet handoff (S156) — extremely stale C81/S30/2026-02-16. Bloat rankings + dead column inventory likely outdated. Do not maintain in research-build; flag for engine-sheet refresh. |
docs/engine/LEDGER_REPAIR.md | engine-sheet handoff (S156) — RECOVERY COMPLETE S94, "DO NOT re-analyze" intact. Column reference (A-AU now per S156) — needs update from A-AT. Audit-light. |
docs/engine/LEDGER_AUDIT.md | engine-sheet handoff (S156) — pre-recovery counts (658/639) stale; CLEAN since S68 status correct. Audit-light. |
docs/plans/ files are the most drift-prone in the repo. Each plan tracks status (active/complete/parked); marking a completed plan "complete" without flagging means future sessions waste cycles re-discovering done work. Audit cadence: every 2-3 sessions, or after any session that closes a plan-tracked phase.
| Doc | What to verify |
|---|---|
docs/plans/TEMPLATE.md | Reference template — verify shape matches active plan files. Audit-light. |
docs/plans/BACKLOG.md | Consolidated parked-phase backlog — verify phases listed are still parked (not started, not complete elsewhere). Cross-check against ROLLOUT_PLAN spine. |
docs/archive/plans/skill-eval-framework.md | HIGH priority not started — verify status; check first skill /skill-check shipped S156 reference still accurate. |
docs/archive/plans/2026-04-16-phase-38-5-measurement-loop.md | DONE S156 — verify Status section reflects completion; consider archive flag. |
docs/archive/plans/2026-04-16-phase-38-6-skill-shrink.md | DONE S156 — verify Status section reflects completion. |
docs/archive/plans/2026-04-16-phase-40-1-session-log-interface.md | DONE S156 — verify. |
docs/archive/plans/2026-04-16-phase-40-3-credential-audit.md | Drafted S156, engine/sheet picks up when priority rises — verify status hasn't changed silently. |
docs/archive/plans/2026-04-16-phase-40-6-injection-defense.md | Drafted by research-build; engine/sheet builds — verify build status. |
docs/archive/plans/2026-04-17-briefing-bundle-trim.md | Drafted S156; media terminal executes — verify execution status. |
docs/plans/2026-04-21-memento-cbr-case-bank.md | 4-phase rollout; reward-tuple capture has standalone value — verify phase 1 status and ≥500 tuples / droplet headroom thresholds for phase B. |
docs/archive/plans/2026-04-21-md-audit-skill.md | /md-audit skill plan — verify status; merges with /doc-audit eventually (Option B in S175 review). |
docs/archive/plans/2026-04-25-canon-fidelity-rollout.md | DONE S175 — verify Status section reflects 25/25 completion + Q1/Q2/Q3 resolutions + Out-of-scope findings. |
docs/plans/mara-reference-files.md | COMPLETE S105 — verify archive status; consider folder move to archive. |
Plan-file specific checks:
pointers:) point to existing filesPer-persona docs for Mags Corliss and Mara Vance. CHARACTER.md is in the boot group; everything else here. Logs (JOURNAL, SESSION_HISTORY, DAILY_REFLECTIONS) are append-only — audit-light or skip.
| Doc | What to verify |
|---|---|
docs/mags-corliss/NEWSROOM_MEMORY.md | Editorial decisions, errata, cross-cycle continuity notes current? Recent editions reflected? |
docs/mags-corliss/NOTES_TO_SELF.md | Editorial flags, story tracking, character tracking, Discord notes — entries growing? Stale flags removed when story closed? |
docs/mags-corliss/TECH_READING_ARCHIVE.md | Tech reading log — recent papers added (S170 outside-AI reviews, S145+ Memento, etc.)? |
docs/mags-corliss/JOURNAL.md + JOURNAL_RECENT.md | Append-only logs. Audit-light: entry count growing each session? JOURNAL_RECENT correctly carries last 3 entries? |
docs/mags-corliss/SESSION_HISTORY.md | Append-only. Verify older sessions rotated from SESSION_CONTEXT land here. |
docs/mags-corliss/DAILY_REFLECTIONS.md | Append-only nightly reflection log. Cron still firing (11 PM CDT)? |
docs/mara-vance/README.md | Quick-access index for Mara reference materials — links current? |
docs/mara-vance/IN_WORLD_CHARACTER.md | Mara's in-world character file — consistent with current civic-governance role? |
docs/mara-vance/CLAUDE_AI_SYSTEM_PROMPT.md | System prompt for Mara's claude.ai project — current? Reflects S171 rehire? |
docs/mara-vance/OPERATING_MANUAL.md | v2.0 — verify version + governance procedures still match current pipeline. |
docs/mara-vance/MEDIA_ROOM_INTRODUCTION.md | Newsroom interface for Mara — current? |
docs/mara-vance/CIVIC_GOVERNANCE_MASTER_REFERENCE.md | Complete reference for Oakland civic governance mechanics — sync with civic-office-ledger + canon council members? |
docs/mara-vance/CIVIC_ELECTION_ENGINE.md | Election engine reference — accurate? |
docs/mara-vance/CIVIC_VETO_IMPLEMENTATION.md | v1.7 — verify version current; mayoral veto + override votes mechanics still match engine. |
docs/mara-vance/INITIATIVE_TRACKER_VOTER_LOGIC.md | civicInitiativeEngine v1.7 voter logic — verify version. |
docs/mara-vance/AUDIT_HISTORY.md | Mara's audit history across editions — most recent edition (E92, A grade after Maker override) entry present? |
Update this after each audit. /doc-audit with no argument picks the oldest.
Tracker reset S175 — group definitions expanded significantly (5 → 7 groups, ~28 → ~80 docs). Prior S156 audit notes preserved as historical context but do not match current group scope. All groups need re-audit under v2.0 definitions.
| Group | Last Audited (v2.0) | Session | Notes |
|---|---|---|---|
| boot | 2026-06-01 | S251 | Re-audit (~39 sessions after S212), oldest group (tied with infra/persona, picked for boot-criticality + heaviest recent churn). 14 docs surveyed; 2 real research-build-lane content fixes shipped + 1 skill-criterion fix + 1 Mike's-lane flag + 2 light, 8 healthy. Fixes shipped (research-build lane): (1) BOOT_ARCHITECTURE.md — 3 epochs of drift in the canonical boot doc, all corrected: S221 (PERSISTENCE.md→CHARACTER.md rename across lines 27/58-60; unregistered-window fallback line 45 still said "research-build steward" — internal contradiction with the correct Mags-only statement at Decision 5; Persona Levels table still had civic/research-build on the dead "Light + PERSISTENCE" tier vs current operational-no-character mode) + S248 (Decision 2 + the /session-startup line still described the pre-ADR-0009 limit 80 / 231-line boot read — boot no longer reads SESSION_CONTEXT; hook emits the Shipped block in <godworld-state>); stamp 2026-04-18→2026-06-01 + ADR-0009 added to sources/pointers. (2) SCHEMA.md §7 folder tree + placement rules — docs/canon/ (S174) and docs/adr/ (S187), both load-bearing, were absent from the map; added both + changelog. (3) doc-audit/SKILL.md boot row — its own SESSION_CONTEXT criterion ("under 300 lines / last 5 sessions") was the pre-ADR-0009 model; rewrote to the span model so the next boot audit doesn't false-flag a healthy on-demand file. Mike's-lane flag (not touched — identity rule, never edit auto-memory on own judgment): MEMORY.md = 25,405 bytes (24.8KB) over the 24.4KB ceiling by ~419B; the file's own footer warns index entries are too long. Decision needed: prune index entries / raise limit / accept. Light (within tolerance, not actionable): CLAUDE.md population stamp "~1,366 / S212 live counts" 39 sessions old but engine lifecycle work deploy-held for C96 so population materially unchanged; the boot-doc title still reads "— S165" (origin marker, content now current). Healthy / no-fix (8): SESSION_CONTEXT.md 169 lines (healthy by any measure); .claude/rules/ = 6 files exactly matching CLAUDE.md L48 index (identity/engine/newsroom/civic/research-build/dashboard); CHARACTER.md identity-only, no session counter (correctly points to SESSION_CONTEXT L5), family POPIDs present (Robert 594 / Sarah 595 / Michael 596); CANON_RULES + INSTITUTIONS updated 2026-05-24 (current); identity.md current; index.md has rollout-rules + GAP_TRIAGE_TEMPLATE properly registered (governance.30 S251); POST_MORTEM_C92 frozen. Commit: boot-group fixes shipped this session; cross-terminal git stack checked clean before push. |
| plans | 2026-05-31 | S248 | Re-audit (~36 sessions after S212). 61 plan files (30 new since S212). Built a tag-vs-ROLLOUT-vs-index matrix (frontmatter state-tag × open in ROLLOUT_PLAN × present in ROLLOUT_ARCHIVE × registered in index). 11 stale frontmatter tags flipped active/draft → complete — each confirmed closed on BOTH axes (ROLLOUT row archived AND own plan-body status DONE/closed/superseded), not just the substring heuristic: dispatch-gap-followups, c93-gap-triage-execution, run-cycle-gap-log-surface (DONE S198), vote-trigger-mechanism (DONE S199), skill-eval-expansion (gov.2 closed S216), civic-tracker-collision-schema (civic.9), canon-2-faith-scrub (canon.2 S218), boot-persona-contamination (done S221), supermemory-profile-leverage (gov.12/17), pipeline-29-research-build (S230), session-end-collapse (gov.7 S230). Held deliberately (1): skill-eval-framework — its expansion row (gov.2) is archived but the doc is the PARENT framework whose own status reads "Designed S141, not built, HIGH priority"; flipping it would mislabel still-aspirational design as shipped. Left active, noted. False positives correctly NOT touched: 7 complete-tagged plans that grep-matched ROLLOUT_PLAN only via the Spine table (historical "all DONE") or Changelog refs, not open-work rows (phase-38-5/6, 40-1/3/6, world-data-ingest, skill-supermemory-alignment) — tags already correct. Index check: docs/index.md records plan links + descriptions, NOT state words — so tag flips need zero index edits (verified: plan-line state-word scan = 0). No body-content drift / no dead refs. Open plans (c95-triage, session-context-on-demand, citizen-lifecycle-fame, cycle-init-admin, sift-v2, canon-3) correctly stay active/draft — their ROLLOUT rows are open. Light flag (not actionable, prior-precedent): ~8 plans carry updated: stamps 30+ sessions stale but content aligns with ROLLOUT — flipped-tag plans not date-bumped (closure detail lives in ROLLOUT changelog + archive). Render note: bash output channel glitched hard mid-audit (empty/stale returns); all 11 flips confirmed landed via grep before this row; index-state finding confirmed inline. Push held — stacks on cross-terminal git stack. |
| media | 2026-05-31 | S248 | Re-audit (~42 sessions after S206). ~30 docs surveyed; 1 real drift fixed (2 docs) + known prior-flagged handoffs unchanged + healthy. Fix shipped (1 finding, 2 docs): civic-office-okoro (Deputy Mayor Brenda Okoro) added since the S206 stamp — 26 agent dirs live, both pipeline docs said 25. (a) AGENT_NEWSROOM.md — agent count 25→26, civic office 7→8 with okoro named, four-file count 24→25, stamp S206→S248; (b) EDITION_PIPELINE.md Layer-2 voices-parallel list gained okoro (Deputy Mayor) (she's a city-hall Layer-2 cascade target per .claude/skills/city-hall/SKILL.md L161 + CASCADE_ROUTING; four-file complete; buildVoiceWorkspaces.js still says "7 civic offices" — engine-sheet lane, flagged not fixed). Note: AGENT_NEWSROOM "25 journalists" refs (bay_tribune_roster.json voice profiles, §Full Reporter Roster) are a DIFFERENT count — okoro is a civic voice not a journalist — left unchanged. Changelog-growth check PASS: story_evaluation + brief_template + citizen_selection all carry fresh S241 (C95) entries — post-publish Step 10 / direct-evidence path IS running (resolves the recurring S180/S206 "Step 10 not running" flag). Prior-flagged handoffs still pending media-terminal (unchanged, not research-build lane): 2041_athletics_roster S45 stamp, RICHMOND/ANTHONY_RAINES/P_SLAYER indexes 2026-02-12 stamps. Engine-sheet flag: buildVoiceWorkspaces.js "7 civic offices" undercounts okoro. Render note: tool-output rendering glitched repeatedly this session (stale/scrambled returns); every claim re-verified via computed grep -c before editing. Push held — stacks on cross-terminal git stack. |
| engine | 2026-05-30 | S248 | Engine-sheet S248 audit — same-session as the engine.5 lifecycle/fame design work (deliberately re-audited my own just-touched lane). 7 my-lane docs; 2 fixes + 2 deferred findings + 3 healthy. Fixes shipped (2): (1) ENGINE_REPAIR — frontmatter 2026-05-24→2026-05-30 + new S248 Log entry (Track 1 ship d173310 deploy-held + Row 24 career-drift-freeze filed 7ee5d87 + Row 25 lifecycle/fame filed 9a532ad + Row 22 blast-radius reclassification); Rows 22/24/25 are this session's own additions so the stale stamp was real. (2) ENGINE_MAP — "Last verified" S234→S248 + S207→S248 touch-log entry for generationalEventsEngine v2.6→v2.7 (Track 1 wedding→MaritalStatus / birth→NumChildren++, DEPLOY HELD for C96; phase dispatch + function set UNCHANGED so the call-order map still holds). Deferred findings (report-only, not engine-sheet-fix-now): ROLLOUT_PLAN "Last Updated S238" stale (shared research-build spine header; engine.29 content correct; stamp bump owed at research-build close — not touched mid-stack while research-build has unpushed governance commits); ENGINE_STUB_MAP regen still pending from S234 (S248 added no new functions — 2 local indices + in-place mutations only — so didn't worsen; still needs a dedicated /stub-engine pass). Healthy / no-fix (3): LEDGER_AUDIT + LEDGER_HEAT_MAP + SHEETS_MANIFEST — S248 added 0 ledger rows (Track 1 deploy-held, no cycle ran) so all current at S234. Push held — S248 doc-audit commit stacks on a cross-terminal git stack (3 engine-sheet + 2 research-build unpushed); research-build runs the push at close. |
| engine | 2026-05-24 | S234 | Engine-sheet S234 audit (~28 sessions after S206). 22 my-lane docs surveyed; 4 fixes shipped + 1 follow-up flagged + 4 healthy + 8 cross-terminal docs out-of-scope. Fixes shipped (4): (1) ENGINE_MAP — S207-S233 touches block added (S229 §3.5 batch 1/2/3 — runCivicElections + bondEngine + Chicago Path B disable; engine.4 satellite-status close; engine.11 chaos-cars Phase 1 T1.4 seed; S232 canon.3 T6/T8/T9 + followup + ingest root-cause fix; S233 canon.3 T7/T10/T11 POPID alias resolver) + S234 "Last verified" stamp; (2) ENGINE_REPAIR — frontmatter 2026-05-07 → 2026-05-24, 3 new log entries (S229 §3.5 cluster CLOSED end-to-end with all 11 sites resolved across 3 batches + 2 clasp deploys live; S229 Row 4 satellite-status closed; S232 verify-pass on §3.5 post-deploy stable across C93+C94 + canon.3 T9 backfill 22-row net delta context), Row 8 fix-pointer rewritten from "B3-B7 GATED on C94 smoke-test" to "§3.5 CLOSED S229 — UNGATED; B5/B6/B7 are remaining frontier"; (3) LEDGER_AUDIT — new §Current State S234 refresh with headline numbers table (836 → 858 rows / POPID → POP-00973 / Tier T4 +22 / Status enum NEW pending=22 + lowercase 'active'=1 drift + Recovering disappeared / non-canon-12 neighborhoods 219 → 221), S94 recovery re-verification table holding, Tier×ClockMode matrix update, 5 drift classes documented (Status pending writer-origin + 1 lowercase regression + 8-variant neighborhood breakdown + POPID gaps unchanged + Recovering disappearance noted), per-column completeness deltas; (4) LEDGER_HEAT_MAP — S234 stamp-pass with live delta note (Sim_Ledger 836→858 / LifeHistory_Log ~3,669→~3,762 within tolerance / Story_Seed_Deck steady-state holds), no table rewrites needed. Follow-up flagged (1): ENGINE_STUB_MAP last regen 2026-05-07 (S205); ~6 file deletes since (arcLifecycleEngine + hookLifecycleEngine + worldEventsLedger + rollbackToCycle80 + citizenFameTracker + generateCitizensEvents) + chaos-cars seed + tests added; needs dedicated /stub-engine regen pass. Healthy / no-fix (4): SHEETS_MANIFEST accepts staleness per S185 security-key gate (live Anthropic API key in Drive sheets blocks routine regen until handled); DOCUMENTATION_LEDGER sunset-flagged; LEDGER_REPAIR S94 RECOVERY COMPLETE + DO NOT re-analyze intact; ENGINE_CONNECTIVITY_ROLLOUT (Phase 34, research-build lane historical). Out of scope (cross-terminal): ROLLOUT_PLAN (research-build spine), PHASE_24/33/38/39/40_PLAN (research-build), REVIEWER_LANE_SCHEMA + INSTITUTIONAL_VOICE_AGENTS (post-S174 four-file structure, research-build), CYCLE_SEPARATION (S113 historical, research-build), phase19_agent_personas (research-build), PHASE_DATA_AUDIT (research-build). |
| data | 2026-05-24 | S234 | Engine-sheet S234 audit (~22 sessions after S212). 6 my-lane docs surveyed; 2 fixes shipped + 3 healthy + 1 overlap-handled-in-engine. Fixes shipped (2): (1) SIMULATION_LEDGER — headline row count ~837 → 858; max POPID POP-00951 → POP-00973; LEDGER_AUDIT pointer S181 → S234; Last audited S187 → S234 + tier breakdown from S234 audit (T1=21/T2=64/T3=210/T4=563) + Status breakdown (826 Active + 22 pending + 9 Retired + 1 lowercase 'active' drift); ClockMode/Tier sub-counts in body still S105-stale at Population Structure table (engine-sheet refresh deferred — full breakdown lives in LEDGER_AUDIT now). (2) SPREADSHEET — Simulation_Ledger row count refreshed to 858; SCHEMA_HEADERS stamp updated from 2026-04-27 to 2026-05-12 (S213 auto-regen); Last audited S187 → S234. Other per-tab row counts in Active Tabs table still S187-era — SCHEMA_HEADERS authoritative for any specific tab; full per-tab refresh deferred to dedicated session. Healthy / no-fix (3): SCHEMA_HEADERS.md auto-regenerated 2026-05-12 (S213) — authoritative; LEDGER_REPAIR S94 RECOVERY COMPLETE + DO NOT re-analyze intact (engine-sheet handoff from S187 — column reference A-AT → A-AU body update still deferred, audit-light); LEDGER_AUDIT S234 major refresh shipped in /doc-audit engine same session. Overlap handled in /doc-audit engine: LEDGER_HEAT_MAP S234 stamp-pass + LEDGER_AUDIT S234 major refresh both shipped under engine-group commit; data group cites the same fixes. |
| boot | 2026-05-09 | S212 | Re-verify after S207 trim + S212 work. 14 docs surveyed; 1 actionable fix (docs/index.md stamp 2026-04-30→2026-05-09 — content current, all S204+ docs registered including ADR-0003, routing-rationale, claude-mem-vs-ecc-v2, engine-routing-foundation, chaos-cars-engine, boot-load-audit). S205 prior findings resolved: SESSION_CONTEXT.md was 821 lines, now 105 (S207 trim shipped 76, +29 since — under spec 300); CHARACTER.md S203→S212 current. Light flags (decision-required, Mike's lane): (1) MEMORY.md auto-memory at 26.6KB / 178 lines vs CLAUDE.md spec 24.4KB — S212 added 3 inline rules (gen-eval + load-out + role-taxonomy); 2.2KB over. Decision needed: prune / raise limit / accept. (2) CLAUDE.md line 131 population stamp "~837 per S187" — now 26 sessions stale (was 18 at S205); within tolerance per S205 framing. Healthy: 6 .claude/rules/ files (engine + newsroom + dashboard + identity + civic NEW S212 + research-build NEW S212), CLAUDE.md line 35 path-scoped list updated, BOOT_ARCHITECTURE.md no stale 5-terminal claims (clean post-S211), CANON_RULES + INSTITUTIONS intact, POST_MORTEM_C92 frozen at S172, identity.md current, CONTEXT.md at /root/GodWorld/CONTEXT.md (correct location per CLAUDE.md), docs/index.md catalog content current. |
| boot | 2026-05-07 | S205 | Full v2.0 audit complete — closes S176 partial. 14 docs deep-audited (CLAUDE.md, 4 rules files, SCHEMA.md, index.md, BOOT_ARCHITECTURE.md, POST_MORTEM_C92_CONTAMINATION.md, CANON_RULES.md, INSTITUTIONS.md, CHARACTER.md, MEMORY.md auto, SESSION_CONTEXT.md, CONTEXT.md). 3 stale, 0 inconsistent, 0 dead refs. All 3 stale findings owned by /session-end ritual, NOT doc-audit: (1) CHARACTER.md line 5 "Session: 203" should be S205 (session-end manual update); (2) SESSION_CONTEXT.md is 821 lines vs spec 300, Recent Sessions runs S179 down to S144 — Maintenance Rule at line 488 not being enforced (rotation to SESSION_HISTORY.md not happening); (3) CLAUDE.md line 131 population stamp cites S187 (~837), current is ~836 per S204 — within tolerance, 18 sessions stale on stamp. New since S176 (verified intact): ADR-0001 + ADR-0002 + ADR-0003 (this session) + CONTEXT.md (S187) + 2 new plans (engine-routing-foundation + chaos-cars-engine). Healthy: BOOT_ARCHITECTURE (S165 split intact), CANON_RULES (three-tier + sports-history carveout), INSTITUTIONS (tier-organized), SCHEMA, index (current with S205 additions), MEMORY auto (24K at 24.4KB limit), all 4 rules files, JOURNAL_RECENT (3 entries spec'd). Outstanding flag for follow-up: SESSION_CONTEXT.md trim is operationally broken — 35+ session entries persisted, boot-time read costs more than spec, "last 5 sessions" is fiction. Either dedicated trim session or fold into next /session-end. |
| engine | 2026-05-08 | S206 | Engine-sheet S206 audit. 25 docs surveyed; 6 stale, 1 inconsistent, 1 dead ref, 10 healthy. Fixes shipped (7): (1) ENGINE_MAP.md — bumped "Last verified" S185→S206; replaced "unchanged from S120" claim with full S188/S199/S200/S204/S205/S206 touch summary; struck-through line 79 dispatch entry 5-GenericCitizens with "DISABLED S205" annotation pointing to commit d89693f + call-site lines; struck-through line 376 Math.random fallback row with disable note. (2) ROLLOUT_PLAN.md — Last Updated S204→S206. (3) .claude/rules/engine.md line 44 — annotated generateGenericCitizens.js exception entry with "DISABLED S205, retained for reversibility" + processAdvancementIntake "GC paths inert post-S205, retire pending C94+C95 monitor"; line 45 also annotated arcLifecycleEngine.js (DELETED S199 bbdca3a) + hookLifecycleEngine.js strikethrough (DELETED S201 954d994). (4) SHEETS_MANIFEST.md — header staleness flag added; authoritative pointer to SCHEMA_HEADERS.md (regenerated S206); full regen still gated on dedicated session for Drive security finding per S185 note. (5) PHASE_42_INVENTORY.md — header note "Snapshot frozen S184; current state in PHASE_42_PATTERNS Changelog"; inventory retained as historical baseline only. (6) Moved docs/engine/ROLLOUT_PLAN_backup_S147.md → docs/archive/ROLLOUT_PLAN_backup_S147.md (orphan, no inbound link). (7) This tracker row. Healthy (no fix): ENGINE_REPAIR (S205 my edits), ENGINE_STUB_MAP (regen S205), LEDGER_HEAT_MAP (S202 refresh — S185 audit's "extremely stale" note itself outdated), LEDGER_AUDIT (S199 refresh), LEDGER_REPAIR (recovery-complete + DO NOT re-analyze preserved), LEDGER_REPAIR_HOUSEHOLDS (S201), PHASE_42_PATTERNS (S205 changelog), SCHEMA_HEADERS (S206 regen), ROLLOUT_ARCHIVE (frozen), DOCUMENTATION_LEDGER (sunset-flagged). Out of scope (other lanes): Phase plans 33/38/39/40 status drift (research-build); SHEETS_MANIFEST full regen + Drive security key (dedicated session). |
| engine | 2026-04-29 | S185 | Engine-sheet S185 follow-up audit. Closes 3 of the S180/S181 staleness flags + propagates S185-session changes. Fixed (3, commit 1c75362): (a) ENGINE_STUB_MAP regenerated via node scripts/stubEngine.js — picks up DELETE batch (commit bbdca3a) removing 20 unreferenced functions; stamp S156 → 2026-04-29; 154 files / 929 functions. (b) ENGINE_MAP "Last verified" stamp bumped S180/S181 → S185 with engine-sheet S185 touches enumerated (recordWorldEventsv3 v3.6 + DELETE batch). Phase dispatch sequence unchanged. (c) ENGINE_REPAIR frontmatter updated: 2026-04-27 → 2026-04-29. Deferred (1): SHEETS_MANIFEST regen — Business_Ledger row count changed 52→61 this session (S185 9-firms ingest), Simulation_Ledger 911→837 (sheet-hygiene blank-row trim). crawlSheetsArchive.js regen surfaces Drive-wide security finding (live Anthropic API key in personal Drive sheets) noted at original S156 generation; a refresh requires a dedicated session to handle that re-surface, not folded into routine doc audit. S180/S181 plan-file Status drift remains research-build scope: PHASE_38/39/40 plan files still show "Ready to build" / "Parked" status fields that don't match commit reality. Not engine-sheet's lane. PHASE_24_PLAN header still self-corrects engine v3.1/C86 → v3.3/C92 inline (acceptable). INSTITUTIONAL_VOICE_AGENTS four-file architecture reflected (current). Still current: PHASE_DATA_AUDIT (no S185 ctx.summary changes), REVIEWER_LANE_SCHEMA, CYCLE_SEPARATION, ENGINE_CONNECTIVITY_ROLLOUT, PHASE_33_PLAN, phase19_agent_personas. |
| media | 2026-05-08 | S206 | Re-audit (~26 sessions after S180/S181). 28 docs surveyed; 3 stale fixes applied + 4 prior-flagged handoffs still pending media-terminal. Research-build fixes (3): (1) EDITION_PIPELINE.md — header changelog bumped to add S206 routing-foundation entry (Engine A + Engine B emit cols M-R via priorityEngine.js + bylineEngine.js → Story_Seed_Deck applyStorySeeds v3.12; consumer skills sift/write-supplemental/dispatch/interview wired per Phase 4); plus "Four terminals" → "Five terminals (post-S165 — mags added)" architecture-line correction. (2) AGENT_NEWSROOM.md — date stamp S156 → S206; content verified accurate (25 agent dirs in .claude/agents/ matches doc; four-file structure intact across 24 active; engine-validator scope-noted N/A). (3) output/DISK_MAP.md — Last Updated S180/181 → S206 with new S206 artifact families catalogued (routing_diagnosis, routing_root_cause, priority_engine_validation, storyline_binding_evidence, byline_shadow_log) + C93 single-log convention noted (consolidated per S195). Prior-flagged handoffs still pending media terminal (4): 2041_athletics_roster.md S45 stamp (~160 sessions stale, prior S180/S181 audit flagged — unfixed); RICHMOND_ARCHIVE_INDEX.md + ANTHONY_RAINES_PORTFOLIO_INDEX.md + P_SLAYER_JOURNEY_INDEX.md all stamp 2026-02-12 (~85 days, append-only logs that should reflect post-Feb work); story_evaluation.md S144 starter "refine after C92" never refined — post-publish Step 10 still not running per S180/S181 finding (recurring); CANON_ARCHIVE_LEDGER.md is structural reference (not per-edition index — prior S180/S181 audit note "E84-E92 missing" was misframing; doc shape is Structure / Directory Layout / Agent Search Patterns, no episode entries by design — note retracted). Healthy / no-fix (~17): brief_template (S197 fresh), citizen_selection (S170 fresh), MEDIA_ROOM_STYLE_GUIDE (S180/181 fixed S146 cycle reversal), REAL_NAMES_BLOCKLIST (S175 carveout intact), TIME_CANON_ADDENDUM, intake.md, JOURNALISM_AI_OPTIMIZATIONS (v1.2 complete S147), CITIZEN_NARRATIVE_MEMORY, MEDIA_ROOM_HANDOFF, MEDIA_INTAKE_V2.2_HANDOFF, podcast/SHOW_FORMATS, EDITION_PIPELINE_v1_archive (frozen), DESK_PACKET_PIPELINE (SUPERSEDED-flagged), PAULSON_CARPENTERS_LINE (canon-permanent), DRIVE_MANIFEST + GOOGLE_DRIVE_INTEGRATION (no S206 changes to Drive structure), CITIZENS_BY_ARTICLE + ARTICLE_INDEX_BY_POPID (post-publish-built indexes — drift shows post-publish gaps, not doc-layer issue), PLAYER_CARD_INDEX. Note: prior S180/S181 entry below preserved as historical context for the original v2.0 baseline. |
| media | 2026-04-26 | S180/S181 | First full audit under v2.0. 14 docs deep-audited; 10 stale, 2 inconsistent, 1 dead-ref cluster. Research-build fixes applied (4): MEDIA_ROOM_STYLE_GUIDE line 28 cycle-rule reversed to match .claude/rules/newsroom.md S146 reversal; AGENT_NEWSROOM agent count 27→25 + four-file architecture (IDENTITY+LENS+RULES+SKILL) post-S175; REAL_NAMES_BLOCKLIST sports-history carveout note added; DISK_MAP S156 timestamp bumped to S180/S181 with C92 output file inventory. Media-terminal handoffs (6): CANON_ARCHIVE_LEDGER (E84-E92 missing, 2026-03-05 stale), 2041_athletics_roster (S45 stale, cross-check truesource ingest), story_evaluation (S144 starter — "refine after C92" never happened, post-publish Step 10 may not be running), CITIZENS_BY_ARTICLE (2026-02-05, regenerate), DRIVE_MANIFEST (2026-02-23, refs 101 files vs 4 local PDFs), RICHMOND_ARCHIVE_INDEX (2026-02-12). Dead-ref cluster: CANON_ARCHIVE_LEDGER + DRIVE_MANIFEST reference output/drive-files/ archive structure (~377 files claimed) — local has 4 PDFs only. Worth investigating: archive relocated, never local, or cleaned up? Current: EDITION_PIPELINE, TIME_CANON_ADDENDUM, intake.md, brief_template.md (S170 fresh), citizen_selection.md (S170 fresh), JOURNALISM_AI_OPTIMIZATIONS (v1.2 complete), CITIZEN_NARRATIVE_MEMORY, DESK_PACKET_PIPELINE (properly SUPERSEDED-flagged). 10 lower-priority docs not deep-audited this pass (ARTICLE_INDEX_BY_POPID, ANTHONY_RAINES/P_SLAYER portfolio indexes, PAULSON_CARPENTERS_LINE canon-permanent, PLAYER_CARD_INDEX, GOOGLE_DRIVE_INTEGRATION, MEDIA_ROOM_HANDOFF, MEDIA_INTAKE_V2.2_HANDOFF, podcast/SHOW_FORMATS, EDITION_PIPELINE_v1_archive). |
| infra | 2026-05-09 | S212 | Re-audit (~25 sessions after S187). 14 docs surveyed; 4 stale fixes applied + 9 healthy + 1 engine-sheet handoff (preserved from S187). Research-build fixes (4): (1) STACK.md "Last updated" stamp S187/2026-04-29 → S212/2026-05-09 + skill count 43→47 + 4-terminal note (post-S211) + S212 skill-bag bundle reference; (2) STACK.md line 113 "## Skills (41 total, S156)" → "## Skills (47 total, S212)" — 6 additional skills added since S156 baseline; (3) STACK.md line 115 "All 41 skill files" → "All skill files" (count moved to header); (4) FOUR_COMPONENT_MAP.md updated: 2026-04-29→2026-05-09 + line 86 skill count 41→47 + path-scoped rules row expanded to include civic.md / research-build.md NEW S212 + identity.md (always-loaded) — previously listed only engine/newsroom/dashboard. Inline S211 mags-trim note already landed at line 41 (the meta-pattern from /doc-audit plans S212 — content updated but stamp didn't follow; this audit closes that). Healthy (no fix, S187 verifications hold): OPERATIONS.md (PM2 + cron list — verified live: 4 processes godworld-dashboard / mags-bot / moltbook / spacemolt-miner), DASHBOARD.md (40 endpoints — verified dashboard/server.js grep), DISCORD.md, SUPERMEMORY.md, CLAUDE-MEM.md, WORKFLOWS.md, ACTION_MANAGED_AGENTS.md, CANCELLATION.md, RESEARCH.md (recent S206/S207 entries landed). Light/no-fix (3): research4_1 / research4_2 (undated reference docs, content stable per S187), briefing_bloat_audit_2026-04-17.md (research artifact). Engine-sheet handoff preserved from S187: STACK.md line 24 "162 files" Apps Script clasp deploy claim — engine .js count is ~170; precise clasp-deploy count is engine-sheet's lane. |
| infra | 2026-04-29 | S187 | First full audit under v2.0. 14 docs audited; 5 stale, 1 light-update, 7 current, 1 engine-sheet handoff. Research-build fixes applied (5): STACK.md S156→S187 stamp + skill count 41→43 + Simulation_Ledger 761→~837 rows / 47 cols A-AU pointer-to-SCHEMA_HEADERS; FOUR_COMPONENT_MAP.md updated: 2026-04-16→2026-04-29 + "Four terminals"→"Five terminals" + new mags row in §2 environment inventory (S165 fallback terminal); RESEARCH.md System table — 7 row updates (citizens 675→837/47, terminals 4→5, dashboard 31→40 endpoints, containers "5"→"5 active + 1 legacy", workflows "6 session types"→"7 workflow patterns", AutoDream Gemini-2.5-Pro note added, +1 new row for CONTEXT.md vocabulary); MIGRATION_OFF_CLAUDE.md status Active→Research/Watch + tags active→research-watch + updated: bump; CANCELLATION.md Step 2 "5 containers"→"5 active + legacy". Engine-sheet handoff (1): STACK.md line 24 claims "162 files" Apps Script clasp deploy — actual engine .js count is ~170 across phase01-11 + utilities + lib; precise clasp-deploy count is engine-sheet's lane (deploy filter excludes some lib files). Light flag, not blocking. Current (7): OPERATIONS.md (PM2 + cron list matches reality exactly), DASHBOARD.md (40 endpoints verified), SUPERMEMORY.md (6-container framing matches MEMORY.md), CLAUDE-MEM.md (worker port 37777 verified, AutoDream Gemini config matches /root/.claude-mem/settings.json), DISCORD.md (bot v2.10 + Haiku 4.5 + container access matches PM2 + scripts/mags-discord-bot.js), WORKFLOWS.md (post-S165 reframe correctly noted), ACTION_MANAGED_AGENTS.md (Status: Ready to Evaluate matches ROLLOUT). Light/no-fix (3): research4_1.md + research4_2.md (undated reference docs, content stable, audit-light — no SCHEMA frontmatter intentionally per "old docs are fine"); briefing_bloat_audit_2026-04-17.md (research artifact, status active, recommendations live in plans/2026-04-17-briefing-bundle-trim.md). |
| data | 2026-05-09 | S212 | Re-verify (~25 sessions after S187). 6 docs surveyed; 0 actionable fixes / 1 light drift within tolerance / 5 healthy. Live ledger reality verified: node scripts/auditSimulationLedger.js shows 836 rows / 47 cols / max POPID POP-00951; SIMULATION_LEDGER.md says "~837" — 1-row drift since S185, within tolerance. Healthy (no fix): SCHEMA_HEADERS.md auto-regenerated 2026-05-08 (S206) — authoritative; SPREADSHEET.md S187 audit stamp accurate, SCHEMA_HEADERS pointer stays the live source; LEDGER_HEAT_MAP.md S202 refresh per S206 audit ("extremely stale" note retracted); LEDGER_REPAIR.md S94 RECOVERY COMPLETE + DO NOT re-analyze intact; LEDGER_AUDIT.md S199 refresh per S206. All 3 engine-sheet-lane LEDGER_ docs are current per S206 engine audit* — S187's "needs full regen" handoffs all closed by engine-sheet's S199-S202 work. Report only — no edits this audit. |
| data | 2026-04-29 | S187 | First full audit under v2.0. 6 docs audited; 2 stale fixes applied + 3 engine-sheet handoffs flagged + 1 light flag. Research-build fixes (2): SIMULATION_LEDGER.md headline 761→~837 rows + max POPID POP-00951 + S185 trim/S184 +150 context + new authoritative-current-state pointer to LEDGER_AUDIT + S187 audit stamp; SPREADSHEET.md Simulation_Ledger row count 761→~837 in Active Tabs table + audit stamp bump + SCHEMA_HEADERS regen note. Engine-sheet handoffs flagged (3): LEDGER_HEAT_MAP.md (extremely stale C81/S30/2026-02-16 — ~157 sessions stale; bloat rankings + dead-column inventory entirely outdated; needs full regen via engine-sheet); LEDGER_REPAIR.md (S94 RECOVERY COMPLETE intact + "DO NOT re-analyze" rule preserved per skill description; column reference A-AT→A-AU somewhere in body still needs engine-sheet touch; audit-light); LEDGER_AUDIT.md (S181 refresh predates S184 female-balance +150 + S185 trim — headline counts 760 rows / 686 extant / POPID range to POP-00801 are pre-S184; needs scripts/auditSimulationLedger.js re-run from engine-sheet to capture current state with POP-00951 max + ~837 rows). Light flag (1): schemas/SCHEMA_HEADERS.md last regen 2026-04-27 (S181) is pre-S185 sheet-hygiene trim; auto-generated, regen on engine-sheet's schedule, not blocking — per S185 doc-audit tracker entry the regen surfaces a Drive-wide security-key finding from crawlSheetsArchive that requires a dedicated session. |
| plans | 2026-05-09 | S212 | Re-audit (~26 sessions after S186). 31 plan files (10 new since S186). 7 frontmatter tag drifts confirmed + fixed: (1) engine-routing-foundation draft→active (5 of 6 phases closed S206; Phase 6 cutover gated on 3+ cycles shadow-log data); (2) chaos-cars-engine draft→active (per ROLLOUT line 110 S205 "PROMOTED... extracted to active plan" — promotion = active state regardless of whether implementation work shipped); (3) disk-inventory-and-dead-file-detection active→complete (DONE S203 per ROLLOUT, /disk-audit skill shipped end-to-end); (4) phase-40-3-credential-audit active→complete (EXECUTED S156 per ROLLOUT line 302, two commits + smoke tests green); (5) md-audit-skill active→complete (Phase 1+2 shipped S189; Phases 3+4 obviated by zero-orphans finding); (6) vote-trigger-mechanism draft→active (Phase 1 + Phase 2.1 DONE S199 per changelog); (7) run-cycle-gap-log-surface draft→active (Phase 2 SHIPPED S199 — changelog explicitly logged "tag flipped draft → active" but the actual frontmatter edit never landed in the plan file). Meta-pattern surfaced (filed as research-build LOW followup): item #7 specifically — changelog logged intent-to-flip but frontmatter didn't follow. Suggests "update tags when work ships" discipline is informal/easy to miss when work happens at engine-sheet (which doesn't typically touch plan frontmatter). Worth a post-execution gate. No body content drift / no inconsistencies / no dead refs. 24 plans verified accurate (phase-42-writer-consolidation active = in-progress B3-B7, bay-tribune-unified-ingest-rebuild active = blocked-pending-SMFS — frontmatter vocab differs from ROLLOUT state taxonomy by design, memento-cbr active = blocked-on-tuple-gate, discord-bot-edition-currency active = T5-outstanding, boot-load-audit active = ready-for-joint-review, all S186-fixed plans still aligned). Light flag (not actionable): skill-eval-framework / BACKLOG / TEMPLATE have updated: 2026-04-16 ~30 sessions stale but content aligns with ROLLOUT. |
| plans | 2026-04-29 | S186 | First full audit under v2.0. 21 plan files. 6 stale frontmatter tags fixed: phase-38-5/38-6/40-1/40-6 active→complete (DONE S156); world-data-unified-ingest draft→complete (DONE S183); phase-42-writer-consolidation draft→active (S184/S185 progress in flight). 5 stale index entries fixed: matching tag flips on the 5 above + intake-side-citizen-derivation draft→done (file already correct). 4 updated: dates bumped to S156 closure date (2026-04-17) on the four S156-closed plans + 1 to S186 (phase-42). Pointer integrity: 21/21 plans pass; 1 documented forward-ref (Memento → concepts/case-based-reasoning, created by Phase 1 Task 1.1). Light flags: mara-reference-files lacks YAML frontmatter (S105 plan, predates SCHEMA §3, leave per "old docs are fine"); only canon-fidelity-rollout has explicit ## Status section — others rely on frontmatter tags per S145 convention (acceptable). Outstanding: briefing-bundle-trim updated 2026-04-17 with no progress (correctly tagged active, waiting on media-terminal exec — staleness is the work, not the plan). |
| persona | 2026-05-09 | S212 | Re-audit (~25 sessions after S187). 18 docs surveyed; 0 stale in research-build lane / 2 mara-handoff drifts now growing / 1 light flag (Mike's lane) / 16 healthy. S187 prior fixes intact: TECH_READING_ARCHIVE backfill (entries now grow through S207 — Dreaming + Creative Work + Pocock + affaan-m + 2.1.115-119); DAILY_REFLECTIONS Superseded banner intact. Mags-corliss lane (research-build, all healthy): JOURNAL.md 174 entries (+19 since S187, growing); JOURNAL_RECENT.md correct rotation S209/S210/S211 via rotateJournalRecent.js; NEWSROOM_MEMORY.md Last Updated S196 with DJ photo-canon errata logged (Mike's lane); SESSION_HISTORY.md 95 entries, S207 trim rotated S179–S132 in this week; TECH_READING_ARCHIVE.md touched May 8; NOTES_TO_SELF.md last Apr 30; DAILY_REFLECTIONS.md banner-only. Mara-handoff drifts (still pending Mara/Mike, not research-build): AUDIT_HISTORY.md "Last Updated Cycle 84 — 2026-02-25" — was "missing E85-E92" at S187, now missing E85-E93 era (9 editions un-audited; Mara's claude.ai project authority); README.md Feb 26 stamp — Week 2/3/4 plans never landed at S187, still hasn't 73 days later (Mike/Mara to either remove planning section or note deferred indefinitely). Light flag (Mike's lane): NOTES_TO_SELF.md "Editorial Craft Notes (E92 Forward)" anchor edition now 1 stale (E93 PRINT COMPLETE this week); file rule says Mike deletes resolved items, not research-build's lane to edit. Cosmetic note: SESSION_HISTORY has two entries labeled "Session 174" with different dates (2026-04-24 vs 2026-04-25) — append-only history quirk, not load-bearing. No actionable fixes — report only. Other healthy / no-fix mara docs: CIVIC_GOVERNANCE_MASTER_REFERENCE (Apr 9 framework-stable), CIVIC_ELECTION_ENGINE / CIVIC_VETO_IMPLEMENTATION / INITIATIVE_TRACKER_VOTER_LOGIC (all v1.7, framework-stable), MEDIA_ROOM_INTRODUCTION (Apr 15), OPERATING_MANUAL (v2.0 Feb 25 stable), IN_WORLD_CHARACTER (Feb 6 backstory stable), CLAUDE_AI_SYSTEM_PROMPT (Apr 15, S171 rehire verification still pending Mike's lane). |
| persona | 2026-04-29 | S187 | First full audit under v2.0. 18 docs audited; 2 stale fixes applied + 6 mara-vance handoffs flagged + 10 stable/audit-light. Research-build fixes (2): TECH_READING_ARCHIVE.md backfill — last entry was S99 (2026-03-17), 88 sessions stale; appended one consolidated S187 catch-up entry covering S141 (Gemini autodream), S145 (Memento + Hermes), S147 (functional-emotions), S154 (DeepSeek migration test), S170 (outside-AI reviews), S172 (Solo MCP), S177 (Claude Code 2.1.115-119), S187 (Pocock + affaan-m skill steals). Pointer-only per wiki-not-recall rule (S145). DAILY_REFLECTIONS.md — added S187 status banner: superseded since Feb 23, 2026 (S55 era); daily-heartbeat cron disabled per OPERATIONS.md §Disabled; active reflection cron discord-reflection.js writes to JOURNAL_RECENT.md instead (verified via logs/discord-reflection.log showing today's entry "JOURNAL_RECENT.md updated"); historical entries preserved as canon, file not maintained going forward. Mara-vance handoffs (6, audit-light, NOT fixed in research-build): AUDIT_HISTORY.md — last edition mentioned C82-C84 era; missing E85-E92 (~8 cycles); only Mara writes audit history per her claude.ai project authority. CLAUDE_AI_SYSTEM_PROMPT.md — Phase 39.5/S147 reviewer-lane charter present (post-S147), but unverified whether S171 rehire is reflected; Mike's lane (gets pasted into claude.ai project instructions when changed). README.md — frontmatter "Last Updated 2026-02-11"; "What's Next" Week 2/3/4 plans (PublicSupport, council availability, vote history) never landed in 4 months — Mara's framework didn't iterate; either remove the planning section or note Week 2-4 deferred indefinitely. IN_WORLD_CHARACTER.md — stable backstory, Mara's role unchanged, no fix needed. OPERATING_MANUAL.md / CIVIC_VETO_IMPLEMENTATION.md / CIVIC_ELECTION_ENGINE.md / INITIATIVE_TRACKER_VOTER_LOGIC.md — all v1.7-anchored; framework hasn't iterated past v1.7, so version-stale doesn't mean content-stale. CIVIC_GOVERNANCE_MASTER_REFERENCE.md (Apr 9) + MEDIA_ROOM_INTRODUCTION.md (Apr 15) — recent enough, sync with civic-office-ledger left to Mara per her data-source authority. Stable / audit-light (10): JOURNAL.md (Apr 29 fresh, 155 entries growing — verified count via grep without displaying body per S169 rule), JOURNAL_RECENT.md (3 entries match JOURNAL last 3: Entry 153 Thread Holds / 154 Loop Closing Right / 155 Five Hits Gone), SESSION_HISTORY.md (Apr 19 = S178/S179 era, append-only, rotates from SESSION_CONTEXT correctly), NEWSROOM_MEMORY.md (Apr 26 fresh), NOTES_TO_SELF.md (Apr 23, running file), CHARACTER.md (audited in boot group separately), plus the 4 v1.7 Mara civic-engine docs noted above (framework-stable, not Mara-handoff-blocked). |
| Group (S156 scope) | Notes |
|---|---|
| engine | 5 stale, 2 inconsistent, 0 dead refs. ENGINE_MAP "Last verified S120" (21 days stale — no safeRand_ or Phase 38/39/40 refs). ENGINE_STUB_MAP claims 122 JS files, actual 125 — regenerate via /stub-engine. SHEETS_MANIFEST 57 days stale. PHASE_DATA_AUDIT no freshness header, no Phase 40 coverage. DOC_LEDGER 12 sessions stale BUT deprecated per docs/index.md header (folding into index over time). No dead file refs. |
| media | AGENT_NEWSROOM patched (agent count 25+ → 27, desk 6 → 7, builder counts current). DISK_MAP Last-Updated bumped + S156 files noted. DESK_PACKET_PIPELINE stays SUPERSEDED (canonical is EDITION_PIPELINE.md). EDITION_PIPELINE.md (S144) terminal/skill map still accurate. Pipeline-level flag (NOT a doc fix): story_evaluation.md / brief_template.md / citizen_selection.md changelogs have ZERO ### YYYY-MM-DD cycle entries — post-publish Step 10 isn't writing to them. Media-terminal problem, not doc-layer. |
| infra | Re-audited same session after patches landed. Prior pass patched 16 findings; re-verification clean. One remainder found + fixed: CLAUDE-MEM.md §Cost Optimization was TODO text describing Sonnet 4.6 summarizer and 120-session/6,282-observation counts — the switch to Gemini 2.5 Pro free tier happened S141; rewrote section as DONE with the current config pointer. |
| data | Partial — research-build fixed 2 cross-terminal docs. SIMULATION_LEDGER.md: row/column drift fixed (761 rows, 47 cols A-AU per SCHEMA_HEADERS — doc had 46/AT); ClockMode/Tier/Status/Flag sub-counts flagged as stale (S105-S140). SPREADSHEET.md: tab count explained; per-tab row counts flagged stale — SCHEMA_HEADERS authoritative. Ledger docs deferred to engine-sheet. |
Before any judgment-mode auditing, run the existing scanner — free, deterministic, and it scopes your Opus pass to what's actually drifted:
node scripts/mdStalenessDetector.js # → output/md_audit_<DATE>.md (mtime / orphan / dead-ref, ~32s, read-only)
Judgment-audit only the docs it flags (stale-by-mtime, orphan-candidate, dead-ref) plus the group's own one-liner count checks (ls .claude/agents | wc -l, etc.). Healthy-by-mtime docs don't need a full content pass unless their subject code changed this session. This is the gov.38 offload: the scan is deterministic (no model); only the content-drift verdict is judgment. Don't hand-walk ~80 docs in the premium seat when the scanner already ranked them. (Roster + band taxonomy: [[../../../docs/GEMINI_OFFLOAD]] §Job-routing inventory.)
For each doc, extract every verifiable claim and check it:
find / ls / wc -lpm2 listwc -l (boot group especially)Check that docs in the group agree with docs they reference:
.claude/agents/ actual directoriesFlag docs that reference:
After the audit, update the tracker table in this file with the date, session, and any notes.
DOC AUDIT — [group] — [date]
================================================
STALE (needs update):
1. [doc] — [what's wrong] — [what's true now]
INCONSISTENT (docs disagree):
2. [doc1] says X, [doc2] says Y — [which is correct]
DEAD REFERENCES (doc points to something that doesn't exist):
3. [doc] references [path/script/tab] — doesn't exist
================================================
Docs audited: N
Stale: N | Inconsistent: N | Dead refs: N
Next group due: [group name]
/doc-audit boot — after any session that changes boot files (CLAUDE.md, identity rules, canon files, MEMORY.md, SCHEMA, index)/doc-audit engine — after engine code changes, phase plan completion, deploys/doc-audit media — after edition pipeline changes, post-publish criteria updates, new desk reporters/doc-audit infra — after service/infrastructure changes/doc-audit data — after sheet structure changes or ledger maintenance/doc-audit plans — after any plan-tracked phase completes (highest cadence — every 2-3 sessions)/doc-audit persona — after Mara/Mags character or governance updates (lower cadence — every 8-10 sessions)/doc-audit — every 5 sessions, rotates to oldest groupThe current 7-group structure is a surgical patch over the original 5-group v1.0. Long-term, the /md-audit skill ([[archive/plans/2026-04-21-md-audit-skill]]) will handle existence-staleness (orphan MDs, mtime drift, broken inbound links) — complementary to this skill's content-staleness focus.
Option B (deferred to next major refactor): replace fixed groups with frontmatter-driven audit cadence. Each doc declares its own audit_cadence: field (e.g., every-session, weekly, monthly, on-change); /doc-audit reads frontmatter across docs/, computes overdue set, audits whatever's stale. Converges with /md-audit (both walk frontmatter); eventually they merge into a single /audit skill with content + existence checks.
When /md-audit lands, revisit whether this skill should:
/md-audit into unified frontmatter-driven /auditAfter every group run, append a row to [[../../docs/AUDITS]] Run history table:
/doc-audit <group>), findings (1-line: drift count + severity), action taken (fixes applied: N or report only), artifact path (commit hash if fixes shipped, else session note).