| 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). |
