@chrono-meta/fh-gate 1.4.53 → 1.4.55

package/.claude-plugin/marketplace.json

@@ -11,13 +11,13 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "1.4.53",
+      "version": "1.4.55",
       "description": "Hub meta-operations toolkit — 33 skills + 7 agents. New in 1.4.53: `fh-codex-doctor` (npm bin) — Codex adapter drift scanner; reads the documented M1/M2/M3 skill tier map + skill/agent source and reports codex-native/adapter-required/claude-native/unclassified per unit, wired into `npm test`/`prepublishOnly` (fail-closed on unclassified Claude-native primitives). New in 1.4.49: steel-quench gains Step 0.6 Verdict-Invariance Probe (groundedness axis — a load-bearing judged gate's verdict must track behavior, not rubric phrasing; measured flip-count over cross-family paraphrases; arXiv:2605.06161 Policy Invariance anchor); multi_model_sidecar_strategy §Vendor-native harness (a model is strongest in its own vendor CLI — Claude/CC, GPT/codex, Gemini/Antigravity; a universal router degrades all of them, so it stays an autocomplete/QA sidecar, never orchestration); predelete_check.sh fail-closed rewrite; memory-hygiene A-TMA anchor. New in 1.4.48: phantom-quench + steel-quench gain external frontier anchors (arXiv:2607.02052 package-hallucination; arXiv:2607.02057 prompt-coverage-adequacy); README model-flat claim reframed from a per-release point-curve to structural invariants (operation flattens across tiers; depth tier-order fixed within a generation). New in 1.4.47: onboarding step ① surfaces the Mode D companion-store session-start load in the auto-read salience anchor (previously only in the local binding + rules, so a greeting could skip the load). New in 1.4.46: context-doctor command-output axis (route to rtk/proxy for verbose CLI stdout, complementing .claudeignore; risk-gated to token-scarce envs). New in 1.4.41: context-doctor 2026 trigger vocab (context engineering/rot/collapse) + phantom-citation hardening; hub measurement-integrity-checklist (cross-model measurement pre-flight: display-name pin/reps≥3/discriminating probe). New in 1.4.40: install-wizard queryable-wiki scaffold (INDEX + session-start read + R/W/C ingest). New in 1.4.39: auto-decorrelation (cross-family verifier sidecar recruitment) + video-ingest (capability-routed video ingestion). New in 1.4.x: verify-axis check-class taxonomy (mandatory-pass/measured/judged), no-reinvention Tier-0 inventory, 7-class failure taxonomy, Destructive-Op Gate, Wave-T (Temper), tier-floor governance, Mode D Model Notice, FC consent lane, default-Sonnet guidance. New in 1.3.0: public-surface-audit, field-harvest Mode B auto-trigger, 4-axis gate scope ext. Validated cross-CLI: Claude Code, Codex, Gemini.",
       "source": "./plugins/fh-meta"
     },
     {
       "name": "fh-commons",
-      "version": "1.4.53",
+      "version": "1.4.55",
       "description": "Project-agnostic utility skills — 4 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate) + 1 agent (quench-challenger). Domain-independent utilities transplantable into any project.",
       "source": "./plugins/fh-commons"
     }

package/CATALOG.md

@@ -89,7 +89,7 @@ Cloud session (Mode D, ext): new field template — external-MCP tool gating wit
 - Decision: prefer host-native per-tool permission config as enforcement; this template = what-to-gate + portable fallback. §6 install row is conditional (MCP present); the proactive mount-intent trigger is the load-bearing path.
 
 ### 2026-06-11 | forge-harness | #identity-marker, #door-skeleton, #target-tier-sim, #below-floor-consumer, #false-control-kill
-**File:** CLAUDE.md §Active Onboarding (+ fh_detail_protocols.md, scripts/below_floor_scan.sh, .claude/rules/operations.md)
+**File:** CLAUDE.md §Active Onboarding (+ fh_detail_protocols.md, scripts/below_floor_scan.sh, knowledge/shared/rules/operations.md)
 Cloud session (Mode D): 🐿️ marker folded into the returning-user door skeleton — one salience unit with the menu, closing the sonnet-sim marker-drop residual (`fh_signal_2026-06-11`); verified by blind sonnet Agent sim PASS (verification tier = failure tier; in-session model-pinned dispatch available in cloud, no headless fallback needed). 6/15 billing one-line amendment rode the same CLAUDE.md edit (no churn commit). below_floor_scan.sh ships as the standing consumer the pre-commit hook promised ("weekly audit re-queues below-floor markers") but never had — resolution via `floor-rerun:`/`floor-writeoff:` marker appends, wired as weekly Phase 1.5 step 2.
 - Decision: ack rubber-stamp (card item 4) closed via route-around — build the re-run consumer, leave the ack untouched (per opus-challenger verdict on the reverted regex attempt).
 - Decision: opus challenger PASS 0S+3B — marker-append/hook-collision replicated CLEAN; P9 check: "builds the control, not paper-over".
@@ -161,7 +161,7 @@ Backlog cleanup (cloud session 2): goal-quench phantom vocab fixed — "steel-qu
 - Open: npm 1.4.8 republish ships plugin.json/README/SKILL.md count+phantom fixes (folded into the open laptop handoff).
 
 ### 2026-06-10 | forge-harness | #credit-economy, #operator-intake, #lightweight-triage, #frontier-digest
-**File:** plugins/fh-meta/skills/frontier-digest/SKILL.md (+ .claude/rules/sister_asset_protocol.md)
+**File:** plugins/fh-meta/skills/frontier-digest/SKILL.md (+ knowledge/shared/rules/sister_asset_protocol.md)
 Credit-economy engine run #2 formalization (operator-approved; this session = manual run #2: 7 walled sources → 8 audits → 15 same-day gate-passed imports, 2 human corrections): R1 — frontier-digest Step 0.5 operator-intake asks for walled-channel sources (YouTube/LinkedIn/X, machine-403) on cadence runs only, skippable, try wall-bypass (WebSearch + secondary) first. R2 — sister protocol lightweight path: dedup-hit/no-increment sources get a one-paragraph entry, full cross-audits reserved for A/B-tier.
 - Decision: the operator stays the wide-net sensor for walled channels by design (human = scarce oracle), the machine owns endurance (triage→gate cycles); intake cost discipline keeps the wide net wide.
 - Follow-up (same day): Step 0.5 video-harvest ladder — Tier 1 sidecar (codex / Gemini-route, agentic = approval-mode first) → Tier 3 Claude+yt-dlp transcript → operator floor; laptop verification trio handed off. First applied instance of the capability-probe principle.
@@ -187,7 +187,7 @@ CC built-ins utilization imports (operator-approved; video claims verified 9/13
 - Decision: built-in beats plugin install at ~80% coverage; FH native beats built-in only when it adds governance.
 
 ### 2026-06-10 | forge-harness | #ingest-gate, #contradiction-scan, #crossref-lint, #llm-wiki, #karpathy
-**File:** .claude/rules/sync_push_protocols.md (+ harness-doctor SKILL.md, probes.md)
+**File:** knowledge/shared/rules/sync_push_protocols.md (+ harness-doctor SKILL.md, probes.md)
 Karpathy LLM-Wiki sister-audit imports (operator-approved; convergence case n=5, citable primary source): I1 — contradiction scan as Sync step 3 (ingest gate, judged + verify-bidirectional pair): new knowledge grepped against existing claims before indexing, conflicts flagged in both files, old-claim removal is HITL. I2 — harness-doctor L4 knowledge cross-ref lint: no CATALOG entry = S-tier index orphan, no inbound ref = R-tier orphan page. Probes G-SYNC-01/G-LINT-01 added (30 total).
 - Decision: scale escape (W1) deliberately NOT built — watch-item with trigger (CATALOG hundreds of entries / repeated search misses); operator-preferred first remedy = salience-splitter-style CATALOG split-mapping, RAG hybrid only after that.
 - Open: npm republish (harness-doctor SKILL.md shipped) — folded into the open 1.4.8 handoff.
@@ -283,7 +283,7 @@ PR #64: Added scope-driven sidecar routing (Step D) to goal-quench Phase 1.5: ta
 - Decision: overhead multiplier documented as empirical calibration constant; sidecar routing is scope-signal-driven, not mode-locked
 
 ### 2026-06-03 | forge-harness | #goal-quench, #non-coercive, #companion-store, #ephemeral-handoff
-**File:** .claude/rules/modes_and_value.md
+**File:** knowledge/shared/rules/modes_and_value.md
 Formalized two non-coercive guidances: companion-store recommendation conditioned on accumulating context into meta-harness without a local fork; ephemeral-environment handoff rule made mode-agnostic (Mode D → companion-store handoff/, all others → committed note or PR comment in working repo).
 - Decision: single-source preserved — rule lives in public mirror; companion store holds only outputs, never a rule copy
 

package/CLAUDE.md

@@ -21,9 +21,20 @@ Running Claude Code in this project activates **Control Tower** mode.
 
 The forge-harness hub is not just a repository — it is the **command center for all Claude Code-connected projects in your local environment**.
 
+**Doctrine (2026-07-12, operator-forged)**: a harness **machinizes intent** — it reads the human's
+intent and forges it into a machined form (AI-followable rules or deterministic code), via
+`intent → forge → agreement (HITL) → machinery`. Its payoff is relocating trial-and-error off the human
+(into the harness, run in parallel), so human time drops and attention routes to irreversible points.
+FH is the **meta-harness and nursery**: it incubates field harnesses (projects *and* new capabilities of
+existing harnesses) in its own sandbox — expensive per run, cheaper in total because trial-and-error
+pools and compounds — and **emits** them as independent specialized harnesses (shipped today as
+scaffold + approval machinery; the full chamber flow is the named target). Over other harnesses it
+operates in two modes: **compose** (cluster strengths) ∪ **disrupt** (melt and reforge via crucible;
+core invariants never melt). Full doctrine: `knowledge/shared/harness-core/harness_incubator_doctrine.md`.
+
 | Layer | Role | Representative Assets |
 |---|---|---|
-| **① Control Tower** | Coordinates all connected projects and **drives harness-ification across them** — decides *which* projects to harness and *when*, propagates harness assets to each, and feeds their synced learnings into the hub's compounding loop. The *how* (rules · gates · 6-axis) is executed via the Core Axis. Command HQ, not a passive registry. | `.claude/rules/auto_project_mapping.md` (mapping + **Full-Harness Mode**) · `harvest-loop` (compounding loop) · `templates/` (project-harness bundle) · `CATALOG.md` |
+| **① Control Tower** | Coordinates all connected projects and **drives harness-ification across them** — decides *which* projects to harness and *when*, propagates harness assets to each, and feeds their synced learnings into the hub's compounding loop. The *how* (rules · gates · 6-axis) is executed via the Core Axis. Command HQ, not a passive registry. | `knowledge/shared/rules/auto_project_mapping.md` (mapping + **Full-Harness Mode**) · `harvest-loop` (compounding loop) · `templates/` (project-harness bundle) · `CATALOG.md` |
 | **② Frontier → Org Propagation** | Proactively applies global AI/harness frontier thinking and **translates it for your organization**. | `knowledge/shared/harness-core/harness_frontier_diagnosis_*.md` · `knowledge/{your-org}/` |
 | **③ AI Collaboration Guide** | Accumulates and distributes best practices for token efficiency and dialogue methodology — "how to ask, delegate, and record". | `CHEATSHEET.md` · `knowledge/shared/dialogue/ai_dialogue_playbook.md` · `MEMORY.md` intent-based + associative recall (`knowledge/shared/dialogue/memory_intent_recall.md`) |
 | **Core Axis** | **Harness Engineering (How)** — the methodology and practice axis that realizes the three layers above. The 6-axis framework is the operating unit. **A harness is a means, not an end** — Field harness: "simpler over time" (complexity = warning signal). Meta-harness: *optimize*, not necessarily simplify — complexity earns its scope; red flags are orphaned, redundant, and decorative units, not complexity itself. | `harness_6axis_framework.md` · `hub_compounding_loop.md` · `claude_code_runtime_flow.md` · `.claude/agents/` (sub-agents) |
@@ -49,6 +60,18 @@ Two orthogonal layers — never collapse them.
   self-correct over agreeing (governor-catch). Tone never touches this.
 - **Speech / reaction layer (soft)**: choose warmer words and a steadier texture. Softness is
   word-choice, not length — it adds no filler and lengthens nothing.
+- **Register — match the user's language *and* register (applies to EVERY response, not just greetings)**:
+  reply in the user's language and in their register (formal ↔ informal). **Consistency is the rule, not
+  the default**: do NOT drift between formal and informal — Korean 반말↔존댓말, English casual↔corporate —
+  within a turn, across turns, or across a session. Register drift is a UX defect and dilutes the mascot
+  identity. If unsure which register a session is in, match the user's most recent message. The
+  Orthogonality guard below applies to register too (a warmer register never softens judgment). This rule
+  lives in always-loaded CLAUDE.md, not only in memory, so it fires every turn without depending on
+  recall — the 2026-07-12 miss was a session that drifted register because the rule lived only in memory.
+  Tone has **no** mechanical hook gate by nature: always-loaded salience is the strongest available lever,
+  **not a floor** (no mechanical floor exists for tone — an accepted limitation, not a guarantee). The
+  operator or project may pin a concrete default register in a local binding (`CLAUDE.local.md` / UAP
+  `preferred register`) — that pin is operator taste and stays local, never in this public file.
 - **Not flattery**: soft charisma is not pleasing the user. Disagree plainly when the work calls for it;
   warmth and a "no" coexist (no Gemini-grade sycophancy).
 - **Greeting / onboarding**: open with a warm, identity-revealing welcome (new / returning / operator
@@ -61,7 +84,7 @@ leaked into the judgment layer and the response is wrong, not warm.
 
 ## New Project Onboarding
 
-> Detailed procedure: `.claude/rules/auto_project_mapping.md` (5-step mapping + §6 Full-Harness Mode)
+> Detailed procedure: `knowledge/shared/rules/auto_project_mapping.md` (5-step mapping + §6 Full-Harness Mode)
 
 1. `mkdir tracks/{project_name}/` — track name = project root name
 2. Hub common principles outrank project rules (scope hierarchy)
@@ -174,7 +197,7 @@ that skill class, and not a retroactive sweep of all routers.
 
 ## FH Improvement 4-Axis Auto-Gate (Self-Verification Orchestrator)
 
-**Whenever the AI modifies FH assets** (SKILL.md · `.claude/rules/*.md` · `templates/` · `CLAUDE.md` · substantive `knowledge/` docs · substantive `docs/*.md` · `AGENTS.md` — see Substantive carve-out below),
+**Whenever the AI modifies FH assets** (SKILL.md · `.claude/rules/*.md` · `knowledge/shared/rules/*.md` (relocated protocol rules — always full-gate, NOT under the knowledge carve-out) · `templates/` · `CLAUDE.md` · substantive `knowledge/` docs · substantive `docs/*.md` · `AGENTS.md` — see Substantive carve-out below),
 the 4-axis verification chain runs **automatically before the first commit** of that session.
 No user request is needed — this is a mandatory autonomous step, not a proposal.
 
@@ -401,7 +424,14 @@ let the innovator center a recommend cascade, produce a ranked install plan, and
    `CLAUDE.md`, mapped `tracks/`, **locally-connected sibling repos** (the env-delta SessionStart hook already
    emits "N unmapped sibling repos"), and the `LOCAL_SKILL_REGISTRY` + stack/language. Then **branch**:
    *new-build* (no prior harness) · *extend-existing* (harness present → found→extend, never fork) ·
-   *maintain* (mature harness → route to the Field-Harness Diagnostic instead). This audit-and-branch pre-step
+   *maintain* (mature harness → route to the Field-Harness Diagnostic instead).
+   **new-build sub-branch — simulate-first (incubator doctrine)**: judge the project's character before
+   building. Clear · small · low failure-cost → build immediately (current flow). Uncertain · exploratory ·
+   failure-expensive → **recommend simulate-first**: run the project as a simulation inside the FH chamber
+   (harness-unit sandbox) and *emit* the initial project only after the simulation holds — one-line
+   recommendation, operator decides (HITL; never forced). Same branch applies to a **new capability of an
+   existing harness** (incubate in the chamber, then transplant). Rationale + economics:
+   `knowledge/shared/harness-core/harness_incubator_doctrine.md §3`. This audit-and-branch pre-step
    is imported from the revfactory/harness Phase-0 State Audit (sister-audit 2026-07-07) — it tightens FH's
    found→extend reflex and is the "이미 로컬에 연결돼 있으면 자동 탐색" mechanism.
 2. **Innovator-centered recommend**: `persona-innovator` centers the cascade (Mode I on acceleration / Mode F
@@ -638,6 +668,7 @@ At session start, determine the last run time from history files and auto-propos
 |---|---|---|
 | `/frontier-digest` | `tracks/_meta/frontier_digest_*.md` | Propose at session start if 7+ days since last run |
 | `/harness-doctor` | `tracks/_meta/*harness_doctor*.md` | Propose at session start if 30+ days since last run |
+| Weekly audit (`/harvest-loop` lightweight) | `tracks/_audit/weekly_audit_*.md` | Propose at session start if 7+ days since last run (incl. `below_floor_scan.sh` step — detail: `knowledge/shared/rules/operations.md`) |
 
 > A cadence reminder the user has repeatedly declined is **muted** per the UAP (see the loop below) — don't re-nag.
 
@@ -654,7 +685,7 @@ Some proposals are not *time*-overdue — they fire **once when a specific work
 
 ## Operational Adaptation Loop — User-Tuned Self-Optimization
 
-> Detail: `.claude/rules/operational_adaptation.md`
+> Detail: `knowledge/shared/rules/operational_adaptation.md`
 
 Self-healing is not only FH-self-dev (Mode D 4-axis) and reactive (`verify-bidirectional`). A **standing, per-user operational loop** tunes FH behavior to the individual during normal field use, and escalates **only generalizable** learnings to the `field-harvest` → FH-origin PR funnel — idiosyncratic taste stays local (drift guard).
 
@@ -681,6 +712,11 @@ Default operation is a **standard interactive session**. Agent dispatch (single
 
 Mapped paths: check `auto_project_mapping.md` or `find ~/projects -maxdepth 1 -type d` for actuals.
 
+**Invocation log obligation (always-loaded — do not rely on recall)**: immediately after any custom
+sub-agent invocation, append to `knowledge/shared/learnings/subagent_invocations_log.yaml` (8 fields ·
+outcome: `accepted`/`partial`/`rejected`/`sustained` — `sustained` = decided NOT to invoke, also recorded).
+This feeds the 60/40 promotion gate + UAP loop; detail: `knowledge/shared/rules/operations.md`.
+
 ### Context Card — Required Format for Dispatch
 ```
 [Session Context Card]
@@ -721,11 +757,11 @@ Tiers: S=light(~5K) · M=standard(~15K, FH default) · L=full(~30K) · XL=max(~6
 
 **Current: Beta → External Validation Achieved** — v1.0 formal release conditions: additional external install evidence + at least 1 external PR.
 
-> Usage modes (A/B/C) + what-you-get (Layer 1/2) details: `.claude/rules/modes_and_value.md`
+> Usage modes (A/B/C) + what-you-get (Layer 1/2) + **ephemeral-session handoff rule** (leave a surfaced handoff in a durable location before an ephemeral/cloud session ends): `knowledge/shared/rules/modes_and_value.md`
 
 ## Auto Project Mapping Protocol
 
-> Detailed procedure: `.claude/rules/auto_project_mapping.md` (5-step mapping + §6 Full-Harness Mode)
+> Detailed procedure: `knowledge/shared/rules/auto_project_mapping.md` (5-step mapping + §6 Full-Harness Mode)
 
 When the user requests **"connect a project"** · **"link to hub"** · **"map this project"** · **"scan parent directory and connect"**, follow the `auto_project_mapping.md` protocol. When they request **"harness-ify this project"** · **"full harness setup"** · **"프로젝트 하네스화"** (or accept the post-mapping promotion prompt), run **§6 Full-Harness Mode** — installs project-local harness assets (session rules · context filter · env card) from `templates/`, approval-gated and non-overwriting. (The FH self-gate is FH-internal and is not installed into projects.)
 
@@ -799,17 +835,17 @@ Card update is NOT a sub-step of harvest-loop — even if harvest-loop is skippe
 
 ## Session Sync / Knowledge Push Protocol
 
-> Detailed procedure: `.claude/rules/sync_push_protocols.md`
+> Detailed procedure: `knowledge/shared/rules/sync_push_protocols.md`
 
 When the user requests "sync", "save session", etc., follow the `sync_push_protocols.md` protocol. CATALOG.md format, tag conventions, and track mapping are also referenced in that file.
 
 ## Sister Asset Protocol
 
-> Detailed procedure (3 steps · restrictions · branch sync): `.claude/rules/sister_asset_protocol.md`
+> Detailed procedure (3 steps · restrictions · branch sync): `knowledge/shared/rules/sister_asset_protocol.md`
 
 When a sibling asset on the same topic is discovered (internal team or external frontier), follow `sister_asset_protocol.md`. Keep the detection threshold low — the goal is to close awareness gaps.
 
 ## Operations Reference
 
-> CATALOG.md format · tag conventions: `.claude/rules/sync_push_protocols.md`
-> Sub-agent operations · weekly improvement cycle · maturity 3-phase roadmap: `.claude/rules/operations.md`
+> CATALOG.md format · tag conventions: `knowledge/shared/rules/sync_push_protocols.md`
+> Sub-agent operations · weekly improvement cycle · maturity 3-phase roadmap: `knowledge/shared/rules/operations.md`