@chrono-meta/fh-gate 3.1.3 → 3.2.0

package/.claude/rules/fh_4axis_gate.md

@@ -45,7 +45,7 @@ paths:
 
 ## FH Improvement 4-Axis Auto-Gate (Self-Verification Orchestrator)
 
-**Whenever the AI modifies FH assets** (SKILL.md · **`SKILL_detail.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` · `scripts/**/*.sh` · agent definitions (`plugins/*/agents/**/*.md` · `.claude/agents/**/*.md`) — see Substantive carve-out below),
+**Whenever the AI modifies FH assets** (SKILL.md · **`SKILL_detail.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` · `scripts/**/*.sh` · `scripts/**/*.py` (🟥 `.py` since 2026-09-07 — shipped python under scripts/ was unclassified; 7 shipped files sat outside the gate, `fh_signal_2026-09-07_gate-python-blindspot.md`) · agent definitions (`plugins/*/agents/**/*.md` · `.claude/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.
 

package/.claude-plugin/marketplace.json

@@ -11,19 +11,19 @@
   "plugins": [
     {
       "name": "fh-meta",
-      "version": "3.1.3",
+      "version": "3.2.0",
       "description": "New in 2.2.0: BREAKING (gate): chamber step 6 now reads ACTUAL.md, not BUDGET.md — an in-flight chamber run whose actual cost sits in BUDGET.md blocks until the ACTUAL: line moves to tracks/_chamber/<slug>/ACTUAL.md (the runner prints the path). Why: BUDGET.md's pre-verdict hash IS the ordering witness, and step 6 hard-blocked until that same file changed, so every run that reached COMPLETE necessarily mutated a witnessed artifact and verify returned TAMPERED — the chamber's promotion condition was unsatisfiable by construction, not by strictness. Two roles (immutable witness / post-verdict calibration sink) had collided in one file; each was correct alone, so neither side's code showed the conflict. Also: ko-tech-writer Step 2/4-b scans are now calibration-backed (known-pair fixtures + reproducible command, shipped) — discrimination is proven, 'zero residue' is explicitly NOT; chamber lane suite 12 -> 33 including the runner x witness seam no test covered; chamber_run.sh now teaches the two-commit discipline (gate hashes and verdict hash must land in separate commits/PRs — it previously advised the opposite). New in 2.1.0: BREAKING (gate): `crossfamily: declined` in an Axes 2-3 marker now requires grounds naming a record path that RESOLVES on disk — bare `declined`, and `declined` justified by author judgment, are blocked at commit. Remedy: cite where the operator decision lives (e.g. `.. — operator declined sidecars, per knowledge/shared/rules/operational_adaptation.md`), or use `DEGRADED_PANEL_UNUSED` if a panel was reachable and you chose not to recruit it — which is what author judgment actually is. `declined` was the only enum value with no grounds requirement; a cross-family review then broke the first (vocabulary-grep) fix three ways — self-validating on the value's own token, vacuous keyword passes, and over-blocking real declinations in natural prose — so the check asserts a resolvable record instead of words. Also: standpoint axis gains `tier1b` (a STATIC read of a target repo, executed nothing) plus a decide-in-order procedure, after blind floor-tier sims graded pure cold-reads as `tier2` three rounds running; steel-quench Wave 1's sixth angle (gate-locality) gains the output-template row it never had, so a mandatory angle stops being structurally unreportable; verify-bidirectional gains category 5 (prescriptive doctrine statement); Sister Asset Protocol gains an active-adoption trigger; new resident doctrine — Mechanization Boundary, Local Execution First, Skeleton-not-Muscle, Expedition track, and this package's versioning policy. Hub meta-operations toolkit — 35 skills + 7 agents. New in 2.0.1: harness-doctor cadence hook, portability lint wired into pre-commit, branch_claim.sh claim-count-vs-tree-count warning, louder confidentiality-scan fail-open notice, fh-gate.sh missing-package.json survival, identity ① reclassified 🟢 (cross-harness adapters + relay argument channel). 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": "3.1.3",
+      "version": "3.2.0",
       "description": "Project-agnostic utility skills — 5 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate · ko-tech-writer) + 1 agent (quench-challenger). Domain-independent utilities transplantable into any project.",
       "source": "./plugins/fh-commons"
     },
     {
       "name": "fh-qp",
-      "version": "3.1.3",
+      "version": "3.2.0",
       "description": "QP (Quality Platform) — the generic edition of a field QA harness's Prepare→Automation→Regression loop as an FH plugin: 4 skills (qp router · qp-plan · qp-run · qp-regress) + qp_tools.sh (target-class · adapter-probe · mask · surface-reach · mtm-check · run-verbs, typed exit codes) + a zero-domain-constant profile slot + 29 known-pair lanes. Drives web targets through the session's Playwright MCP and desktop targets through computer-use MCP (mobile deferred); calls a registered qasp typed capability when one exists (strictest-wins) — none is registered today, so the MCP fallback is the first edition. Verdict contract: a MACHINE closure requires a recorded assertion; a failed first step is attributed BLOCKED, not FAIL; surface_reach counts every TC in the denominator. Born as chamber run #18 (EMIT, 2026-09-05).",
       "source": "./plugins/fh-qp"
     }

package/AGENTS.md

@@ -120,6 +120,12 @@ Because non-Claude runtimes do not auto-load Claude path rules, apply these rule
    require instrument suspicion.
 6. **Irreversible intent:** before publish, delete, or history rewrite, read and apply the
    Pre-Publish or Destructive-Op gate in `CLAUDE.md`. `pre-push` is only the git-side backstop.
+   **An automated verdict never clears an irreversible gate on its own, whatever its measured error
+   rate.** Surface class decides, not the number: a wrong finding on a review surface costs a reader
+   a minute, while on publish/delete/rewrite the wrong call is the whole loss. So improving a verdict
+   engine's score is not a route to promoting it onto an irreversible surface — the terminal step
+   stays a human or an explicit logged override. This matters here because a non-Claude runtime
+   reading this file is itself often the verdict engine in question.
 7. **Self-contrast on asset touch:** the trigger for the three-layer self-contrast (process ·
    engines · identities) is *touching an FH/PMH asset*, not being asked. Pick verification axes by
    failure mode — running all six every time is not the rule. Record, in the existing Axes 2–3

package/CLAUDE.md

@@ -41,7 +41,7 @@ core invariants never melt). The nursery also **verifies what it births**: harne
 | **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 프런티어 답습 · Frontier absorption** | 확신이 안 서는 자리에서 **책장(우리가 이미 가진 것) → 도서관(세상이 이미 만든 것)** 순으로 먼저 뒤진다. 목적은 **재발명 차단**이지 외부 인용으로 똑똑해 보이는 것이 아니다. | `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` · `plugins/*/agents/` (sub-agents) |
+| **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.<br>**And what it is a means *to* is Governance Engineering (What for)** — 🐿️ *«수치를 목표로 움직이되, 그 수치가 게이트를 열지는 않는다»*: drive the error rate toward 0.x% **and** hold the surfaces where no number buys passage. Two verbs, and the second one carries the load — drop it and the discipline decays into "lower the number and the gate opens", which §Irreversibility Gates forbids by name. Measured content, not a slogan: five review arms ran **2.7 %–13.6 %** claim-error on the same eight cases — every one usable on a review surface, **not one** usable on publish/delete/rewrite. That distance is why this axis exists. Canon: `governance_engineering_definition.md` (operator formulation 2026-09-09; the term exists in IT/data governance — what is ours is the referent, and an outbound claim of novelty owes a stated delta, never mere absence of prior use). | `harness_6axis_framework.md` · `hub_compounding_loop.md` · `claude_code_runtime_flow.md` · `plugins/*/agents/` (sub-agents) |
 
 > **번호가 둘이다 — 이 표의 ①②③ 은 «3층 미션»이고, 정체성 등급표의 ①~④·Ⓑ 는 «5대 정체성»이다.**
 > 같은 것을 다르게 세는 게 아니라 **다른 분류**이므로 번호가 어긋나도 모순이 아니다. 여기 **②**(프런티어 답습)는
@@ -570,7 +570,7 @@ Every new `SKILL.md` must clear a **6-item bar** (role-duplication via `/asset-p
 
 ## FH Improvement 4-Axis Auto-Gate (Self-Verification Orchestrator)
 
-**FH 자산을 수정하면**(SKILL.md · **SKILL_detail.md** · `.claude/rules/*.md` · `knowledge/shared/rules/*.md` · `templates/` · `CLAUDE.md` · substantive `knowledge/`·`docs/*.md` · `AGENTS.md` · **`scripts/**/*.sh`** · **에이전트 정의**(`plugins/*/agents/**/*.md` · `.claude/agents/**/*.md`)) **4축 검증 체인이 그 세션 첫 커밋 전에 자동 실행된다.** 사용자 요청 불요 — 제안이 아니라 의무 단계다.
+**FH 자산을 수정하면**(SKILL.md · **SKILL_detail.md** · `.claude/rules/*.md` · `knowledge/shared/rules/*.md` · `templates/` · `CLAUDE.md` · substantive `knowledge/`·`docs/*.md` · `AGENTS.md` · **`scripts/**/*.sh`** · **`scripts/**/*.py`**(`.py` 는 2026-09-07 부터 — 그 전엔 출하 파이썬 7개가 게이트 밖이었다) · **에이전트 정의**(`plugins/*/agents/**/*.md` · `.claude/agents/**/*.md`)) **4축 검증 체인이 그 세션 첫 커밋 전에 자동 실행된다.** 사용자 요청 불요 — 제안이 아니라 의무 단계다.
 
 **기계층 — 무엇이 실제로 막는지 나눠서 말한다(2026-08-04 실측).** `git commit` 은 `templates/.git-hooks/pre-commit` 이 **하드 차단**한다: 축이 전부 PASS 할 때까지 커밋이 안 되고, 아래 상세가 로드되지 않아도 훅이 막는다 — 이 산문은 훅 위의 살리언스 층이지 유일 floor 가 아니다. 다만 **훅은 클라이언트측이고 `--no-verify` 로 우회된다**(§Integration branch 가 이미 그렇게 말한다 — 두 곳이 어긋나 보이던 것을 여기서 맞춘다). **그리고 서버측 검증엔 남은 잔여가 있다(2026-08-12 재확인 — `contexts=[]` 서술은 stale, 정정됨)**: `main` 은 `enforce_admins: true` 로 **푸시 경로**(PR 경유)를 강제하고, legacy `required_status_checks.contexts` 는 **`["validate"]`** — `validate` 잡(`.github/workflows/validate.yml`, 메타데이터·`selfcheck.sh` 배선 레인)이 실제 **필수 체크**다. ⚠️ **`validate` 는 Axis 1 이 아니다** — Axis 1(`regression-guard.yml` → `templates/regression_guard.sh`)은 여전히 필수 체크가 **아니고**, 그 워크플로의 `paths:` 필터가 `SKILL.md`·`.claude/rules/*.md`·`CLAUDE.md`·`templates/*.md` 만 보므로 이 절이 4축 대상으로 나열한 `knowledge/shared/rules/*.md`·`docs/*.md`·`AGENTS.md`·`scripts/**/*.sh`·에이전트 정의·`SKILL_detail.md` 만 바뀐 PR 에는 **Axis 1 자체가 돌지도 않는다**. `validate` 쪽 남은 갭은 `strict: false`: 그 체크는 PR 브랜치에 푸시할 때마다 재실행되지만(오픈 시점 한정이 아니다), 그 뒤 main 이 움직여도 재검증을 강제하지 않으므로 **초록으로 남아 있는 체크가 실제로 병합되는 최신 트리를 본 적이 없을 수 있다.** 즉 서버가 강제하는 건 *체크가 초록인가*지 *그 체크가 지금의 main 을 봤는가*가 아니다. Axes 2–3(마커)·Axis 4(매니페스트)는 그 파일들이 `tracks/**` 로 gitignored 라 CI 가 **구조적으로 볼 수조차 없다**. 정직한 표현은 "하드 차단"이 아니라 "**가용한 가장 강한 층**"이다. **미해결 잔여**: `strict` 를 켜는 것도, Axis 1 을 필수 체크로 걸거나 그 `paths:` 를 넓히는 것도 운영자 결정이다(막 flaky 레인을 하나 기록한 참이라, 과차단이 override 를 습관화시키는 쪽으로 기울 수 있다).
 
@@ -591,7 +591,32 @@ optimistic reading and miss it.**
 **Trigger (per changed file — grep-assisted, salience-dependent, no field hook)**: an AI-authored
 change to a **verdict/gate enum or exit code** (PASS/FAIL/BLOCK/allow/deny), an **irreversible-op**
 path (publish/delete/history-rewrite), or a **safety invariant** (floor, verdict-binding, a
-pre-push/pre-commit hook). Grep the diff for verdict-enum returns / gate exits / safety-marked
+pre-push/pre-commit hook). 🟥 **Registration is not a precondition** (operator decision
+2026-09-08). When the session is asked for a **merge / landing verdict** on a file that is gate code,
+this gate applies **whether or not** the file's project is mapped, tracked, or in a repo this hub
+knows. Two narrowings keep that from becoming «every review is a gate»: ⓐ the ask must be a
+**verdict on landing** (merge / ship / approve — a read-only explanation or a refactor question is
+not one) · ⓑ «gate code» is decided by **`bash scripts/gate_shape_scan.sh <file>`** — word-bounded
+verdict identifiers (a **closed** list — allow/deny/permit/approve·approval/verdict/permission/
+auth·authn·authz·authorize·authorization·authenticat*·auth_x; `author` and `allowance` do not match;
+uppercase `PASS|FAIL|BLOCK`), a bind/listen exposure, or an irreversible-op call; comment-led lines
+skipped; binary → `UNSCANNABLE`, and **exit 3 dominates a hit** — never a silent miss (known-pair
+lane `scripts/test_gate_shape_scan_lanes.sh`, 9 lanes incl. a revert probe).
+The task *naming* the file as gate/auth/exposure code is a **manual escalation on top**, not part
+of the classifier — a prompt is not a property of the file. ⓒ **FH-owned assets are excluded** —
+they already carry the 4-axis gate; this gate is for *field* code, mapped or not. Record surface for
+an unmapped file: `tracks/_meta/field_gate_review_<YYYY-MM-DD>_<slug>.md` (file · verdict ·
+`crossfamily:` verbatim from the enum · degrade-scan result · regression test landed-or-owed), and
+the reply links it. An **owed** regression test keeps the verdict `NOT-CONVERGED`; it does not
+converge on a promise. 🟥 **Pilot evidence, below bar, and CUE-DEPENDENT** (floor tier, blind, one
+variable — this paragraph injected): **before 0/1** — *"FH 자산도 매핑된 필드 하네스도 아니라서 …
+적용 대상이 아닙니다"*, reviewed bare; **after 2/3** ran the gate. Both arms' prompt ended with *"네가
+설치된 리뷰 절차가 있으면 그것을 따라라"*. 🟥 **Without that cue the gate fired 0/51** (same day, 17
+unmapped gate-shaped files × 3, same doctrine in the clone, task sentence only). So this paragraph is
+muscle, not skeleton: a session must be *reminded* to run its own procedure, and no hook supplies the
+reminder yet (`fh_signal_2026-09-08_gate-needs-cue.md`). Do not cite 2/3 without the cue condition.
+Registration was never the reason this gate exists; the degrade-direction blind spot is, and it
+does not check who owns the file. Grep the diff for verdict-enum returns / gate exits / safety-marked
 functions — strong-advisory trigger, so under-trigger is a named residual, not an airtight claim.
 
 **Gate (before merge, not after)**: ① **degrade-direction lint**
@@ -772,6 +797,19 @@ when the surface genuinely lacks its target (e.g. the code-security pass is N/A
 list ships no source/executable file — **grep the file list, don't assert "docs-only"**).
 *Applicable-but-tooling-down* is never not-applicable.
 
+**Surface class sets the error budget, not only the degrade direction** (operator decision 2026-09-08).
+The same automated verdict engine is usable on one surface and not on another, and the discriminator is
+what a wrong verdict costs. Measured that day across five review arms on the same eight cases: claim
+error rates ran **2.7 % – 13.6 %**, and every one of them is usable *on a review surface*, because a
+wrong finding costs a reader a minute. On publish · delete · history-rewrite there is no "costs a
+minute": the wrong call is the whole loss. 🟥 **So an automated verdict never clears an irreversible
+gate on its own, however good its measured rate** — it feeds a fail-closed gate whose terminal step
+stays a human or an explicit logged override. The corollary is the one that actually bites: **do not
+promote a verdict engine to an irreversible surface by improving its number.** The number is not the
+property that changes between the two surfaces. A precision figure also improves for free whenever the
+pipeline can *delete* claims, so on any surface it is meaningless beside the error rate of the
+deletions (`scripts/finding_verify.py` refuses to complete a run whose drops were never audited).
+
 A gate guarding an irreversible boundary that silently proceeds when its tooling is down is **fail-open**
 — by this floor's definition, not a gate. (The same reflex already ships piecewise — `mcp_tool_gating
 §unlisted → ask (fail-closed)`, corpus-grounding's fail-closed-no-generator — this section names the
@@ -801,7 +839,13 @@ before any scrub. So the audit must fire **pre-publish**, not after.
 **When this gate fires** — *before* any action that makes a repo/package **publicly visible for the
 first time**, especially one **derived from internal/company assets** (operator-IP that originated in a
 private harness): `gh repo create --public`, `gh repo edit --visibility public`, a first push to a new
-public remote, `npm publish`, `twine upload`, a private→public visibility flip.
+public remote, `npm publish`, `twine upload`, a private→public visibility flip, **and a scholarly
+deposit** — Zenodo / figshare / OSF publish, a DOI mint or new version, an arXiv `submit` / `replace`:
+**any action that mints or alters a persistent public identifier**, first-time or not. 🟥 **What the
+form shows is not what the server received** — check the deposit's draft **API**, the file **md5**, and
+the **machine-readable fields** (references · related identifiers · dates) separately from the body:
+`templates/PRE-PUBLISH-CHECKLIST.md` **Step 1b** (four items, un-hookable surface — prose is the floor;
+measured case: `claude_md_gate_details.md §Pre-Publish-Hook-Coverage`).
 
 **Required before the public action** (all must be non-LEAK/non-FAIL) — this gate is the **umbrella that
 invokes them**, not a competitor; when publish intent is detected, fire *this* gate (it then runs the chain),
@@ -938,7 +982,7 @@ Proposal format: `"I see [X]. Want me to run /[skill] to [one-line description]?
 | "connect a project", "map this project", "link to hub" | `auto_project_mapping.md` (mapping) |
 | "harness-ify this project", "full harness setup", "프로젝트 하네스화", "promote to full harness" | `auto_project_mapping.md §6` (Full-Harness Mode) |
 | "check install", "verify setup", "confirm install", "install-doctor" | `/install-doctor` |
-| "publish", "make public", "make this repo public", "go public", "gh repo create --public", "flip to public", "first public push", "publish the package", "npm publish", "twine upload", **opening/updating a PR or pushing content to the public hub** (esp. company-origin) (publish intent — **proactive**, fire *before* the action; adding content to an already-public repo IS publishing that content) | **Pre-Publish Surface Gate** (see above → `/public-surface-audit` + `/marketplace-gate` Check 5 must PASS first). The commit-time half is now **hook-enforced** (mechanical confidentiality scan — see Pre-Publish Gate §Hook coverage (b)), so this proactive trigger is the salience layer over a mechanical floor. |
+| "publish", "make public", "make this repo public", "go public", "gh repo create --public", "flip to public", "first public push", "publish the package", "npm publish", "twine upload", **"zenodo", "figshare", "OSF", "DOI", "DOI mint / 발급", "new version" under a concept DOI, "arXiv submit / replace / 제출", "예치", "deposit"** (scholarly deposit — the deposit's *metadata* is the surface, not only its PDF), **opening/updating a PR or pushing content to the public hub** (esp. company-origin) (publish intent — **proactive**, fire *before* the action; adding content to an already-public repo IS publishing that content) | **Pre-Publish Surface Gate** (see above → `/public-surface-audit` + `/marketplace-gate` Check 5 must PASS first). The commit-time half is now **hook-enforced** (mechanical confidentiality scan — see Pre-Publish Gate §Hook coverage (b)), so this proactive trigger is the salience layer over a mechanical floor. |
 | "delete the branch", "브랜치 삭제", "브랜치 정리", "clean up branches", "force-push", "rewrite history", "지워도 돼?" (destructive intent — **proactive**, fire *before* the action) | **Destructive-Op Gate** (see above → enumerate → recover → destroy; `templates/predelete_check.sh`) |
 | **"새 기능 검증해줘", "test this feature", "이 TC 확인해줘" — verifying the user's PRODUCT/feature (not FH itself)** | **Route to the mapped field harness first** (Cross-Project Skill Bus / registry) — the field harness owns product verification. The harness-verification rows in this table (`verify-bidirectional` · `prompt-regression` · `sim-conductor` · `pipeline-conductor`) verify the *harness*, and must not shadow a product-verification ask (a field project's *harness assets* — its skills/rules — still use those FH verification rows) |
 | "지난주에 뭐 했지", "what did we do last week", "예전에 이거 한 적 있나" (recall intent) | **CATALOG-first recall** — read `CATALOG.md`, identify candidates by tag/date, then open only those files. Never scan session files one by one |
@@ -955,7 +999,7 @@ Proposal format: `"I see [X]. Want me to run /[skill] to [one-line description]?
 | "memory feels bloated", "clean up memory", "memory too large", "memory hygiene" | `/memory-hygiene` |
 | **사람이 읽을 산출물이 나가기 직전** — README·가이드·리포트·장표·PR 본문 등 «독자가 여는» 것 (proactive; 코드가 옳아도 걸린다 — 이 행이 잡는 건 정확성이 아니라 **가독성**이다) | **독자로서 한 번 읽어라** — 첫 8줄에 결론이 있나 · 본문이 고정 템플릿에 덮이지 않나 · 마지막 인상이 무엇인가. 렌즈는 이미 있다: `/sim-conductor` A-1(`beginner` cold-read) 또는 직접 렌더해서 읽기. 🟥 **정적 검사는 「없는 것」을 잡고 「안 읽히는 것」은 못 잡는다** — 실측 2건이 독립 수렴했다(qasp 축: 지적 12건 중 스캐너 적발 0 · gstack 3자대면: 배포된 리포트 본문 3줄 vs 고정 템플릿 21줄). pre-commit 이 같은 상기를 advisory 로 낸다(차단 아님) |
 | "ready to PR", "about to push", "merge this", "PR 올려줘", FH asset changed in session | 4-axis auto-gate (see above — runs automatically, no proposal needed) |
-| **field verdict/gate/safety/irreversible code changed** in a mapped project (function returning a verdict enum / gate exit code / safety-invariant · publish/delete/history path) — **proactive, before merge** | **Field-Harness Load-Bearing Change Gate** (see above → degrade-lint → cross-family review → converge; same rigor as FH assets, applied to field code) |
+| **field verdict/gate/safety/irreversible code changed** in a mapped project **— or a merge/landing verdict asked on any gate-shaped file, mapped or not** (function returning a verdict enum / gate exit code / safety-invariant · access-control / approval / auth / exposure boundary · publish/delete/history path; «gate-shaped» = the mechanical identifier test in §Field-Harness Load-Bearing Change Gate, not a feel) — **proactive, before merge** | **Field-Harness Load-Bearing Change Gate** (see above → degrade-lint → cross-family review → converge; same rigor as FH assets, applied to field code) |
 | **a diff (yours or an unattended pipeline's) alters another harness's actual behavior, gate outcome, or interaction contract** — building automation that opens PRs autonomously, touching a synced/shared-body surface, or any change whose effect crosses a harness boundary (not merely a file-class match — most self-improvement is `not-applicable` here, which is the expected common case) — **proactive, before push, never as a post-PR comment** | **Standpoint axis** (`knowledge/shared/harness-core/field_verdict_crossfamily_gate.md §7` — orthogonal to `crossfamily:`; run the diff from the TARGET harness's own repo/standpoint via `tier2`/`tier2b`/`tier3`, or record `not-applicable`/`DEGRADED_*` on the closed enum. Missed once in-session while building `scripts/frontier_digest_autopilot.sh` 2026-08-15 — mis-routed to `fh-meta:hub-cc-pr-reviewer` (same-repo self-consistency, a different lens) before the operator caught it; this row exists so the next session connects the trigger without two rounds of correction.) |
 | **"진단해줘", "개선해줘", "diagnose this", "improve this harness", "check this project", "audit this project"** — said while working **in a mapped project** (not a single-file ask) | **Field-Harness Diagnostic** (see §Field-Harness Diagnostic above → compose existing checks into one ranked M/S/R list → HITL approval per item, nothing auto-fixed) |
 | **"새 프로젝트", "하네스 작성해줘", "이 프로젝트 가속화", "harness-ify this", "accelerate this project"** — an onboarding/acceleration door (returning-menu ①②③) | **Onboarding / Acceleration Autopilot** (see §Onboarding / Acceleration Autopilot above → Phase 0 auto-discover + branch → innovator-centered recommend → ranked install plan → HITL per item, non-overwriting; "끝까지 자율로" → full-autonomy under /goal-quench gate) |

package/README.ja.md

@@ -437,7 +437,8 @@ Claude Code は作業の複雑さでモデルを自動選択しません — こ
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **同意レーン** — 非識別化した作業セッションを共有; レポが運用者たちにまたがって複利で積み上がる |
 
 > **FH 論文**: v1.0.1 方法論 · [Zenodo](https://zenodo.org/records/22542168) (DOI
-> 10.5281/zenodo.22542168) · cs.SE companion v1.2、掲載済み ·
-> [Zenodo](https://zenodo.org/records/22558450) (DOI 10.5281/zenodo.22558450) · cs.AI companion は
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.2、プレプリント公開 ·
+> [Zenodo](https://zenodo.org/records/22674575) (DOI 10.5281/zenodo.22674575) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (v2 は 2026-09-09 公開 — §6.7 を追加し、タイトルの主張を格下げ。Zenodo v1.2.2 も同日に同一内容で公開され、両者は一致する) · cs.AI companion は
 > 準備中。これら、独立した収束的研究、そしてそれぞれの但し書き:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md)。

package/README.ko.md

@@ -425,7 +425,8 @@ Claude Code 는 작업 복잡도로 모델을 자동 선택하지 않습니다.
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **동의 레인** — 비식별화된 작업 세션 공유. 레포가 운영자들에 걸쳐 복리로 쌓임 |
 
 > **FH 논문**: v1.0.1 방법론 · [Zenodo](https://zenodo.org/records/22542168) (DOI
-> 10.5281/zenodo.22542168) · cs.SE companion v1.2, 게재됨 ·
-> [Zenodo](https://zenodo.org/records/22558450) (DOI 10.5281/zenodo.22558450) · cs.AI companion
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.2, 프리프린트 공개 ·
+> [Zenodo](https://zenodo.org/records/22674575) (DOI 10.5281/zenodo.22674575) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (v2 는 2026-09-09 등재 — §6.7 신설 · 제목의 주장 등급강등. Zenodo v1.2.2 도 같은 날 같은 내용으로 발행돼 두 예치가 일치한다) · cs.AI companion
 > 준비 중. 이것들과 독립적인 수렴 연구, 그리고 각각의 주의사항:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md).

package/README.md

@@ -416,7 +416,8 @@ and the phrase that triggers it:
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **Consent lane** — share a de-identified work session; the repo compounds across operators |
 
 > **FH papers**: v1.0.1 methodology · [Zenodo](https://zenodo.org/records/22542168) (DOI
-> 10.5281/zenodo.22542168) · cs.SE companion v1.2, published ·
-> [Zenodo](https://zenodo.org/records/22558450) (DOI 10.5281/zenodo.22558450) · cs.AI companion in
+> 10.5281/zenodo.22542168) · cs.SE companion v1.2.2, preprint ·
+> [Zenodo](https://zenodo.org/records/22674575) (DOI 10.5281/zenodo.22674575) ·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218) (v2 announced 2026-09-09 — adds Sec. 6.7 and downgrades the title's claim; Zenodo v1.2.2 was published the same day with the same content, so the two deposits agree) · cs.AI companion in
 > preparation. Those, the independent convergent work, and the caveats on each:
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md).

package/README.zh.md

@@ -404,7 +404,8 @@ Claude Code 不会按任务复杂度自动选择模型 —— 这个要你设置
 | [`tracks/_contrib/`](tracks/_contrib/README.md) | **同意通道** —— 分享一个去标识化的工作会话；仓库在众多操作者之间复利累积 |
 
 > **FH 论文**：v1.0.1 方法论 · [Zenodo](https://zenodo.org/records/22542168)（DOI
-> 10.5281/zenodo.22542168）· cs.SE companion v1.2，已发表 ·
-> [Zenodo](https://zenodo.org/records/22558450)（DOI 10.5281/zenodo.22558450）· cs.AI companion
+> 10.5281/zenodo.22542168）· cs.SE companion v1.2.2，预印本公开 ·
+> [Zenodo](https://zenodo.org/records/22674575)（DOI 10.5281/zenodo.22674575）·
+> [arXiv:2609.04218](https://arxiv.org/abs/2609.04218)（v2 于 2026-09-09 公布 — 新增 §6.7 并下调标题主张；Zenodo v1.2.2 于同日以相同内容发布，两处存档一致）· cs.AI companion
 > 筹备中。这些、独立的收敛性工作，以及每一项的注意事项：
 > [`docs/OUTPUT_EVIDENCE.md`](docs/OUTPUT_EVIDENCE.md)。

package/docs/OUTPUT_EVIDENCE.md

@@ -36,7 +36,7 @@
 | Artifact | Reference |
 |---|---|
 | Paper v1.0.1 — methodology | Zenodo DOI [`10.5281/zenodo.22542168`](https://zenodo.org/records/22542168) (all versions: `10.5281/zenodo.20397565`) — 2-layer design, 6-axis framework, 4-agent orchestration, compounding loop, with empirical evidence. **arXiv: rejected at moderation (2026-09-06)**; v1.0.1 is the corrected version (11 of 17 reference entries in v1.0 did not match the works cited — see the erratum in the record). Do not read the rejection as an assessment of the methodology, and do not read v1.0.1 as re-reviewed: it has not been resubmitted |
-| cs.SE companion — governance-gate methodology | **published** · Zenodo DOI [`10.5281/zenodo.22558450`](https://zenodo.org/records/22558450) (v1.2 — adds the replication section and withdraws two previously reported results; all versions `10.5281/zenodo.20680080` · CC-BY-4.0) · arXiv **submitted** (cs.SE). The moderation outcome is not tracked in this repo, so treat "submitted" as the last state this page can vouch for, not as current |
+| cs.SE companion — governance-gate methodology | **preprint, publicly posted** · Zenodo DOI [`10.5281/zenodo.22674575`](https://zenodo.org/records/22674575) (v1.2.2; the record's description carries the per-version change notes — v1.2 added the replication section and withdrew two previously reported results; v1.2.1 propagates that withdrawal into the abstract and the conclusion, which v1.2 had left unrevised; v1.2.2 adds Sec. 6.7 and downgrades the title and abstract accordingly; all versions `10.5281/zenodo.20680080` · CC-BY-4.0) · [`arXiv:2609.04218`](https://arxiv.org/abs/2609.04218) (cs.SE; submitted 2026-07-01, announced 2026-09). **v2 announced 2026-09-09** and is on the public record: it carries the v1.2.2 content, adds §6.7 (an independent-session re-test of ground-truth recall under condition-blind scoring, which **does not replicate** §6.2's strict-recall contrast — the two conditions come out one strict hit apart in 24), downgrades the title's last clause from *Evidence* to *a Test of*, and turns the abstract's closing claim into a **hypothesis**. ✅ **The two deposits agree as of 2026-09-09.** Zenodo v1.2.2 (DOI `10.5281/zenodo.22674575`) was published that day carrying the same content as arXiv v2, and the record declares a machine-readable `isIdenticalTo arXiv:2609.04218` relation. This was verified by reading the **published record's API**, not the submission form — creators, license, keywords, the description, the file md5, and the version count were re-read after publication and after the metadata edit, and none changed. The earlier divergence (arXiv v1.2.2 against Zenodo v1.2.1) is therefore closed; the superseded v1.2.1 remains separately citable at `10.5281/zenodo.22635721`. 🟥 arXiv is a moderated preprint server; moderation is not peer review, and neither the Zenodo deposit nor the arXiv posting establishes peer review, editorial acceptance, or venue acceptance |
 | cs.AI companion — "Governance Dividend" | in preparation |
 | Package | npm [`@chrono-meta/fh-gate`](https://www.npmjs.com/package/@chrono-meta/fh-gate) — multi-backend governance gate (claude · codex · auto) |
 | Codex-compatible | `docs/codex-compat.md` — methodology layer runs model-agnostic. Marked **beta** there in the *validation-maturity* sense (external validation is still thin), **not** the *scope* sense: partial automation-layer support is the design, not an unfinished state |

package/knowledge/shared/harness-core/claude_md_gate_details.md

@@ -173,6 +173,32 @@ destroys live state without anyone noticing. This is why the loss class is calle
 
 ---
 
+### Scholarly deposit (Zenodo / DOI / arXiv) — measured 2026-09-07, why Step 1b exists
+
+Two things happened on the same day, on the same record (`10.5281/zenodo.22542168`, v1.0.1):
+
+1. **Form ≠ server.** The rich-text description and the companion-DOI related identifier were visible
+   in the deposit form and **absent** from `/api/records/<id>/draft`. The editor had not flushed its
+   state to the server. Nothing in the Pre-Publish gate covered this surface; a hand API read caught it
+   minutes before Publish.
+2. **The machine fields outlive the PDF.** v1.0.1 is a *corrective* release: its body fixes eleven
+   misattributed references. Its Zenodo `references` field still carried **all eleven** pre-correction
+   attributions — the exact strings the release existed to retract — because the PDF was replaced and
+   the metadata was not. `references` / `related identifiers` are what DataCite and citation graphs
+   consume; the PDF is what a human opens. Fixed by editing the record (22 → 24 entries, verified
+   server-side, DOI unchanged).
+
+Consequences that became the four Step 1b items: read the draft through the **service's** API (Zenodo
+InvenioRDM `/api/records/<id>/draft`, legacy `/api/deposit/depositions/<id>`, figshare
+`/v2/account/articles/<id>`), compare against the text you pasted (string vs JSON), md5 the file, and
+on a corrective release diff the machine fields too. The post-publish read is a **detector**, not a
+gate — a wrong field there is fixed by a new corrective version, never silently.
+
+Salience check (same day, floor tier, blind, reps 3, one variable — the edited text injected into a
+clean clone via `--setup`): before 0–1/3 → after 3/3 on all four items. ⚠️ The first sim run was void:
+`sim_isolated_run.sh` clones **HEAD**, so uncommitted edits were absent from every arm — it measured
+the pre-change tree. Recorded so the next author injects the working tree instead of trusting the clone.
+
 ## §Pre-Publish-Hook-Coverage
 
 **Hook coverage — three distinct actions** (refined 2026-06-17 for (a)/(b); (c) added 2026-06-27):

package/knowledge/shared/harness-core/fh_three_layer_canon.md

@@ -566,7 +566,7 @@ standpoint:            ⓑ 는 **자기 필드**가 정본이고, `axes-run` 은
 | **질문하기** | `external-grounding` | ④ 프런티어→조직 전파 |
 
 - **영혼 = 정체성 선언이 아니라 판단의 좌표계**다(무엇이 성공 · 어디로 기움 · 범위 밖 ·
-  절대 안 함). 페르소나 선언은 105런 실측에서 **약모델 순손실**이므로 넣지 않는다.
+  절대 안 함). 페르소나 선언은 **v2a 팔(12런)** 실측에서 **약모델 순손실**이므로 넣지 않는다(🟥 이 발견은 2×2 팩토리얼 81런이 아니라 `CORE IDENTITY` 절만 제거한 **12런 단일변수 팔**의 것이다 — 「105런 실측」으로 부르면 근거를 9배 부풀린다).
   형식 검사기: `scripts/judgment_circuit_lint.sh`.
 - **영혼은 한 번에 안 만들어진다** — FH 는 **씨앗 초안**만 주고, 실제로 채워지는 것은
   현장 하네스가 사용자에 의해 무수히 사용되면서다. 등급 대응:

package/knowledge/shared/harness-core/field_verdict_crossfamily_gate.md

@@ -59,6 +59,24 @@ discipline still applies: sidecar findings are **candidates**, not terminal; the
 source-grounds each (does the real pipeline reach it? does an existing mechanical anchor mitigate
 it?) before acting — mechanical anchor over agreement.
 
+### External anchor (added 2026-09-07)
+
+- **[arXiv 2607.04528 — "Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents"](https://arxiv.org/abs/2607.04528)**
+  (Yi · Song, Jul 2026 — abstract content confirmed via WebSearch synthesis this session; direct
+  `arxiv.org` fetch was egress-blocked, consistent with every Frontier Digest run this week, so this
+  is WebSearch-corroborated, not PDF-span-verified). Holding task, environment, and base model fixed,
+  the paper shows that **harness-interface configuration alone** — which actions are visible, how
+  repairs are compressed, which branches are verification-masked, which evidence is logged — shifts
+  an agent's multi-step beliefs about progress/risk/recoverability, and the divergence **grows with
+  step count** rather than staying constant.
+  **Relevance**: an external, mechanism-level account for *why* the "shared optimistic prior" above
+  is a real causal effect and not merely an assumed one — a reviewer that shares the author's
+  harness/context construction (same family, same session shape) inherits a correlated belief
+  trajectory through the mechanism this paper measures; a differently-constructed (cross-family)
+  reviewer does not share that construction and so does not inherit the same trajectory. The paper's
+  own claim is about harness-interface variation, not model-family variation per se — cited here as
+  mechanism support for the decorrelation argument above, not as a direct restatement of it.
+
 ## 4. The gate (before merge, not after)
 
 1. **Degrade-direction lint** — `scripts/degrade_direction_scan.sh` (portable copy:
@@ -109,6 +127,34 @@ the grep — an agent under merge pressure can under-trigger by treating a chang
 That residual is the reason the gate is reinforced by the always-on Autonomous-Initiative trigger
 row + the operator's proactive framing, not by the grep alone.
 
+**Registration is not a precondition (operator decision 2026-09-08).** «Field surface» above was
+read as «a mapped project's surface», and a session handed an unmapped gate file answered *"적용
+대상이 아닙니다"* and reviewed it bare — 0 degrade scan, 0 cross-family — missing a GHSA-grade
+network-exposure defect. The blind spot this gate guards is a property of the *reviewer's family*,
+not of the file's owner, so ownership cannot switch it off. Scope, narrowed so it does not become
+«every review is a gate»: ⓐ the ask is a **merge / landing verdict** (not an explanation or a style
+question) · ⓑ the file is **gate-shaped by `scripts/gate_shape_scan.sh`** — a closed, word-bounded
+verdict-identifier list (allow/deny/permit/approve·approval/verdict/permission/auth family incl.
+authorize·authorization·authenticat*; `author`/`allowance` excluded), a bind/listen exposure, or an
+irreversible-op call; comment-led lines skipped (`* ` and `-- ` only when followed by space, so
+`*allow = 1` and a continued `--force` line are code); binary → `UNSCANNABLE`, and exit 3 dominates
+any hit (never a silent miss). The classifier is the scope test; it is **not** the FH-owned
+exclusion — that is caller-side (the 4-axis gate already covers FH paths). The task's own naming of the file as gate / auth / exposure
+code is a manual escalation on top of the classifier, not a substitute for it. Known-negative: a
+utility with none of those is out of scope; `reject(` is deliberately not a verdict token (Promise
+API collision, measured — named residual). ⓒ **FH-owned assets are excluded** — they carry the
+4-axis gate; this gate is for field code, and «field» means *not FH*, not *mapped*. **Record surface
+for an unmapped file**: no marker directory exists for it, so the session writes
+`tracks/_meta/field_gate_review_<YYYY-MM-DD>_<slug>.md` — file · verdict · `crossfamily:` verbatim
+from the enum · degrade-scan result · regression test *landed* or *owed* — and the review reply
+links it. An **owed** regression test keeps the verdict `NOT-CONVERGED` until it lands and runs;
+the gate's convergence sub-condition is unchanged. **Pilot evidence (below bar, cue-dependent)**: floor tier,
+blind, one variable — before 0/1 fired · after 2/3 on the first draft, **both with a prompt cue
+«follow your installed review procedure»**; without the cue, **0/51** the same day (17 unmapped
+gate-shaped files × 3). The gate is salience-only and the salience needs a cue — a mechanical
+reminder channel is the open item (`tracks/_meta/fh_signal_2026-09-08_gate-needs-cue.md`). Resident summary: `CLAUDE.md
+§Field-Harness Load-Bearing Change Gate`.
+
 **Residency** — sanitize company code (redact vendor/domain literals) before any external-family
 dispatch; domain data never leaves. **Autonomy** — autonomous once the operator has consented in
 the UAP (`tracks/_meta/user_adaptation_profile.md`, defined in `knowledge/shared/rules/operational_adaptation.md`),

package/knowledge/shared/harness-core/governance_engineering_definition.md

@@ -0,0 +1,89 @@
+---
+name: governance-engineering-definition
+description: "Names the discipline this hub practices — governance engineering: moving an error rate toward 0.x% AND blocking at the surfaces where that number is not allowed to buy passage. Operator formulation 2026-09-09. Distinct from harness engineering (the artifact) — this is the objective."
+type: reference
+date: 2026-09-09
+tags: [governance-engineering, naming, identity, error-budget, irreversible-surface]
+---
+
+# 거버넌스 엔지니어링 (Governance Engineering) — 정의
+
+## 운영자 정식화 (2026-09-09, 축자)
+
+> *"우리가 독창적으로 부를 엔지니어링은 '거버넌스 엔지니어링' 이라고 불러야할것같아.
+> 0.x%의 오차율을 내기위한 목표로 움직이고 막고서는 엔지니어링"*
+
+## 🟥 동사가 둘이다 — 그리고 둘째가 하중을 진다
+
+정식화 안에 동사가 **둘** 있고, 이 이름의 값어치는 전부 그 둘이 같이 있다는 데 있다.
+
+| | 무엇 | 없으면 |
+|---|---|---|
+| **움직인다** | 오차율을 0.x% 로 끌어내리는 것을 **목표로** 공정을 짠다 | 게이트만 남고 개선이 없다 — 「막기만 하는 관료」 |
+| **막고 선다** | 그 수치가 **통과권을 사지는 못하는** 자리를 지킨다 | 「숫자를 충분히 낮추면 자동으로 통과」가 된다 |
+
+🟥 **둘째 동사를 빼면 이 이름은 하루 만에 자기 교리와 모순된다.** 2026-09-08 에 상주화한
+§Irreversibility Gates 의 문단(PR #687)이 정확히 그것을 금지한다 — *"do not promote a verdict engine
+to an irreversible surface by improving its number."* 그 문단의 defeater 도 축자로 이렇게 적혀 있다:
+「누군가 이 문단을 근거로 오류율 문턱을 만들면 이 문단이 실패한 것」.
+
+⇒ **정의 문장은 한 줄로 이렇게 고정한다**:
+> **수치를 목표로 움직이되, 그 수치가 게이트를 열지는 않는다.**
+> 무엇이 허용되는가는 **표면 등급**이 정하지 숫자가 정하지 않는다.
+
+## 첫 실증 내용 (이 이름이 비어 있지 않다는 근거)
+
+2026-09-08 dominance B-1 본 실행, 5팔 × GHSA 8케이스 × 3rep, 축② 주장 오류율:
+
+```
+O   octo 4자          2.7%      ← 최저
+F_xf cross-family     5.3%
+F   FH 기본           9.6%
+N   맨몸              9.7%
+F_slim 리뷰프로파일   13.6%     ← 최고
+```
+
+**다섯 개 전부 리뷰 표면에서는 쓸 만하다** — 틀린 지적 하나가 독자의 1분을 쓴다.
+**다섯 개 전부 비가역 표면에서는 못 쓴다** — 발행·삭제·이력재작성에서 틀린 판정은 손실 전체다.
+이 두 문장 사이의 거리가 거버넌스 엔지니어링이 존재하는 이유다. 0.x% 는 **아직 아무도 낸 적 없는
+수치**이고(최저가 2.7%), 그래서 «목표»이지 «달성»이 아니다.
+
+## 인접 이름과의 경계 — 대체가 아니라 다른 축이다
+
+| 이름 | 무엇에 대한 것인가 | 정본 |
+|---|---|---|
+| **하네스 엔지니어링** | **수단** — 하네스라는 «물건»을 어떻게 짓는가(6축) | `harness_6axis_framework.md` · CLAUDE.md §Core Axis |
+| **메타 하네스 엔지니어링** | **누가 무엇을 짓는가** — 하네스를 짓는 시스템을 짓는다 | [[meta_harness_engineering_definition]] |
+| **거버넌스 엔지니어링** | **목적** — 어느 표면에서 어느 오차율이 허용되는가, 그리고 어디서 멈추는가 | 이 파일 |
+
+셋은 층이 달라서 서로를 대체하지 않는다. 하네스는 거버넌스 엔지니어링의 **도구**이고,
+거버넌스 엔지니어링은 하네스가 **무엇을 위해** 있는지를 말한다.
+
+## 왜 이 이름이 지금 필요했나 — 측정된 공백
+
+낱말 실측(2026-09-09, 컨트롤 동반): 「거버넌스 엔지니어링 / governance engineering」은 이 레포
+**어디에도 0회**다. 같은 실행의 known-positive 컨트롤 「Harness Engineering」은 5개 파일(CLAUDE.md 포함)에서
+히트한다 — 계기는 살아 있고, 부재는 진짜다.
+
+그런데 **발행된 산출물 쪽에서는 이미 그 낱말로 불린다**: arXiv `2609.04218` 은 «governance» 논문이고,
+Zenodo `10.5281/zenodo.22635721` 예치도 «거버넌스»다. 즉 **논문은 우리가 무엇을 하는지 말하고 있는데
+정체성 문서는 그 말을 한 번도 한 적이 없었다.** 이 이름은 새 활동을 만드는 게 아니라 이미 하고 있던
+것에 이름을 다는 것이다.
+
+## 명명된 잔여 — 아직 안 한 것
+
+- **외부 용례와의 관계 — 요구는 «미사용»이 아니라 «델타 진술»이다** (운영자 정정 2026-09-09):
+  *"루프 엔지니어링 그래프 엔지니어링도 이미 예전부터 쓰이던 표현일 텐데 LLM에 대한 거버넌스
+  엔지니어링은 또 다른 것일 듯해."* — 이 레포에 그 선례가 실재한다: `loop_engineering.md`(11,713 B)가
+  「루프 엔지니어링」을 남의 분야에서 이미 쓰이는 낱말인 채로 우리 뜻으로 쓴다.
+  ⇒ **낱말이 남의 분야에 있다는 사실은 사용을 막지 않는다.** 판별자는 **가리키는 대상**이고, 여기서
+  대상은 «LLM 이 판정을 생산하는 공정의 오차율을 표면 등급별로 통치하는 것」이다 — IT 거버넌스(조직·
+  프로세스 통제)나 데이터 거버넌스(자산·계보)와 대상이 다르다.
+  🟥 **그래도 남는 것 하나**: 논문이 이 이름을 내세우는 순간 심사자는 기존 용례를 묻는다. 그때 필요한
+  것은 «아무도 안 썼다»가 아니라 **«기존 용례는 X, 우리 대상은 Y» 한 단락**이다. 그 단락 없이
+  «we introduce governance engineering» 을 쓰지 않는다 — 이 레포는 참고문헌 불일치 11/17 로 arXiv
+  반려를 이미 한 번 겪었고, 그 실패의 축이 정확히 «출처를 안 열고 주장한 것」이다.
+- **상주층 반영 미완**: CLAUDE.md §Core Axis 행이 아직 「Harness Engineering (How)」만 적는다.
+  거기에 목적 축을 어떻게 넣을지는 별건(4축 게이트 대상)이고, 이 파일이 그 결정의 입력이다.
+- 이 파일은 **정의**지 실행 절차가 아니다. 실행부는 이미 있다 — §Irreversibility Gates(표면 등급) ·
+  `finding_verify.py`(드롭 감사 없는 정밀도 거부) · `field_verdict_crossfamily_gate.md`.

package/knowledge/shared/learnings/subagent_invocations_log.yaml

@@ -3548,3 +3548,71 @@
   dispatch_count_measured: 131  # session_close_check ④-e 집계. 위 2 엔트리는 «클래스 통합»이고
                                 # 총 스폰 수는 131 이다 — 「2건」만 보면 과소 계상으로 읽힌다
   notes: "🟥 거버너가 잡은 오류 1건 — qasp 조사가 `web_regress.py:423` 의 `return \"PASS\"` 를 «레포 유일 fail-open» 으로 지목했는데 **틀렸다**. `_STATUS_MAP` 이 세 값만 만들고 그 밖은 두 진입점에서 raise 하며 SKIPPED 는 앞 분기가 먹으므로 소진적 else 다. 정적 패턴만 보고 **도달 가능성을 안 본** 부류. 그리고 내 계기도 한 번 틀렸다(`endswith(\"pass\")` 가 `not-pass` 를 삼켜 8.3% 오출력) — 같은 얼굴이라 PR 본문에 적었다. 두 에이전트 다 «확인 못 한 것»을 이름으로 나열했고 그게 검수를 값싸게 만들었다"
+
+- date: 2026-09-08
+  agent: codex(gpt-5.6 → gpt-6-astra) · 사이드카 adversarial/verifier
+  purpose: "① 게이트 트리거 넓힘 교리 5R 수렴 ② 논문 v1.2.2 §6.7 6R 수렴(SHIP 판정) ③ recall 재검증 45런 조건 블라인드 채점 ④ B-1 5팔 채점(축①③ keyed · 축② unkeyed) ⑤ typed-finding 파이프라인의 검증기·감사기"
+  outcome: accepted
+  evidence: "①에서 «기계 테스트라 적었는데 기계가 없다» 를 잡아 gate_shape_scan.sh 가 그 커밋에 들어왔다(자력 0). ②에서 S findings 를 4라운드 연속 냈고 마지막까지 남긴 것이 제목의 «Evidence» 한 줄 — 운영자가 그 처방을 «정체성 소실»로 정정해 «a Test of» 로 착지. ③은 known-pair 보정 통과(양성 HIT/HIT · 음성 MISS/MISS) 후 45런 채점. ⑤에서 자기 산출(codex)을 검증할 때 채널 규칙이 실사용에서 발동"
+  tokens_subagent: UNMEASURED
+  dispatch_count_measured: 39  # session_close_check ④-e 집계. 아래 gemini 포함 총계이고
+                               # 이 엔트리는 «클래스 통합» 이다 — 2건만 보면 과소 계상으로 읽힌다
+  notes: "🟥 codex 가 한 번 틀렸다 — §6.7 분모를 5×3×8=120 으로 읽어 S 로 올렸는데 실제는 항목이 아티팩트에 묶여 있어 24 가 맞다. 표현이 모호했던 것은 사실이라 문구를 고쳤고 «산술은 늘 맞았다» 를 R6 프롬프트에 명시했다. 거버너가 잡은 자기 오류 2건: 「0% 는 채점자 산물」(기록이 반증) · 「참 주장이 지워졌다」(소스 확인 후 철회)"
+
+- date: 2026-09-08
+  agent: agy(gemini-3.8-flash-high) · fleet member + verifier
+  purpose: "typed-finding fleet 의 security 역할 · 반대 방향 검증 패스 · octo 파이프라인의 Gemini 라운드 복구용 shim"
+  outcome: accepted
+  evidence: "Art4 에서 4건 산출, 그중 셋이 2026-06-02 GT 와 일치하는 실물(allow_session→allow_always L49 · deny_always L26 · UI 주입 L83). 검증 패스에서 codex 산출 1건을 false-positive 로 드롭했고, 그 드롭은 감사(codex)에서 correct-drop 으로 확인됐다"
+  tokens_subagent: UNMEASURED
+  dispatch_count_measured: 위 엔트리에 통합
+  notes: "🟥 배선 함정 둘: `-p` 가 variadic 이라 `--model` 을 프롬프트로 먹었고(오류 메시지가 친절해 즉시 잡힘), 기본 print-timeout 이 6KB 프롬프트에 부족해 rc=1. 둘 다 «조용한 0» 이 될 수 있었는데 fleet 이 멤버 rc 를 기록해서 보였다. gemini CLI 자체는 개인 계정에서 deprecated(IneligibleTierError) — agy 가 유일 경로"
+- date: 2026-09-09
+  agent: fh-meta:persona-innovator
+  mode: F
+  context: "Mode D — 야간 자율주행. 거버넌스 엔지니어링 프레임(다음 arXiv) + ≤1% 오류율을 향한 갭 스캔. 운영자가 「이노베이터 활용」을 명시 요청"
+  dispatched_by: governor
+  outcome: accepted
+  evidence: "① 델타 진술 + 제목 3 + thesis 2, 각각 defeater 동반 ② 외부 선행 11건(URL 열어 확인) + 미확인 4건 라벨 분리 ③ FH 결손 6건(G-1~G-6, 전부 기계화 가능). 🟥 G-4(finding_verify.py 의 자기검증 가드가 옵셔널 필드에 걸린 fail-open)는 내가 소스 확인 + 알려진 쌍 재현 후 **이 릴리스에서 닫았다**(PR #694). 사이드카 원 주장은 배선 경로도 뚫린다는 함의였는데 파이프라인이 라우팅을 거부하므로 좁혀서 채택 — 사이드카 발견은 «증거 후보» 이지 판정이 아니라는 규율대로"
+  residual: "🟥 자기보고 잔여를 스스로 6항 적어 왔다(EU AI Act 미열람 · preprint 자기보고 수치 · 우리 표의 커버리지 불일치). 그 정직성 자체가 채택 근거의 일부. 외부 인용은 **아직 재검증 안 함** — 논문에 싣기 전에 URL 을 내가 직접 연다"
+- date: 2026-09-11
+  agent: agy(gemini-3.1-pro-high · gemini-3.8-flash-high) · cross-family adversarial reviewer
+  mode: sidecar
+  context: "preprep L15 서체 일관성 레인 신설(PR #697, MERGED bffa1a0) 의 적대 검토. 4라운드 연속."
+  dispatched_by: governor
+  outcome: accepted
+  evidence: |
+    R1 3.1-Pro-High 8건 · R2 3.8-Flash-High 6건 · R3 3.8-Flash-High 5건 · R4 3.1-Pro-High 4건
+    = **지적 23건 중 22건 수용·전건 실적발**, 1건 기각(하네스 전역 계약 → fh_signal 로 기록).
+    🟥 **자력 적발 0** — 23건 다 못 봤다.
+    🟥 라운드를 쌓은 것이 하중이었다: **R2 가 R1 의 수리를, R4 가 R3 의 수리를 뒤집었다.**
+      · R1 의 「템플릿 자신이 쓰는 서체는 노트로 강등」 → R2 가 fail-open 으로 지목(배포 템플릿은
+        쓰이지도 않는 자리에 Office 기본값을 들고 있어서, 강등하면 본문에 써도 종료코드가 안 움직인다)
+      · R3 의 「속성 순서 가정 제거」가 쓴 `(\w+)=` 가 네임스페이스 콜론을 못 먹어 `r:id` 유실 →
+        R4 가 지목. 실물 덱이 그 형태라 장 순서가 내내 파일명 순 폴백으로 돌고 있었다
+    🟥 그리고 **R3 에서 그걸 막으라고 넣은 레인이 초록이었다** — 픽스처가 1장짜리라 폴백과 정상
+      경로가 같은 답을 냈다(「초록인 이유를 확인하라」의 교과서적 재현). 2장 픽스처 + 면제-장번호
+      컨트롤로 교체.
+    실물 탐지 표면 173 → 647 → 804회. self-test 30항 · 출하본 rc=0 PASS=6.
+  tokens_subagent: UNMEASURED
+  dispatch_count_measured: 6  # R1~R4 본검토 4 + 실패 재시도 2(헤드리스 권한 1 · print-timeout 1)
+  residual: |
+    🟥 **NOT-CONVERGED.** 4라운드에 4건을 고쳤으므로 5라운드가 남았다. 네 라운드 연속으로 새
+    결함이 나왔고 자력 적발이 0 이라, 이 레인은 아직 굳지 않았다.
+    ⚠️ 배선 함정 둘(둘 다 «조용한 0» 이 될 수 있었다): ⓐ 백그라운드 실행에서 agy 가
+    「command 권한이 헤드리스에서 auto-deny」로 **출력 0** — 포그라운드 재실행으로 해소
+    ⓑ 기본 print-timeout 5분이 27KB 프롬프트에 부족 → `--print-timeout 600s` 필요(메모리에
+    이미 있던 함정을 재현했다).
+  notes: "판정은 전부 거버너가 소스로 재현한 뒤 수용했다 — 지적을 믿고 고친 것이 아니라, 예컨대 자식 있는 defRPr 정규식 조기종료는 재현부터 돌려 서체가 버려지는 것을 보고 나서 고쳤다. 사이드카 발견은 «증거 후보» 이지 판정이 아니라는 규율대로."
+
+- date: 2026-09-12
+  agent: agy(gemini-3.1-pro-high) · cross-family adversarial reviewer
+  mode: sidecar
+  context: "preprep L15 4라운드 — 자정을 넘겨 실행된 분. 본체 기록은 2026-09-11 엔트리에 통합돼 있다"
+  dispatched_by: governor
+  outcome: accepted
+  evidence: "4건 지적 전건 실적발·수리. 그중 하나가 **R3 수리가 심은 결함**(`(\\w+)=` 가 네임스페이스 콜론을 못 먹어 `r:id` 유실 → 장 순서가 파일명 순 폴백). 나머지 셋도 fail-open: `<a:t xml:space=\"preserve\"> 미독 · `<a:sym>` 슬롯 미포함(실물 157개) · 템플릿 endParaRPr 이 허용 집합으로 승격"
+  tokens_subagent: UNMEASURED
+  dispatch_count_measured: 위 2026-09-11 엔트리에 통합 (클래스 통합)
+  residual: "NOT-CONVERGED — 5라운드가 남았다"
+  notes: "🟥 이 엔트리가 따로 있는 이유는 세션이 자정을 넘겼기 때문이다. ④-e 는 «오늘» 기준으로 세므로, 날짜 경계를 넘긴 세션은 양쪽 날짜에 기록이 필요하다 — 원장을 하루 단위로 읽는 계기의 성질이고, 통합 서술만 두면 오늘 자가 0 으로 보인다"

package/knowledge/shared/rules/auto_project_mapping.md

@@ -66,7 +66,7 @@ Mapping complete: N projects
 
 Basic mapping (steps 1–5) registers a project *lightly* (tracks/ + a starter CLAUDE.md + hub link). **Full-Harness Mode adds the project-local harness assets** — identity ① (Control Tower) propagating harness structure to a connected project; the *how* is executed via the Core Axis.
 
-**Scope**: target *mapped* projects only. For FH-self setup / acceleration baseline (zshrc, sentinels, the FH self-gate) use `/install-wizard` — do **not** run §6 on the FH hub itself. **Prerequisite**: the project is already mapped (steps 1–5); §6 is strictly additive. This mode is also the **emit terminus of a chamber run** — a simulate-first incubation that holds routes here on emit (`harness_incubator_doctrine.md §3` Minimal execution skeleton ⑤).
+**Scope**: target *mapped* projects only. (Mapping scopes *installation* of harness assets — it is **not** the precondition for FH's review gates: the Field-Harness Load-Bearing Change Gate fires on a merge verdict for any gate-shaped file, mapped or not — `field_verdict_crossfamily_gate.md §Registration is not a precondition`, 2026-09-08.) For FH-self setup / acceleration baseline (zshrc, sentinels, the FH self-gate) use `/install-wizard` — do **not** run §6 on the FH hub itself. **Prerequisite**: the project is already mapped (steps 1–5); §6 is strictly additive. This mode is also the **emit terminus of a chamber run** — a simulate-first incubation that holds routes here on emit (`harness_incubator_doctrine.md §3` Minimal execution skeleton ⑤).
 
 **Triggers**: "harness-ify this project", "full harness setup", "프로젝트 하네스화", "promote to full harness", or an opt-in prompt offered right after a basic mapping (*"Promote {project} to a full harness now?"*).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "3.1.3",
+  "version": "3.2.0",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "homepage": "https://github.com/chrono-meta/forge-harness#readme",
   "bugs": {
@@ -134,6 +134,15 @@
     "scripts/test_marker_crossfamily_lanes.sh",
     "scripts/residency_closure_scan.py",
     "scripts/test_residency_closure_lanes.sh",
+    "scripts/doc_claim_triad_scan.py",
+    "scripts/test_doc_claim_triad_lanes.sh",
+    "scripts/gate_shape_scan.sh",
+    "scripts/test_gate_shape_scan_lanes.sh",
+    "scripts/finding_fleet.sh",
+    "scripts/finding_verify.py",
+    "scripts/finding_verifier.sh",
+    "scripts/finding_pipeline.sh",
+    "scripts/test_finding_pipeline_lanes.sh",
     "scripts/test_marker_standpoint_lanes.sh",
     "scripts/test_marker_thirdparty_lanes.sh",
     "scripts/test_marker_axes_run_lanes.sh",
@@ -322,6 +331,7 @@
     "scripts/test_fh_qp_lanes.sh",
     "scripts/test_preprep_diagram_lanes.sh",
     "scripts/test_preprep_slide_refs_lanes.sh",
+    "scripts/test_preprep_font_lanes.sh",
     "scripts/test_action_yml_lanes.sh"
   ]
 }

package/plugins/fh-commons/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "fh-commons",
-  "version": "3.1.3",
+  "version": "3.2.0",
   "engines": {
     "claudeCode": ">=1.0.0"
   },