@chrono-meta/fh-gate 1.4.49 → 1.4.51

package/CATALOG.md

@@ -8,6 +8,12 @@ AI reads this file first when searching past work. Open individual files for det
 
 <!-- Add entries in reverse date order (newest at top) -->
 
+### 2026-07-07 | forge-harness | #sister-asset, #cross-audit, #revfactory, #harness-100, #agent-composer, #benchmarking, #linkedin, #source-verification, #diffusion-llm
+**File:** tracks/_audit/session_2026_07_07_revfactory-harness.md
+Sister-asset cross-audit of `revfactory/harness` + `revfactory/harness-100` (AX TF lead-recommended benchmarking target) vs FH — their axis = one-shot team-architecture generation + a 200-harness ready library (breadth/quick-start); FH's axis = dynamic composition (`agent-composer`) + governance (4-axis gate, irreversibility floors, continuity), which their pipeline lacks entirely. Plus LinkedIn source-verification for the operator's 2 queued insight links: diffusion-LLM paradigm-shift paper confirmed accurate (ICML 2026 Outstanding Paper Award, JustGRPO, arXiv:2601.15165 via official ICML blog); "Claude Code loop-engineering" post confirmed to be about `k021/claude-code-skills` — the *same* sister-asset Gemini already analyzed, not new content.
+- Decision: no functional import beyond a C-tier team-pattern naming label for `agent-composer` output; FH's governance moat holds (revfactory doesn't compete on that axis). Both LinkedIn links closed.
+- Open: adopt 6-pattern naming in agent-composer (operator HITL); harness-100-style pre-built library stays gated behind the existing 3+-recurrence trigger.
+
 ### 2026-06-27 | forge-harness | #sister-asset, #cross-audit, #hermes-agent, #nous-research, #self-improving-agent, #skills, #memory, #messaging-gateway
 **File:** tracks/_contrib/session_2026_06_27_hermes-agent-nous-self-improving-cross-audit.md (committed via _contrib consent lane — authored in an ephemeral cloud session where tracks/_audit/ is gitignored/non-durable)
 Sister-asset cross-audit of **Hermes Agent (Nous Research)** vs FH, triggered by a LinkedIn post (esperer) distilling Hermes' official *Tips & Best Practices* (post = faithful doc summary, not original methodology; same summary circulates on Threads). ~90% of Hermes' best-practice surface is already present in FH (persistent memory · auto-skill-from-repetition · skill self-improvement · context economy · delegation · model selection — all grounded to `plugins/*/skills/`), and on the **self-improvement + governance** axis FH is *ahead*: Hermes *advises* "review auto-generated skills," FH *mechanically enforces* it (pre-commit 4-axis gate + steel/phantom-quench + HITL). Key honest finding — most apparent "gaps" dissolve: cron/daemon is a **deliberate FH boundary** (`self_evolution_routine.md` §8 "recommendation surface, not a daemon"), external-memory-providers **already audited** (companion-store pluggable, 2026-06-11). Only genuine absence = **messaging gateway** (Telegram/Slack daily-driver), which is a *delivery channel*, not methodology.
@@ -177,7 +183,7 @@ CC built-ins utilization imports (operator-approved; video claims verified 9/13
 ### 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)
 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 = skill-splitter-style CATALOG split-mapping, RAG hybrid only after that.
+- 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.
 
 ### 2026-06-10 | forge-harness | #golden-probes, #offline-eval, #doc-code-coupling, #anthropic-4layer
@@ -282,7 +288,7 @@ Post-merge micro R-tier cleanup: corrected two prompt-regression probe expectati
 
 ### 2026-06-03 | forge-harness | #goal-quench, #skill-evolution, #mode-ladder, #sidecar-routing
 **File:** plugins/fh-meta/skills/goal-quench/SKILL.md
-Evolved goal-quench into a fluid core→pro→max mode ladder. Core: token-budget-gate + pipeline-conductor --quick; pro: +context-doctor +agent-composer; max: +plugin-recommender +cross-ecosystem-synergy-detection. Phase-1 budget verdict auto-recommends mode. Ran full-harness dogfood sweep (33 skills): fixed phantom refs, dead blocks, stale agent forks (4 deleted), trigger collision, and 3 skill-splitter splits.
+Evolved goal-quench into a fluid core→pro→max mode ladder. Core: token-budget-gate + pipeline-conductor --quick; pro: +context-doctor +agent-composer; max: +plugin-recommender +cross-ecosystem-synergy-detection. Phase-1 budget verdict auto-recommends mode. Ran full-harness dogfood sweep (33 skills): fixed phantom refs, dead blocks, stale agent forks (4 deleted), trigger collision, and 3 salience-splitter splits.
 - Decision: RED tier reframed as max-mode decomposition on-ramp, not hard block
 
 ### 2026-06-02 | _audit | sister-asset, token-efficiency, compression, headroom

package/CHEATSHEET.md

@@ -511,7 +511,7 @@ Claude agents feature
 |---|---|---|
 | `install-wizard` | First-install onboarding (zshrc, sentinels, the FH self-gate) | "first-time setup", "run the install wizard" |
 | `hub-cc-pr-reviewer` | Reads a PR diff → 8-matrix baseline-consistency check → review comment + merge call | "review this PR", "check this diff" |
-| `skill-splitter` | Splits an over-large SKILL.md that "does everything" into scoped files | "this skill is bloated", "SKILL.md too large", "split this skill" |
+| `salience-splitter` | Splits an over-large SKILL.md that "does everything" into scoped files | "this skill is bloated", "SKILL.md too large", "split this skill" |
 
 ### Agents (sub-agents, dispatched — not slash commands)
 

package/CLAUDE.md

@@ -142,7 +142,7 @@ Compose session-card candidates **into door ③ (field) and the 🔧 door (FH-de
 
 **Identity marker**: every greeting response (Step ②) opens with 🐿️ then an identity-revealing welcome line **on the same line** (a space after 🐿️; exact count not significant — the renderer collapses it — the invariant is *same-line*, not 🐿️ alone) — new / exploratory = "Welcome to FH." · returning = "Welcome back to FH." · operator (FH-dev state) = "The FH operator — good to see you." It is embedded in all skeletons above (do not strip it when composing doors); the exploratory branch template (`fh_detail_protocols.md` Step 2) uses the "Welcome to FH." line.
 
-**Guards**: explicit task-entry utterance → skip onboarding · once per session · code/debug requests → start working directly · project routing is a suggestion, mention at most once
+**Guards**: explicit task-entry utterance → skip onboarding **menu** (the door skeleton / greeting) — but this **never skips the Mode D companion-store freshness load** (pull + INDEX read + card-vs-commit reconcile); that is a data-load, not the menu, and it fires even when the first message is a task (measured miss 2026-07-05: task-first entry skipped the companion-store pull → stale memory → wrong recommendations; now hook-backed via `scripts/fh_session_load.sh`, see `modes_and_value.md §Session-start freshness`) · once per session · code/debug requests → start working directly · project routing is a suggestion, mention at most once
 **Metadata-is-not-intent guard**: the trigger is the user's **typed message only**. Session metadata — branch name (auto-derived from the first message, e.g. `claude/korean-greeting-*`), repo name, file paths — is **never** a task spec and never suppresses or redirects the greeting trigger. A bare greeting fires onboarding even when the branch name looks like a feature request; if the only "task" signal lives in metadata and not in what the user typed, treat the message as a greeting and run the greeting branch + door skeleton above.
 
 ## New Skill Creation Pre-Commit Gate
@@ -270,20 +270,15 @@ the target-tier sim all shared — the decorrelation value made concrete.
 
 ### Mode D Model Notice (fires once, at the same trigger as this gate)
 
-The moment FH self-development work begins (= the gate's own activation trigger: an FH asset is about
-to be modified), check the **session model** (self-identity; if the runtime withholds it, treat as
-unknown) and surface **one line** — then proceed, never block:
+When FH self-dev begins (an FH asset is about to change), check the **session model** and surface **one
+line**, then proceed — never block, **never switch the model** (human override inviolable): opus-tier+ →
+no notice · below-opus → recommend `/model opus`+ · unknown → static fallback recommend. Once per session;
+field-project (non-FH-asset) sessions never see it. Whether a session actually *escalates* (not just this
+advisory) is governed separately by `capability_escalation_consent.md`.
 
-- Model known and opus-tier or above → no notice (already optimal).
-- Model known and below opus-tier → *"이 작업은 FH 자체개발(Mode D)입니다 — 가용 최강 모델 핀을
-  권장합니다 (`/model opus` 이상; 측정 근거: README §Model setup). 그대로 진행해도 floored
-  디스패치가 깊이 턴을 커버하지만, 세션-레벨 설계 깊이는 핀이 좌우합니다."*
-- Model unknown (runtime withholds identity) → static fallback: *"FH 자체개발 작업입니다 — 세션
-  모델이 opus 이상이 아니라면 핀 전환을 권장합니다 (`/model opus`+)."*
-
-**Guards**: once per session · advisory only — **never switch the session model** (human override is
-inviolable; a pin is not a cap — tier-floor resolution §Floor governance) · field-project operation
-sessions (no FH asset modification) never see this notice — the Sonnet default stays friction-free.
+> **Detail**: See `knowledge/shared/harness-core/claude_md_gate_details.md §Mode-D-Model-Notice` — the
+> exact 3-branch wording (한글), the full guards, and the capability-escalation-consent cross-ref — read
+> when surfacing the notice.
 
 ## Field-Harness Load-Bearing Change Gate (cross-family, pre-merge)
 
@@ -348,6 +343,80 @@ trusted only at opus-tier+; below-floor runs the review or asks, never silently
 > **Detail** (discretion principle · 4-face signature · gate mechanics · n=7 qasp evidence):
 > `knowledge/shared/harness-core/field_verdict_crossfamily_gate.md`.
 
+## Field-Harness Diagnostic — "진단해줘 / 개선해줘" on a mapped project (compose → rank → HITL)
+
+The gate above fires on a **specific field code change**. This is its **on-demand pull sibling**: when
+the operator, working in a mapped project, asks to *diagnose* or *improve* the harness itself ("진단해줘",
+"개선해줘", "check this project"), don't hand-pick one skill — **compose the checks FH already has into a
+single ranked diagnostic list and get per-item approval.** The value is that the operator asks once and
+the harness surfaces *everything* worth fixing, ranked, instead of the operator having to know which of a
+dozen skills to invoke. Every fix is HITL — the diagnostic **proposes**, never auto-edits.
+
+**Composition (no-reinvention — every row is an existing check; the diagnostic only *routes and ranks*):**
+
+| Lens | Existing check | Catches (real examples from 2026-07-08) |
+|---|---|---|
+| **Confidentiality / leak** | `/public-surface-audit` (incl. Step 3c ignore-verification) | a hardcoded internal API host literal in a SKILL body; a `local_*_context.md` that is **tracked** when it should be gitignored (the gitignore-mistake class) |
+| **Split integrity** | `/phantom-quench` **Step 2.7** (bidirectional) | orphan detail sections + phantom pointers in a SKILL.md ↔ SKILL_detail.md pair |
+| **Token / salience** | salience-split candidates (`/context-doctor` · `/salience-splitter` targets) | oversized always-loaded SKILL.md / CLAUDE.md — trim candidates |
+| **Structure** | `/harness-doctor` (L1–L4) | orphaned/redundant/decorative units, missing Done-When, ≥70% overlap |
+| **Verdict/gate degrade** | `scripts/degrade_direction_scan.sh` | a field verdict/gate helper that degrades toward permissive (advisory pre-screen) |
+
+**Output**: one ranked list, `M` (must-fix) / `S` (should-fix) / `R` (recommended) — same tiering as
+harness-doctor — each item stating *lens · file:line · one-line fix*. **Then HITL**: the operator approves
+per item (or a batch); an approved fix routes to the owning skill's normal path (and, if it is itself a
+load-bearing field change, through the Load-Bearing Change Gate above). **Nothing is auto-fixed** — the
+diagnostic's job is the *intelligent list*, the human's job is the *go*.
+
+**Guards**: (a) fires on a **project-level** "진단/개선" ask, not a single-file edit request (those go
+straight to the relevant skill); (b) **once per ask** — not a per-turn nag; (c) **company residency** —
+run leak/confidentiality lenses locally, sanitize before any cross-family dispatch, and *surface*
+company-sensitive findings (tracked company hosts, git-history rewrites) for operator decision rather
+than auto-fixing them (dogfood 2026-07-08: the `local_pmh_context.md` tracked-company-hosts finding was
+surfaced, not auto-untracked — history rewrite is the operator's call); (d) **autonomy floor** — the
+compose/rank judgment is trusted at opus-tier+; below-floor, run the individual checks and present raw
+rather than silently skipping a lens. Scale to the ask: a quick "뭐 고칠 거 있어?" runs the cheap
+mechanical lenses (leak · split · token); "제대로 진단해줘" runs all five + harness-doctor depth.
+
+## Onboarding / Acceleration Autopilot — "새 프로젝트 · 하네스 작성 · 가속화" (discover → compose → rank → install-HITL)
+
+The **install-direction twin of the Field-Harness Diagnostic**: same `compose → rank → HITL` engine, but
+it decides *what to install/wire* instead of *what to fix*. When the operator enters an onboarding /
+acceleration door (returning-menu ①②③: "새 프로젝트", "하네스 작성/작성해줘", "이 프로젝트 가속화",
+"harness-ify", "accelerate this project"), don't hand-run one skill — **auto-discover the local state,
+let the innovator center a recommend cascade, produce a ranked install plan, and gate every install.**
+
+**Flow:**
+
+1. **Phase 0 — State Audit + branch (auto-discovery)**: read the target's existing `.claude/agents|skills`,
+   `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
+   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
+   on FH-dev), composing `plugin-recommender` (Tier 0 platform → Tier 1 official → Tier 2/3) +
+   `cross-ecosystem-synergy-detection` (locally-connected skills worth wiring) + inferred technical level
+   (conversation-cue read, also imported from revfactory) to shape *what* and *how much*.
+3. **Ranked install plan**: one list, `M`/`S`/`R`, each item = *what · why · source (Tier 0 built-in / Tier 1
+   official / local sibling / FH scaffold) · exact install command*. No-reinvention: an official/built-in that
+   covers the need ranks above a net-new scaffold.
+4. **Install — HITL, non-overwriting**: per-item approval; **never clobber an existing `.claude/`** (propose
+   merge/skip if present — this is FH's edge over revfactory's post-plan auto-write and harness-100's raw
+   `cp`). Any generated/installed FH asset runs the **4-axis gate**; a field scaffold runs
+   `asset-placement-gate` + `steel-quench`. **"끝까지 해줘 / 자율로 완주" → full-autonomy**: run the whole
+   plan under the `/goal-quench` budget+quality gate (token cost accepted by the operator), still
+   non-overwriting and still gated per asset — autonomy removes the per-item *prompt*, never the *gate*.
+
+**Guards**: (a) **non-overwriting is inviolable** — the one thing both revfactory surfaces get wrong; FH
+proposes merge, never clobbers; (b) **no-reinvention** — Tier 0/1 first, scaffold only what adds governance;
+(c) **company residency** — discovery of a company sibling repo surfaces it, does not auto-map/leak it;
+(d) **autonomy floor** — the discover/rank judgment is trusted at opus-tier+; below-floor, present the raw
+recommend and ask; (e) **once per door-entry**, not a per-turn nag. This is the door ③ (accelerate) engine
+and the new-project/harness-write path made autonomous — the operator asks once and the harness discovers,
+ranks, and (on request) installs everything worth wiring.
+
 ## Irreversibility Gates — Surface-Class Degrade Invariant (shared spine of the two gates below)
 
 The two gates that follow (Pre-Publish, Destructive-Op) guard **irreversible surfaces**. The floor they
@@ -537,7 +606,7 @@ Proposal format: `"I see [X]. Want me to run /[skill] to [one-line description]?
 | "add this MCP server", "mount this MCP", "mcp.json에 추가", "connect this tool server" (external-MCP mount intent — **proactive**, fire *before* first tool call; mount intent only — a failing/erroring mounted server is `/mcp-circuit-breaker`'s row above) | `templates/.claude/rules/mcp_tool_gating.md` (name-keyed ask/allow table — never trust server annotations or names; fill §3 at mount time) |
 | "token budget", "how expensive", "estimate tokens", "will this cost a lot" | `/token-budget-gate` |
 | "did my rule change break anything", "regression check", "test harness changes" | `/prompt-regression` |
-| "SKILL.md too large", "split this skill", "skill is bloated", "skill file too long" | `/skill-splitter` |
+| "SKILL.md too large", "split this skill", "skill is bloated", "skill file too long" | `/salience-splitter` |
 | "review for the team", "CTO review", "decision-maker", "share with leadership", "approval deck" | `/apex-review` |
 | "run full pipeline", "verify everything", "end-to-end sweep", "chain all verifications" | `/pipeline-conductor` |
 | "help me write a prompt", "build a prompt", "improve this prompt", "prompt template" | `/meta-prompt-builder` |
@@ -546,6 +615,8 @@ 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` |
 | "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) |
+| **"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 below → 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 below → Phase 0 auto-discover + branch → innovator-centered recommend → ranked install plan → HITL per item, non-overwriting; "끝까지 자율로" → full-autonomy under /goal-quench gate) |
 
 **Guard**: Do not propose a skill that is already running. One signal = one-line proposal (no pressure). Before proposing, consult the UAP (§Operational Adaptation Loop): a skill the user has rejected 3+ times is **suppressed**, not re-proposed.
 For per-skill utterance patterns, see the relevant `SKILL.md §Trigger Phrases` section.

package/README.md

@@ -214,7 +214,7 @@ two more signatures keep it running: `harvest-loop` (each session's lessons beco
 | `token-budget-gate` *(fh-commons)* | Pre-task token cost estimate | "How expensive is this?" |
 | `mcp-circuit-breaker` *(fh-commons)* | MCP tool failure pattern detection | "MCP keeps failing" |
 | `quench-challenger` *(fh-commons)* | Adversarial pressure-test agent | "Challenge this with a devil" |
-| *(+ additional assets)* | marketplace-gate · contention-layer · edit-manifest · fact-checker · goal-quench · hub-persona-auditor · install-doctor · memory-hygiene · persona-innovator · prompt-regression · public-surface-audit · skill-splitter | |
+| *(+ additional assets)* | marketplace-gate · contention-layer · edit-manifest · fact-checker · goal-quench · hub-persona-auditor · install-doctor · memory-hygiene · persona-innovator · prompt-regression · public-surface-audit · salience-splitter | |
 
 | Active count | Diagnosis |
 |:---:|---|
@@ -233,7 +233,7 @@ two more signatures keep it running: `harvest-loop` (each session's lessons beco
 | Gate / Guard | `token-budget-gate` · `asset-placement-gate` · `marketplace-gate` |
 | Discovery | `plugin-recommender` · `cross-ecosystem-synergy-detection` · `frontier-digest` · `verify-bidirectional` |
 | Content / Simulation | `sim-conductor` · `apex-review` · `meta-prompt-builder` · `deep-clarify` |
-| Setup | `install-wizard` · `hub-cc-pr-reviewer` · `skill-splitter` |
+| Setup | `install-wizard` · `hub-cc-pr-reviewer` · `salience-splitter` |
 
 > **Full phrasebook** — every skill + agent with its one-line definition and the plain-language phrase
 > that triggers it: [`CHEATSHEET.md` §12](CHEATSHEET.md#12-skills--agents--what-each-does-and-what-to-say).

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

@@ -0,0 +1,125 @@
+# Capability-Escalation Consent Protocol
+
+> **Principle**: any escalation that raises **cost or trust surface** — recruiting a **cross-family
+> sidecar** (external model families see the work) or a **model-tier floor-up** (Sonnet → Opus, higher
+> $/token) — is **consent-gated and negotiated up front**, never sprung silently. A user who was never
+> asked, then finds a paid/external escalation happened, feels **blindsided (뒤통수)**. The harness
+> must run **intelligently on Claude Code alone at the Sonnet floor** for anyone who declined, using
+> **sub-agents** in place of cross-family sidecars — as a *first-class mode*, not a degraded one.
+
+This is a **규약 (convention)**, not a per-call decision: the same answer holds for the whole session
+once settled, and is **remembered across sessions** (UAP) so it is asked at most once.
+
+---
+
+## Two escalation axes (same consent shape)
+
+| Axis | Escalation | Why it needs consent | Floor when declined |
+|---|---|---|---|
+| **(a) Cross-family sidecar** | recruit codex / agy / gemini / local-4090 as a verifier | work leaves the Claude boundary (external family sees it) + external billing | **Tier-3 CC-only sub-agent** (isolation-decorrelation, honest same-family note) |
+| **(b) Model-tier floor-up** | Sonnet → Opus for a depth-heavy turn | higher $/token (Opus ≈ 3–5× Sonnet); the operator's real cost lever | **stay at Sonnet** (the established minimum-recommended floor) |
+
+**Sonnet = minimum-recommended model is already established** — so the declined-floor is safe: the
+harness is *designed* to run well at Sonnet, not crippled by it (`[[feedback_harness_aerodynamics_perceived_perf]]`).
+
+---
+
+## When consent is settled — two entry points
+
+### 1. Onboarding negotiation (install-wizard) — the no-surprise path
+
+install-wizard **explicitly negotiates both axes** at setup, as named items:
+- *"Allow cross-family sidecars (codex/agy/local) for adversarial verification of load-bearing changes? They add external-family decorrelation but external billing applies."* → records `sidecar_consent`.
+- *"Allow automatic Sonnet→Opus floor-up on depth-heavy turns? Opus is ~3–5× the cost; declining keeps you at the Sonnet floor and asks per-occasion instead."* → records `floorup_consent`.
+
+Settling this at onboarding is the **whole point**: the escalation is then *expected*, never a surprise
+on the bill or the egress log.
+
+### 2. Runtime ask-once (for anyone who skipped onboarding setup) — the graceful path
+
+A user who skipped explicit setup is **not** auto-escalated. Instead, the **first time** an escalation
+is actually needed:
+- **Ask once**, at the moment of need, framed with the cost/trust reason:
+  *"This turn needs Opus depth (higher cost) — proceed at Opus, or stay at Sonnet?"* /
+  *"This load-bearing change is best verified cross-family (external billing) — recruit a sidecar, or verify with CC sub-agents only?"*
+- **Accept** → record consent (UAP), proceed, no re-ask.
+- **Decline** → record decline (UAP), **mark the escalation "recommended only"** going forward (surface
+  it as a one-line recommendation when relevant, **never a re-nag**), and **proceed at the floor**
+  (Sonnet / Tier-3 sub-agent).
+
+The ask fires **once per axis**; the answer is remembered. A declined axis becomes a standing floor, not
+a per-turn question.
+
+---
+
+## The declined mode is first-class, not "degraded"
+
+When an axis is declined (or no sidecar is reachable), the fallback is **the user's chosen normal
+operating mode**, and must be framed that way:
+
+- **Cross-family declined → Tier-3 CC-only sub-agent verification.** Multiple **isolated** Claude
+  sub-agents adversarially verify (isolation-decorrelation), with an **honest same-family note**
+  ("no cross-family diversity — verification is isolation-decorrelated only"). This is intelligent
+  operation, **not** "reduced value / degraded" language. (`[[feedback_judge_robustness_mechanical_anchor]]`
+  still holds: the governor keeps the terminal verdict + a mechanical anchor.)
+- **Floor-up declined → stay at Sonnet**, run the turn with good harness structure. No apology framing.
+
+**Reframe rule**: the Sidecar Resolution Protocol's Tier-3 line and auto-decorrelation's degrade ladder
+must not read "no diversity; reduced value" for a *declined* user — that pathologizes their choice.
+Distinguish **declined** (chosen floor — first-class) from **unavailable-but-wanted** (genuine
+degrade-with-note). Only the latter carries the degrade framing.
+
+### Reconciliation with the corp fail-closed invariant
+
+The pmh corp degrade-invariant (`local_pmh_context.md` auto-decorrelation Step 6) says a load-bearing
+change with **no reachable cross-family panel → NOT-CONVERGED / ask operator**. That is the
+**unavailable-but-expected** case (consent given, panel down). The **declined** case is different: the
+user opted out, so Tier-3 sub-agent verification **is** the standing bar (with the honest same-family
+note), and load-bearing changes proceed under it — not blocked. Membership: `floorup_consent`/
+`sidecar_consent == declined` in the UAP routes to the first-class floor; absence of a *wanted* panel
+routes to fail-closed.
+
+---
+
+## UAP persistence (behavioral pref — never domain content)
+
+`operational_adaptation.md` UAP gains two fields:
+- `sidecar_consent: accepted | declined | unset`
+- `floorup_consent: accepted | declined | unset`
+
+**READ** (session start / at point of need): `declined` → route to floor, surface as recommendation
+only, no re-nag. `accepted` → escalation available (still per-need, no auto-run). `unset` → ask-once
+on first need (runtime path above).
+**WRITE**: on onboarding settle, or on the first runtime accept/decline.
+
+Ephemeral/cloud sessions (UAP wiped) → operate from the **Sonnet floor + CC-only** default (the safe
+floor), do not fabricate consent.
+
+---
+
+## Cost lens (why this IS the cost-governance mechanism)
+
+The floor-up consent prompt is **the operator's cost lever made explicit** (measured: Sonnet-economized
+≈ 34× subscription; Opus-full 40–60×, `cost_report_2026-07-07`). Default Sonnet floor + escalate-Opus-
+**only-where-depth-pays**-with-consent is precisely "amortize Opus on the turns that earn it." Pair with
+a **free internal-model execution lane** where the environment has one (`[[feedback_multimodel_3lane_architecture]]`)
+to offload exec cost off the paid API entirely. The protocol turns hard-won economizing into a mechanical default.
+
+---
+
+## Done When
+
+- **Both axes negotiated at onboarding** (install-wizard names sidecar + floor-up as consent items). *[mandatory-pass — grep install-wizard for both items]*
+- **Runtime ask-once wired** for `unset` consent at first need; decline → recommend-only + floor, no re-nag. *[judged — pair: Sonnet target-tier blind sim of a skipped-onboarding session hitting first floor-up]*
+- **UAP fields present + READ applied** (`sidecar_consent`, `floorup_consent`). *[mandatory-pass — grep operational_adaptation.md]*
+- **Declined-mode reframed first-class** (no "degraded/reduced-value" language on a declined user's Tier-3 path). *[judged — pair: challenger reads auto-decorrelation + Sidecar Resolution for pathologizing language]*
+- **Corp fail-closed reconciled** (declined ≠ unavailable-but-wanted). *[judged — pair: the target-tier sim above exercises both branches]*
+
+## Guards
+
+- **Human override inviolable** — a consent is a default, never a cap; the operator can always force a
+  tier/sidecar for a given turn (`[[feedback_verify_before_downgrade]]` floor governance).
+- **Never auto-switch the session model** — the floor-up ASK proposes; the human acts (`/model`). The
+  protocol never flips the model itself.
+- **Sonnet floor is a floor, not a ceiling** — declined-floor-up still escalates *within* Sonnet's
+  harness depth (sub-agents, good structure); it does not cap capability, only cost/trust surface.

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

@@ -182,3 +182,26 @@ freshness + each operator's local session-start binding.
 **Salience-dependent** — prose, not hook-enforced; on a weaker tier may silently not fire. Backstops: ⑤'s
 removal obligation + the reader-side result-file read. A hook-enforced writer-side is a future hardening
 candidate, not built today (keep the surface thin).
+
+## §Mode-D-Model-Notice
+
+The moment FH self-development work begins (= the gate's own activation trigger: an FH asset is about
+to be modified), check the **session model** (self-identity; if the runtime withholds it, treat as
+unknown) and surface **one line** — then proceed, never block:
+
+- Model known and opus-tier or above → no notice (already optimal).
+- Model known and below opus-tier → *"이 작업은 FH 자체개발(Mode D)입니다 — 가용 최강 모델 핀을
+  권장합니다 (`/model opus` 이상; 측정 근거: README §Model setup). 그대로 진행해도 floored
+  디스패치가 깊이 턴을 커버하지만, 세션-레벨 설계 깊이는 핀이 좌우합니다."*
+- Model unknown (runtime withholds identity) → static fallback: *"FH 자체개발 작업입니다 — 세션
+  모델이 opus 이상이 아니라면 핀 전환을 권장합니다 (`/model opus`+)."*
+
+**Guards**: once per session · advisory only — **never switch the session model** (human override is
+inviolable; a pin is not a cap — tier-floor resolution §Floor governance) · field-project operation
+sessions (no FH asset modification) never see this notice — the Sonnet default stays friction-free.
+
+> **Related — capability-escalation consent**: whether a session actually *escalates* to a stronger
+> model or a cross-family sidecar (not just this advisory notice) is governed separately by
+> `knowledge/shared/harness-core/capability_escalation_consent.md` — the negotiated-consent protocol
+> (UAP `sidecar_consent`/`floorup_consent`) that decides ask-once vs. no-surprise floor-up/sidecar use.
+> This notice is the passive advisory; that doc is the active escalation gate.

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

@@ -37,12 +37,31 @@ ls ../ | grep -iE '(forge-harness|meta-harness|-harness|-hub)'
 ls .claude/registry/LOCAL_SKILL_REGISTRY.md 2>/dev/null
 ```
 - File exists and modified within 7 days → load into session
-- Missing or older than 7 days → regenerate:
+- Missing or older than 7 days → regenerate.
+
+**No hardcoded root — derive the install location (users install FH anywhere).** The projects root is
+the *parent of the FH repo*, discovered at runtime, never a literal `~/projects` / `~/PycharmProjects`
+(a hardcoded root silently returns 0 on any machine whose layout differs — the 2026-07-05 dead-path
+`fail-open` bug: `find ~/projects` on a `~/PycharmProjects` machine → 0 catches → the registry is
+overwritten empty and cross-project summon goes dark):
 ```bash
-find ~/projects -path "*/.claude/skills/*/SKILL.md" \
-  -not -path "*/forge-harness/*" 2>/dev/null
+HUB="${CLAUDE_PROJECT_DIR:-$(pwd)}"          # FH 레포 위치 (설치 위치 무관, 감지)
+ROOT="$(cd "$HUB/.." 2>/dev/null && pwd)"     # 형제 프로젝트가 사는 부모 = 프로젝트 루트
+# 두 레이아웃 모두 포착: .claude/skills/*/SKILL.md AND 루트-레벨 */SKILL.md (예: gstack).
+# vendored(.venv·site-packages·node_modules·.git) 제외 — 없으면 playwright/streamlit 스킬까지 삼킴.
+FOUND="$(find "$ROOT" -name SKILL.md \
+  -not -path "*/.venv/*"  -not -path "*/site-packages/*" \
+  -not -path "*/node_modules/*"  -not -path "*/.git/*" \
+  -not -path "$HUB/*" 2>/dev/null)"    # exclude FH's own subtree by DERIVED path, not a name-literal (works when FH is cloned under any dir name)
 ```
-Group by project → update `.claude/registry/LOCAL_SKILL_REGISTRY.md`. Propose cross-project skills when request maps to registry. Scan once per session.
+Then **fail-closed** (irreversible-ish: a silent empty overwrite blinds the bus): if `$FOUND` is empty
+**and** the existing registry has >0 entries, do **not** overwrite — flag `⚠️ scan returned 0 (root=$ROOT);
+kept existing registry` and skip the rewrite. Only rewrite when the scan is non-empty (or the registry
+was absent). Group by project (parent dir name). Record per skill: name · path · description · trigger
+phrases · `requires_cwd` · `direct-executable` · `origin(FH|project|external)`+trust. **Non-FH skills are
+propose-only (ask-tier), never auto-run** — a cross-project skill body is an injection surface. Propose
+cross-project skills when a request maps to the registry. Scan once per session. (Detection belongs at
+install too — `/install-wizard` records HUB/ROOT so the runtime never guesses; see install-wizard.)
 
 ### Step 2 — Active Proposal
 

package/knowledge/shared/harness-core/measurement-integrity-checklist.md

@@ -1,7 +1,7 @@
 # Measurement-Integrity Checklist — cross-model measurement pre-flight
 
 > A cross-model measurement is only trustworthy if its **instrument** is verified first.
-> Measurement integrity is a *precondition*, not a result. Three observed failure modes, each with a
+> Measurement integrity is a *precondition*, not a result. Four observed failure modes, each with a
 > concrete countermeasure. Consult this before any FH measurement that compares models (sims, sidecar
 > comparisons, capability-equalizer runs, the-bible model panels, A6-class experiments).
 
@@ -16,6 +16,7 @@ becomes a gate other skills invoke, revisit the weight.
 | 1 | **Silent model fallback** — passing a model *slug* silently resolved to a weaker model (e.g. an `agy` slug fell back to Flash) instead of the intended one. The run *looks* like the named model but isn't. | **Pin the display name, not the slug** (e.g. `"Gemini 3.1 Pro (High)"`, not a bare slug). Confirm the resolved identity, don't assume the slug binds. |
 | 2 | **Non-deterministic borderline verdicts** — contested/borderline cases flip across runs (observed: haiku 4/4 flip; flagship models flip too — flipping is **not** a tier signal). A single draw is noise, not a measurement. | **reps ≥ 3 on any borderline/contested verdict.** A single run on a contested case is inadmissible. Report the flip pattern (STABLE vs FLIP), not just the modal verdict. |
 | 3 | **Generic self-identity probe** — a probe any model passes ("are you working? → OK") proves nothing about *which* model answered. | **Use a discriminating probe** — one that two different models answer *differently*. A generic-pass probe is invalid. The probe is a **pattern, not a fixed string**: a probe that discriminates Opus 4.8 from Sonnet 4.6 today may both-pass a future model generation, so **re-validate the probe each model generation** (same staleness class `memory-hygiene` exists to catch). |
+| 4 | **Serving-path / quantization variance** — the *same* display-name model served over two different backends (different quantization/infra) is a **different instrument** and yields materially different measurements. Observed: one GLM-5.2 model family gave effect-size delta **+0.21** when served via an internal NVFP4-quantized deployment vs **+0.08** via an OpenRouter relay — same model name, ~2.6× different effect (n=864, reps≥3). A correctly-pinned display name (item #1) is **necessary but not sufficient**. | **Pin *and record* the serving path** — backend host + quantization, not just the display name. Two runs are comparable only if the serving path matches; a name match across different infra is an implicit apples-to-oranges. When you cannot hold it fixed, **report the serving path as a measured variable**, not a constant. |
 
 ## Why these are entangled (and why they matter beyond their own scope)
 
@@ -28,10 +29,17 @@ single-draw artifact. Item #3 (discriminating probe) **embodies** the judge-robu
 mechanical-anchor principle — don't trust self-reported identity, prove it discriminatingly
 ([[feedback_judge_robustness_mechanical_anchor]]).
 
+Item #4 (serving-path variance) **sharpens** item #1 into a two-part identity: #1 catches the *wrong
+model* (a slug that fell back); #4 catches the *right model on the wrong instrument* (a correct name
+served over a different quantization/backend). The verified identity a measurement records is therefore
+**name + serving path**, not name alone — a family-decorrelation claim (cross-family sidecar) is only
+sound once the serving path of each family is itself pinned, else "different family" silently smuggles
+"different infra" ([[reference_measurement_serving_path_variance]]).
+
 ## Done When
 
-- The checklist enumerates all three failure modes, each with its countermeasure.
-  *Check class: mandatory-pass (binary — three items present, each with a countermeasure).*
+- The checklist enumerates all four failure modes, each with its countermeasure.
+  *Check class: mandatory-pass (binary — four items present, each with a countermeasure).*
 - The probe item specifies a **discriminating** test and rejects generic probes.
   *Check class: judged, pair: a probe that two different models both pass must FAIL this check; a
   discriminating one must distinguish them.*
@@ -57,3 +65,15 @@ mechanical log.
 ambiguity). Sister findings: [[feedback_correlated_blindspot_union_over_majority]] (reps≥3 prerequisite),
 [[feedback_judge_robustness_mechanical_anchor]] (discriminating-probe = mechanical anchor),
 [[reference_agy_model_catalog]] (display-name pin — agy slug fallback documented there).
+
+**#4 added** (2026-07-05): serving-path variance surfaced in a cross-family verdict-invariance run
+(n=864, borderline fixtures × 2 conditions × K=6 paraphrase × reps≥3). An identical GLM-5.2 model name
+served over an internal NVFP4-quantized deployment vs an OpenRouter relay gave +0.21 vs +0.08
+effect-size delta — quantifying that "same model name ⇒ same measurement" is false. Provenance +
+generalizable finding: [[reference_measurement_serving_path_variance]].
+
+**External corroboration** (2026-07): the local-LLM community independently reports the same hazard —
+practitioners conflate "running model X" with running a *pruned/quantized derivative* of X (aggressive
+low-bit quantization + expert pruning measurably degrade long-context quality while the model *name* is
+unchanged). This is a general measurement pitfall, not FH-specific: a leaderboard or replication that
+pins only the display name silently compares different instruments across serving paths.

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

@@ -167,6 +167,35 @@ buff and degrades that model's realized intelligence** — not just Claude's. Th
   is autocomplete/QA only, which is exactly its demoted role. (Derived 2026-07-03, operator + cross-vendor
   Gemini concurrence; extends the governor=native-CC point to every vendor.)
 
+### Batch-judging corollary — the native harness is for interactive/agentic work, not batch scoring
+
+The vendor-native harness gives a model its highest capability for **interactive, agentic** tasks
+(repo-grounded audit, multi-step design, tool-use) — but that *same* agentic loop is a **liability for
+high-volume batch judging**: a deterministic verdict emitted over N fixtures, where there is nothing for a
+tool-use loop to do. Measured 2026-07-04 (H1 verdict-invariance run): the native `codex exec` spins a full
+agentic session per judge (hooks + reasoning ≈ an order of magnitude more tokens than a bare completion),
+and native `agy -p` (once its headless permission-wait is cleared) returns *agentic prose* — a "Summary of
+Work" — rather than a parseable last-line verdict. Both **complete**, but at a cost/parse profile wrong for
+batch.
+
+So the dispatch splits by *shape of the task*, not just by family:
+
+- **Batch cross-family judging** (steel-quench Step 0.6 verdict-invariance, auto-decorrelation over many
+  items, any fixed-fixture flip count) → **clean completion APIs** (OpenRouter, model pinned by
+  *display-name* + `served`-field silent-route check) **+ free local** (a 4090 ollama endpoint). Clean,
+  cheap, parseable, per-call pinnable. *Caveat*: a local thinking model needs a large enough output budget
+  or it truncates inside `<think>` and emits an empty verdict — a config axis, not a capacity limit.
+- **Interactive / agentic verification** (repo-grounded catching, the divergence audits where cross-family
+  disagreement *localizes* a bug) → the **native CLIs** (`codex`, `agy`/Antigravity), where the harness
+  earns its overhead.
+
+This is **not** a contradiction of the harness-depth thesis — it *is* it. The harness lifts capability
+exactly where judgment + tools + iteration matter; for a one-shot self-contained verdict the loop has no
+work, so its depth becomes pure cost. Pick the naked API for batch scoring, the native harness for agentic
+audit. (Derived 2026-07-04, operator + H1 measurement; the batch-side dual of the vendor-native thesis
+above. The native-harness Gemini path via `agy` is headless-usable again once tool-permission auto-proceed
+is set — see [[reference_agy_model_catalog]] for the pin/permission mechanics.)
+
 **Maintenance-Cost Rule** — a compatibility layer is cheap as a *thin entrypoint*, expensive when it
 *duplicates canonical knowledge*. The test:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chrono-meta/fh-gate",
-  "version": "1.4.49",
+  "version": "1.4.51",
   "description": "FH runtime adapters — run FH governance, skills, and agents via Claude or Codex with machine-parseable gates.",
   "license": "MIT",
   "keywords": [

package/plugins/fh-meta/skills/agent-composer/SKILL.md

@@ -157,6 +157,13 @@ agent-composer — Composition Plan
 Execute? (Y: run all / E: edit then run / N: cancel)
 ```
 
+Optionally name the composition's shape in the plan header (`Composition pattern: {name}`) so the
+operator recognizes the structure at a glance — a recognition aid, not a routing input.
+
+> **Detail**: See `SKILL_detail.md §Composition-Pattern-Labels` — the six revfactory-vocabulary labels
+> (Pipeline / Fan-out-in / Expert Pool / Producer-Reviewer / Supervisor / Hierarchical) mapped to the
+> existing FH constructs they name — read when labeling a plan header.
+
 ---
 
 ## Step 2.5 — Model Routing Decision (complexity_routing)

package/plugins/fh-meta/skills/agent-composer/SKILL_detail.md

@@ -462,3 +462,25 @@ agent-composer also acts as Curator — surveys existing agents/skills/assets an
 - **External positioning**: Independent convergence with hermes-agent (Nous Research) curator.py pattern
 
 > Architecture basis: Anthropic [Harness Design for Long-Running Apps](https://www.anthropic.com/engineering/harness-design-long-running-apps) — single agent ($9, fails) vs. multi-agent harness ($200, perfect). Cost gap justified by quality gap.
+
+---
+
+## §Composition-Pattern-Labels — revfactory Team-Pattern Vocabulary (naming only)
+
+Optional recognition labels for the `Composition pattern: {name}` line in the Step 2 plan header.
+Borrowed from the revfactory/harness team-pattern vocabulary (sister-asset cross-audit
+`tracks/_audit/session_2026_07_07_revfactory-harness.md`, 2026-07-07). **Each label names an FH
+construct that already exists** — this is a vocabulary import, not a new dispatch mechanism
+(no-reinvention). Use a label only when it fits cleanly; a bespoke composition needs no forced label.
+
+| Pattern label | = existing FH construct |
+|---|---|
+| **Pipeline** | sequential Waves, each consuming the prior's fan-in (Wave 0→1→2) |
+| **Fan-out-in** | parallel Wave 1 split → Step 4 fan-in integration |
+| **Expert Pool** | Step 0.2 capability-fit routing to specialist agents |
+| **Producer-Reviewer** | a generating agent + an adversarial reviewer (`challenger` / Critic) |
+| **Supervisor** | one orchestrator/governor delegates then integrates (the default here) |
+| **Hierarchical** | nested supervisors — cluster orchestration (memory `project_fh_cluster_orchestration`) |
+
+This is a recognition aid, not a routing input — the actual plan still comes from Steps 0.2–2. If a
+composition matches none of the six, omit the label rather than stretching one to fit.

package/plugins/fh-meta/skills/auto-decorrelation/SKILL.md

@@ -100,11 +100,20 @@ Local 4090 = **canary tier** (evidence-of, never terminal verdict).
 
 ## Step 6 — Degrade ladder (the intelligent scale-down)
 
+**Consent branch first — declined ≠ degraded** (`[[capability_escalation_consent]]`): if the UAP has
+`sidecar_consent: declined`, do **not** probe/recruit — route straight to **Tier-3 CC-only sub-agent
+verification** (multiple isolated Claude sub-agents, isolation-decorrelation) as a **first-class chosen
+mode**, with an honest *same-family* note but **no "reduced value / degraded" framing** — the user chose
+this floor. `unset` → ask-once at first load-bearing need (accept → proceed; decline → record + this
+branch). Only proceed to the discovery ladder below when consent is `accepted`.
+
 1. frontier cross-family CLI present → recruit it (decorrelated, at-floor) — best.
 2. only local 4090 present → canary pre-screen + in-session opus governor (canary, not full decorrelation).
 3. nothing present → in-session same-family + **honest below-floor/same-family note** (residual named).
 
-Env non-determinism (CLI presence varies) → **silent degrade, never hard-fail**.
+Env non-determinism (CLI presence varies) → **silent degrade, never hard-fail**. Distinguish this
+**unavailable-but-wanted** case (consent given, panel down → degrade-with-note; for a *load-bearing corp*
+surface, fail-closed per `local_pmh_context.md`) from the **declined** case above (chosen floor, first-class).
 
 ## Step 7 — Output
 

package/plugins/fh-meta/skills/context-doctor/SKILL.md

@@ -117,7 +117,7 @@ Run the audit bash (§Step-Bash) and apply thresholds:
 | CLAUDE.md | Exceeds 300 lines | Section-by-section compression / move completed sections to archive |
 | MEMORY.md | Exceeds 180 lines | Check entry count + move `✅ CLOSED` items to archive section |
 | memory/*.md single file | Exceeds 30K (300 lines) | Suggest splitting accumulated history into separate files |
-| SKILL.md (any) | > 300 lines AND no SKILL_detail.md | Propose `/skill-splitter` — governance-semantic split (not compression); compression removes content, splitting routes it on-demand |
+| SKILL.md (any) | > 300 lines AND no SKILL_detail.md | Propose `/salience-splitter` — governance-semantic split (not compression); compression removes content, splitting routes it on-demand |
 
 **Frequency**: When explicitly called with `/context-doctor` or auto-invoked at session start when MEMORY.md is detected at 180+ lines.
 
@@ -259,7 +259,7 @@ context-doctor (token/context) · harness-doctor (structure) · sim-conductor (s
 |---|---|
 | Want to also check structure after resolving token waste | `/harness-doctor` |
 | Want to validate prescription results from external user perspective | `/sim-conductor Area A` |
-| SKILL.md diagnosed as over-loaded (> 300 lines, no SKILL_detail.md) | `/skill-splitter` — governance-semantic split |
+| SKILL.md diagnosed as over-loaded (> 300 lines, no SKILL_detail.md) | `/salience-splitter` — governance-semantic split |
 | All three skills mentioned simultaneously | Three-Doctor Loop circuit activated — diagnosis→prescription→re-diagnosis cycle
 
 ## Done When
@@ -278,4 +278,4 @@ context-doctor (token/context) · harness-doctor (structure) · sim-conductor (s
 **→ Three-Doctor Loop chain (auto-propose after diagnosis):**
 - Prescription modifies SKILL.md / rules / CLAUDE.md → **propose `/harness-doctor`** re-check after fix (structural integrity)
 - Prescription addresses user-facing context (onboarding, README, install guides) → **propose `/sim-conductor Area A`** (external user impact validation)
-- SKILL.md detected as over-loaded → **auto-propose `/skill-splitter`**: `"I see [skill-name] SKILL.md is [N] lines with no SKILL_detail.md. Want me to run /skill-splitter to do a governance-semantic split?"`
+- SKILL.md detected as over-loaded → **auto-propose `/salience-splitter`**: `"I see [skill-name] SKILL.md is [N] lines with no SKILL_detail.md. Want me to run /salience-splitter to do a governance-semantic split?"`

package/plugins/fh-meta/skills/context-doctor/SKILL_detail.md

@@ -73,11 +73,11 @@ wc -l memory/MEMORY.md 2>/dev/null
 # memory/*.md files exceeding 30K
 find memory -name "*.md" -size +30k 2>/dev/null | xargs wc -l | sort -rn | head -10
 
-# SKILL.md files > 300 lines with no SKILL_detail.md (skill-splitter candidates)
+# SKILL.md files > 300 lines with no SKILL_detail.md (salience-splitter candidates)
 find plugins -name "SKILL.md" 2>/dev/null | while read f; do
   lines=$(wc -l < "$f")
   detail=$(dirname "$f")/SKILL_detail.md
-  [ "$lines" -gt 300 ] && [ ! -f "$detail" ] && echo "[skill-splitter candidate] $f ($lines lines)"
+  [ "$lines" -gt 300 ] && [ ! -f "$detail" ] && echo "[salience-splitter candidate] $f ($lines lines)"
 done
 ```