@chrono-meta/fh-gate 1.4.51 → 1.4.53

package/.claude/registry/README.md

@@ -0,0 +1,26 @@
+# .claude/registry
+
+Machine-readable registries for the forge-harness automation layer.
+
+## agent_cards.json
+
+The **canonical machine-readable mirror** of the agent registry. `AGENTS.md` stays the
+human-facing source of truth (roles, rationale, prose); `agent_cards.json` is its structured
+counterpart for tooling — capability discovery, dispatch routing, and count-drift detection.
+
+Inspired by the **A2A "Agent Card"** pattern (the 2026 standard for agent capability discovery):
+each card declares an agent's `id`, `file`, `role`, `allowed_tools`, `invoked_by`, and a `writes`
+flag. `agent_count` is asserted at the top level and **should equal the number of tracked `.md`
+files in `.claude/agents/`, `plugins/fh-meta/agents/`, and `plugins/fh-commons/agents/`** —
+re-checked on every agent add/remove by `harness-doctor` Step 11-2-B, which compares
+`agent_count` against the live file count; a mismatch is a State-Degradation signal.
+
+### Regeneration
+
+Hand- or script-derived from `AGENTS.md` (Agent Registry + Tool-restrictions tables) plus each
+tracked agent `.md` frontmatter. Regenerate whenever an agent is added, removed, or its tools
+change — and re-check `agent_count`. On any disagreement between `AGENTS.md` and an agent's own
+`.md`, **prefer the agent `.md`** (e.g. `challenger.md` has no `tools:` field, so its tools come
+from `AGENTS.md`).
+
+> Frontier basis: `knowledge/shared/harness-core/harness_frontier_diagnosis_2026-06-02.md` (identity ① Control Tower — closes the "no canonical machine-readable registry / count drift" gap noted in `fh_ecosystem_positioning.md`).

package/.claude/registry/agent_cards.json

@@ -0,0 +1,73 @@
+{
+  "version": "1.0",
+  "generated": "2026-06-07",
+  "source": "derived from AGENTS.md (Agent Registry + Tool restrictions tables) and tracked agent files",
+  "convention": "A2A Agent Card pattern — machine-readable capability discovery, count-synced to plugin agents/ directories",
+  "agent_count": 8,
+  "agents": [
+    {
+      "id": "beginner",
+      "file": "plugins/fh-meta/agents/beginner.md",
+      "role": "First-contact cold-read standpoint (user-mastery spectrum entry tier) — surfaces onboarding friction a fluent author cannot feel; constructive, not adversarial",
+      "allowed_tools": ["Read"],
+      "invoked_by": ["sim-conductor", "marketplace-gate", "install-wizard", "direct"],
+      "writes": false
+    },
+    {
+      "id": "main-player",
+      "file": "plugins/fh-meta/agents/main-player.md",
+      "role": "Engaged-user standpoint (user-mastery spectrum core tier) — intelligently scopes Light/Midcore/Heavy; Heavy carries the classic power-user edge/limit lens",
+      "allowed_tools": ["Read", "Grep", "Glob"],
+      "invoked_by": ["sim-conductor", "direct"],
+      "writes": false
+    },
+    {
+      "id": "expert",
+      "file": "plugins/fh-meta/agents/expert.md",
+      "role": "Domain-authority standpoint (user-mastery spectrum frontier tier) — web-grounded accuracy + SOTA currency, citation-enforced; checks against the external world, not internal assets",
+      "allowed_tools": ["Read", "WebSearch", "WebFetch"],
+      "invoked_by": ["sim-conductor", "paper-review", "direct"],
+      "writes": false
+    },
+    {
+      "id": "challenger",
+      "file": "plugins/fh-meta/agents/challenger.md",
+      "role": "Frontier-grade adversarial evaluator — adapts attack vectors to artifact type, enforces evidence citation, models its own information asymmetry; U1 absorbs the skeptic 'why not just X?' lens",
+      "allowed_tools": ["Read", "Grep", "Glob", "WebSearch", "WebFetch"],
+      "invoked_by": ["steel-quench", "harvest-loop", "sim-conductor", "direct"],
+      "writes": false
+    },
+    {
+      "id": "fact-checker",
+      "file": "plugins/fh-meta/agents/fact-checker.md",
+      "role": "Pre-recommendation deduplication — greps hub assets for existing skills/agents/patterns before a new recommendation; catches stale facts and duplicate work",
+      "allowed_tools": ["Read", "Grep", "Glob"],
+      "invoked_by": ["main-agent-before-new-asset"],
+      "writes": false
+    },
+    {
+      "id": "hub-persona-auditor",
+      "file": "plugins/fh-meta/agents/hub-persona-auditor.md",
+      "role": "Pre-publication audit of external-facing assets — 3+ persona simulation, 4-axis review (resonance/confusion/resistance/supplement), 3-tier revision proposals",
+      "allowed_tools": ["Read", "Grep", "Glob"],
+      "invoked_by": ["hub-cc-pr-reviewer", "sim-conductor", "direct"],
+      "writes": false
+    },
+    {
+      "id": "persona-innovator",
+      "file": "plugins/fh-meta/agents/persona-innovator.md",
+      "role": "Naming gap detection + frame proposals + external frontier absorption signals",
+      "allowed_tools": ["Read", "Grep", "Glob", "WebSearch", "WebFetch"],
+      "invoked_by": ["sim-conductor", "harvest-loop", "direct"],
+      "writes": false
+    },
+    {
+      "id": "quench-challenger",
+      "file": "plugins/fh-commons/agents/quench-challenger.md",
+      "role": "Steel-quench dedicated adversary — 3-DNA synthesis of Devil + Innovator + Prescriber; every attack paired with a concrete fix direction",
+      "allowed_tools": ["Read", "Grep", "Glob"],
+      "invoked_by": ["steel-quench", "install-doctor", "marketplace-gate"],
+      "writes": false
+    }
+  ]
+}

package/.claude-plugin/marketplace.json

@@ -0,0 +1,25 @@
+{
+  "name": "forge-harness",
+  "owner": {
+    "name": "chrono-meta",
+    "email": "chrono-meta@users.noreply.github.com"
+  },
+  "metadata": {
+    "description": "forge-harness — Multi-instance persona orchestration and meta-tooling marketplace for Claude Code. Harness engineering toolkit for teams that want to evolve their AI collaboration practices.",
+    "pluginRoot": "./plugins"
+  },
+  "plugins": [
+    {
+      "name": "fh-meta",
+      "version": "1.4.53",
+      "description": "Hub meta-operations toolkit — 33 skills + 7 agents. New in 1.4.53: `fh-codex-doctor` (npm bin) — Codex adapter drift scanner; reads the documented M1/M2/M3 skill tier map + skill/agent source and reports codex-native/adapter-required/claude-native/unclassified per unit, wired into `npm test`/`prepublishOnly` (fail-closed on unclassified Claude-native primitives). New in 1.4.49: steel-quench gains Step 0.6 Verdict-Invariance Probe (groundedness axis — a load-bearing judged gate's verdict must track behavior, not rubric phrasing; measured flip-count over cross-family paraphrases; arXiv:2605.06161 Policy Invariance anchor); multi_model_sidecar_strategy §Vendor-native harness (a model is strongest in its own vendor CLI — Claude/CC, GPT/codex, Gemini/Antigravity; a universal router degrades all of them, so it stays an autocomplete/QA sidecar, never orchestration); predelete_check.sh fail-closed rewrite; memory-hygiene A-TMA anchor. New in 1.4.48: phantom-quench + steel-quench gain external frontier anchors (arXiv:2607.02052 package-hallucination; arXiv:2607.02057 prompt-coverage-adequacy); README model-flat claim reframed from a per-release point-curve to structural invariants (operation flattens across tiers; depth tier-order fixed within a generation). New in 1.4.47: onboarding step ① surfaces the Mode D companion-store session-start load in the auto-read salience anchor (previously only in the local binding + rules, so a greeting could skip the load). New in 1.4.46: context-doctor command-output axis (route to rtk/proxy for verbose CLI stdout, complementing .claudeignore; risk-gated to token-scarce envs). New in 1.4.41: context-doctor 2026 trigger vocab (context engineering/rot/collapse) + phantom-citation hardening; hub measurement-integrity-checklist (cross-model measurement pre-flight: display-name pin/reps≥3/discriminating probe). New in 1.4.40: install-wizard queryable-wiki scaffold (INDEX + session-start read + R/W/C ingest). New in 1.4.39: auto-decorrelation (cross-family verifier sidecar recruitment) + video-ingest (capability-routed video ingestion). New in 1.4.x: verify-axis check-class taxonomy (mandatory-pass/measured/judged), no-reinvention Tier-0 inventory, 7-class failure taxonomy, Destructive-Op Gate, Wave-T (Temper), tier-floor governance, Mode D Model Notice, FC consent lane, default-Sonnet guidance. New in 1.3.0: public-surface-audit, field-harvest Mode B auto-trigger, 4-axis gate scope ext. Validated cross-CLI: Claude Code, Codex, Gemini.",
+      "source": "./plugins/fh-meta"
+    },
+    {
+      "name": "fh-commons",
+      "version": "1.4.53",
+      "description": "Project-agnostic utility skills — 4 skills (convergence-loop · deliberation · mcp-circuit-breaker · token-budget-gate) + 1 agent (quench-challenger). Domain-independent utilities transplantable into any project.",
+      "source": "./plugins/fh-commons"
+    }
+  ]
+}

package/AGENTS.md

@@ -138,8 +138,8 @@ echo "Apply the following skill to the artifact below." | \
 
 | Tier | Definition | Examples |
 |---|---|---|
-| **M1 — Full** | All phases run without CC-native dependencies — no Stop hook, no `.claude/agents/` dispatch, no `/model` | `token-budget-gate`, `asset-placement-gate`, `phantom-quench`, `deep-clarify`, `deliberation`, `convergence-loop` |
-| **M2 — Partial** | Core workflow runs; CC-native phases require manual adaptation or skip | `steel-quench` (Wave 1–3 ✅; quench-challenger agent = manual), `harness-doctor`, `context-doctor`, `sim-conductor`, `harvest-loop` (git scan phase ✅; PR auto-proposal = manual) |
+| **M1 — Full** | All phases run without CC-native dependencies — no Stop hook, no `.claude/agents/` dispatch, no `/model` | `token-budget-gate`, `asset-placement-gate`, `phantom-quench`, `deep-clarify`, `convergence-loop` |
+| **M2 — Partial** | Core workflow runs; CC-native phases require manual adaptation or skip | `deliberation` (Mediator/Jury Agent steps = manual), `steel-quench` (Wave 1–3 ✅; quench-challenger agent = manual), `harness-doctor`, `context-doctor`, `sim-conductor`, `harvest-loop` (git scan phase ✅; PR auto-proposal = manual) |
 | **M3 — CC-only** | Requires CC Stop hook or session-scoped agent dispatch; methodology reference only | `goal-quench` (Phase 3 Stop hook), `hub-cc-pr-reviewer` (CC session context), `install-wizard` (settings.json write) |
 
 **M2 adaptation pattern**: when a step references `Agent(subagent_type=...)` or a slash command, substitute with `fh-run` (preferred) or a direct `codex exec` call reading the sub-agent's SKILL.md — same workflow, different runtime.

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) -->
 
+### 2026-07-10 | forge-harness | #sonnet-floor, #doctrine, #loop-engineering, #tier-census, #cross-family, #pre-commit-gate, #dispatch-first
+**File:** knowledge/shared/harness-core/sonnet_floor_doctrine.md · knowledge/shared/harness-core/loop_engineering.md
+Encoded the operator-declared **Sonnet-Floor Doctrine** (base ops 100% Sonnet-runnable; tier-gated capability = defect; escalation = dispatch, never substrate; depth ladder = effort→dispatch→anchored-Sonnet) as a canonical axiom node, plus **loop_engineering.md** (5-question design-time discipline + FH loop inventory MECH/PROSE census + evidence-threshold hardening backlog). Cross-family evolution pass: codex gpt-5.5 xhigh repo census (T1 tier refs / T2 loop legs / T3 contradictions) + agy Gemini 3.1 Pro breadth (pattern-level only, zero citations imported — phantom-risk URLs). All 6 identified availability-gates fixed: pre-commit Axis-2 gains a **sonnet-floor lane** (anchor-required, R-tier auto-queue, 8/8 regression fixtures in scripts/test_marker_floor_lanes.sh), self_evolution weekly dead-end recast dispatch-first, Mode D notice re-directed (keep Sonnet + dispatch primary), canary opus-judge → Sonnet-governor+anchor, verify-bidirectional "never stay at sonnet" fixed, 9 SKILL.md `model: opus` hard pins retired (session-inherit). Trust-floors tightened to run-first/ask-last (full Sonnet autonomy; gates stay). Sonnet blind sims: 2 dispatched, 1 salience miss caught (loop-stub enumeration) → hardened → re-sim PASS.
+- Decision: Sonnet = the optimization target, measured spine = H1 (harness benefit largest on weaker tiers); Opus/Fable-only capability is now a named defect class with a census discipline.
+- Open: quarterly/substrate loop rows are governor self-assessment (R-tier external census pending); sonnet-floor markers queue via below_floor_scan.sh R-tier lane.
+
 ### 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.

package/CHEATSHEET.md

@@ -197,6 +197,7 @@ FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-gate   # Codex backend (d
 # Run a skill or agent doc through a backend, outside Claude Code
 npx --package @chrono-meta/fh-gate fh-run --skill <name>
 npx --package @chrono-meta/fh-gate fh-goal "<goal text>"      # goal runner
+npx --package @chrono-meta/fh-gate fh-codex-doctor --strict  # Codex adapter drift check
 ```
 
 | Knob | Values | Effect |

package/CLAUDE.md

@@ -38,6 +38,7 @@ Four foundational assets for hub operations. **Mandatory pre-reference** before
 | `knowledge/shared/harness-core/hub_compounding_loop.md` | Feedback automation | Weekly/monthly/quarterly cycles. Axis-6 Compounding automation |
 | `knowledge/shared/dialogue/ai_dialogue_playbook.md` | Dialogue principles (should) | Session start, token efficiency, rule hierarchy, amplifier/coach dual mode |
 | `knowledge/shared/dialogue/claude_code_runtime_flow.md` | Runtime behavior (does) | Chronological flow during a session · sub-agent delegation flowchart |
+| `knowledge/shared/harness-core/sonnet_floor_doctrine.md` | Canonical invariant | **Sonnet-Floor**: base ops 100% Sonnet-runnable · tier-gated capability = defect · escalation = dispatch (consent-gated), never substrate. Loop companion: `loop_engineering.md` |
 
 ## Voice / Tone — Soft Charisma (delivery layer only)
 
@@ -209,11 +210,14 @@ a session *following prose instructions* (salience-dependent — rules, onboardi
 trigger behavior), or is it mechanically enforced (hooks, scripts — tier-independent, normal 4-axis
 path, exempt)? For salience-dependent changes, verify with a **blind simulation in an isolated Agent**
 (no main-session reasoning inherited — isolation is the FH mechanism that keeps the sim honest) with
-`model:` pinned to the tier the change must survive on. Application strength scales with context:
+`model:` pinned to the tier the change must survive on — **default sim tier = Sonnet** (the base
+floor every FH behavior must survive on, `sonnet_floor_doctrine.md`). Application strength scales
+with context:
 - **Mode D (FH self-dev) — near-mandatory**: any salience-dependent FH asset change runs the sim
-  before Done. Mandatory without exception when the change fixes a behavioral miss *observed* on a
-  specific tier — sim at that same tier (the verification tier must match the failure tier; fixing on
-  a stronger model and verifying by review alone leaves "does it fire on the weaker tier?" unanswered).
+  before Done, at Sonnet by default. Mandatory without exception when the change fixes a behavioral
+  miss *observed* on a specific tier — sim at that same tier, even below Sonnet (the verification
+  tier must match the failure tier; fixing on a stronger model and verifying by review alone leaves
+  "does it fire on the weaker tier?" unanswered).
 - **Field harness assets (templates/ propagated via Full-Harness Mode) — conditional**: sim at the
   default field tier (Sonnet) when the behavior is load-bearing (gates, onboarding, destructive/publish
   paths); skip with a one-line note for low-stakes prose.
@@ -221,8 +225,9 @@ path, exempt)? For salience-dependent changes, verify with a **blind simulation
   (hook logic, scripts, file moves — tier-independent by construction).
 
 **Autonomy floor**: the skip/run *judgment* on conditional cases is itself depth-sensitive — trust it
-only at opus-tier or above. A below-floor orchestrator does not silently skip: it runs the sim or asks
-the operator (one line), mirroring §Floor governance.
+only at opus-tier or above. A below-floor orchestrator does not silently skip — and does not stall:
+its default is to RUN the sim (the conservative branch needs no trust); it asks the operator only when
+no runnable path exists (run-first, ask-last — sonnet_floor_doctrine.md §Autonomy at Sonnet).
 
 Record sim results in the Axes 2–3 marker + sub-agent invocation log.
 
@@ -241,8 +246,9 @@ measurement is trusted.
 **Floor-tier canary (optional pre-screen — token-free, *below* the Sonnet sim)**: a local model ≤ Sonnet
 can blind-pre-screen a salience-dependent edit *before* the Sonnet dispatch is spent. **Canary, NOT gate**:
 a PASS adds cheap floor confidence and you still run the Sonnet sim; a FAIL never blocks alone. The terminal
-verdict stays with the frontier (Sonnet sim + opus judge) — **no judge-only path**, no weak-local-judge
-regression of the judge-robustness principle (mechanical anchor over judge-only verdict).
+verdict stays with the **Sonnet-or-higher governor bound to a mechanical anchor** (an opus judge is the
+dispatch-recommended strengthener, not a requirement — `sonnet_floor_doctrine.md`) — **no judge-only path**,
+no weak-local-judge regression of the judge-robustness principle (mechanical anchor over judge-only verdict).
 
 > **Detail**: See `knowledge/shared/harness-core/claude_md_gate_details.md §Floor-Tier-Canary` — the local
 > model/panel options, the blind-probe procedure, dogfood evidence, and the FAIL-triage (real salience gap
@@ -272,7 +278,8 @@ the target-tier sim all shared — the decorrelation value made concrete.
 
 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;
+no notice · below-opus → **dispatch-first recommend** (keep Sonnet + route depth turns to sidecar/opus
+dispatch; `/model opus` pin = secondary — `sonnet_floor_doctrine.md`) · 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`.
 
@@ -338,7 +345,8 @@ same as the FH cross-family complement. **In autonomous loops** (innovator loop-
 `/goal` · cluster orchestration): this gate is **part of the delegated pipeline**, not an
 afterthought — a load-bearing field change produced autonomously runs the lint → cross-family →
 converge loop *before* it is Done. Autonomy floor (§Floor governance): the skip/run judgment is
-trusted only at opus-tier+; below-floor runs the review or asks, never silently skips.
+trusted only at opus-tier+; below-floor RUNS the review by default (run-first, ask-last — asks only
+when no runnable path exists), never silently skips (sonnet_floor_doctrine.md §Autonomy at Sonnet).
 
 > **Detail** (discretion principle · 4-face signature · gate mechanics · n=7 qasp evidence):
 > `knowledge/shared/harness-core/field_verdict_crossfamily_gate.md`.
@@ -361,6 +369,7 @@ dozen skills to invoke. Every fix is HITL — the diagnostic **proposes**, never
 | **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) |
+| **Loop-readiness** (황민호 loop-eng 5-question lens, 2026-07-10 — detail home: `loop_engineering.md`, incl. the FH loop inventory + design-time discipline) | *Loop-runtime axis — net-new vs Structure* (harness-doctor scans static form; this scans whether the path closes a loop). **Mechanical grep**: `/goal-quench`·`/loop` wiring present · check-class token declared. **Judged**: is the persisted state (card/handoff/memory) actually reloaded · is the declared check-class anchored, not judged-only · does the path halt. Done-When *presence* → see Structure row (no double-grep). **Adversarial pair** (for the judged sub-checks — decorrelated, behavior-vs-checklist): a target-tier blind sim that *runs* the path and observes whether it halts + persists, rather than re-checklisting it (the harness litmus shares this lens's axis, so it is a co-lens, not the adversary). | an agent path that *runs but doesn't loop*: no completion criterion (Done-When absent), judged-only validation with no anchor, no halt/budget guard (runaway/cost), or no state carried to the next run — the 5 questions (initiate · complete · validate · halt · persist) with 0 answers |
 
 **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
@@ -771,7 +780,8 @@ Closing phrase detected ("wrap up", "done", "good work", "end session", etc.)
 > when executing that close step.
 
 **Card-last guard**: ①–④-c (incl. ①-b open-PR sweep, ④-c handoff lifecycle) must ALL complete before
-⑤ runs. Any new information produced during ①–④ (new commits from a merged self-PR, model changes,
+⑤ runs. **Mechanical floor**: `bash scripts/session_close_check.sh` before ⑥ —
+exit 1 (card-last violated / required close artifact missing) blocks the push step until fixed. Any new information produced during ①–④ (new commits from a merged self-PR, model changes,
 new findings, a carry item flipped to DONE) feeds INTO ⑤ — card is never written mid-sequence and
 then left open for more work to accumulate after it.
 

package/README.md

@@ -95,7 +95,7 @@ forge-harness is structured as **two distinct layers**:
 | Layer | Contents | AI compatibility |
 |---|---|---|
 | **Methodology layer** | `tracks/`, `knowledge/`, `SKILL.md` docs, session protocols | Any AI model |
-| **Automation layer** | `.claude/agents/`, hooks, slash commands, `CLAUDE.md` rules | Claude Code only |
+| **Automation layer** | `plugins/*/agents/` (FH agents), `.claude/agents/` (field-project overrides), hooks, slash commands, `CLAUDE.md` rules | Claude Code only |
 
 The methodology layer is the portable core — persistent hub, accumulating learnings, curating cross-project knowledge. The automation layer makes it frictionless when running Claude Code.
 
@@ -149,6 +149,17 @@ FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-run --skill phantom-quenc
 FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-run --agent fh-commons:quench-challenger --file plugins/fh-meta/skills/foo/SKILL.md
 ```
 
+To check whether a changed FH skill/agent surface still has a clean Codex adapter path, run:
+
+```bash
+npx --package @chrono-meta/fh-gate fh-codex-doctor --strict
+```
+
+`fh-codex-doctor` scans the canonical skill/agent registry and reports which units are Codex-native,
+adapter-required, Claude-native, or unclassified. It is a drift detector for the thin adapter boundary;
+it does not try to clone the Claude Code automation layer. When run from an FH checkout it scans the
+current working tree; outside a checkout it scans the installed package.
+
 For Codex-primary work, keep using Codex's native goal/session features when available. `fh-goal` is only a portable wrapper for one-off non-interactive runs that should be followed by FH governance:
 
 ```bash