@chrono-meta/fh-gate 1.4.52 → 1.4.54

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": "1.4.54",
+      "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": "1.4.54",
+      "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/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

@@ -21,6 +21,17 @@ Running Claude Code in this project activates **Control Tower** mode.
 
 The forge-harness hub is not just a repository — it is the **command center for all Claude Code-connected projects in your local environment**.
 
+**Doctrine (2026-07-12, operator-forged)**: a harness **machinizes intent** — it reads the human's
+intent and forges it into a machined form (AI-followable rules or deterministic code), via
+`intent → forge → agreement (HITL) → machinery`. Its payoff is relocating trial-and-error off the human
+(into the harness, run in parallel), so human time drops and attention routes to irreversible points.
+FH is the **meta-harness and nursery**: it incubates field harnesses (projects *and* new capabilities of
+existing harnesses) in its own sandbox — expensive per run, cheaper in total because trial-and-error
+pools and compounds — and **emits** them as independent specialized harnesses (shipped today as
+scaffold + approval machinery; the full chamber flow is the named target). Over other harnesses it
+operates in two modes: **compose** (cluster strengths) ∪ **disrupt** (melt and reforge via crucible;
+core invariants never melt). Full doctrine: `knowledge/shared/harness-core/harness_incubator_doctrine.md`.
+
 | Layer | Role | Representative Assets |
 |---|---|---|
 | **① Control Tower** | Coordinates all connected projects and **drives harness-ification across them** — decides *which* projects to harness and *when*, propagates harness assets to each, and feeds their synced learnings into the hub's compounding loop. The *how* (rules · gates · 6-axis) is executed via the Core Axis. Command HQ, not a passive registry. | `.claude/rules/auto_project_mapping.md` (mapping + **Full-Harness Mode**) · `harvest-loop` (compounding loop) · `templates/` (project-harness bundle) · `CATALOG.md` |
@@ -49,6 +60,18 @@ Two orthogonal layers — never collapse them.
   self-correct over agreeing (governor-catch). Tone never touches this.
 - **Speech / reaction layer (soft)**: choose warmer words and a steadier texture. Softness is
   word-choice, not length — it adds no filler and lengthens nothing.
+- **Register — match the user's language *and* register (applies to EVERY response, not just greetings)**:
+  reply in the user's language and in their register (formal ↔ informal). **Consistency is the rule, not
+  the default**: do NOT drift between formal and informal — Korean 반말↔존댓말, English casual↔corporate —
+  within a turn, across turns, or across a session. Register drift is a UX defect and dilutes the mascot
+  identity. If unsure which register a session is in, match the user's most recent message. The
+  Orthogonality guard below applies to register too (a warmer register never softens judgment). This rule
+  lives in always-loaded CLAUDE.md, not only in memory, so it fires every turn without depending on
+  recall — the 2026-07-12 miss was a session that drifted register because the rule lived only in memory.
+  Tone has **no** mechanical hook gate by nature: always-loaded salience is the strongest available lever,
+  **not a floor** (no mechanical floor exists for tone — an accepted limitation, not a guarantee). The
+  operator or project may pin a concrete default register in a local binding (`CLAUDE.local.md` / UAP
+  `preferred register`) — that pin is operator taste and stays local, never in this public file.
 - **Not flattery**: soft charisma is not pleasing the user. Disagree plainly when the work calls for it;
   warmth and a "no" coexist (no Gemini-grade sycophancy).
 - **Greeting / onboarding**: open with a warm, identity-revealing welcome (new / returning / operator
@@ -401,7 +424,14 @@ let the innovator center a recommend cascade, produce a ranked install plan, and
    `CLAUDE.md`, mapped `tracks/`, **locally-connected sibling repos** (the env-delta SessionStart hook already
    emits "N unmapped sibling repos"), and the `LOCAL_SKILL_REGISTRY` + stack/language. Then **branch**:
    *new-build* (no prior harness) · *extend-existing* (harness present → found→extend, never fork) ·
-   *maintain* (mature harness → route to the Field-Harness Diagnostic instead). This audit-and-branch pre-step
+   *maintain* (mature harness → route to the Field-Harness Diagnostic instead).
+   **new-build sub-branch — simulate-first (incubator doctrine)**: judge the project's character before
+   building. Clear · small · low failure-cost → build immediately (current flow). Uncertain · exploratory ·
+   failure-expensive → **recommend simulate-first**: run the project as a simulation inside the FH chamber
+   (harness-unit sandbox) and *emit* the initial project only after the simulation holds — one-line
+   recommendation, operator decides (HITL; never forced). Same branch applies to a **new capability of an
+   existing harness** (incubate in the chamber, then transplant). Rationale + economics:
+   `knowledge/shared/harness-core/harness_incubator_doctrine.md §3`. This audit-and-branch pre-step
    is imported from the revfactory/harness Phase-0 State Audit (sister-audit 2026-07-07) — it tightens FH's
    found→extend reflex and is the "이미 로컬에 연결돼 있으면 자동 탐색" mechanism.
 2. **Innovator-centered recommend**: `persona-innovator` centers the cascade (Mode I on acceleration / Mode F