@chrono-meta/fh-gate 1.1.0 → 1.2.0

package/.claude/agents/challenger.md

@@ -0,0 +1,169 @@
+---
+name: challenger
+description: Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured [issue · location · severity] output consumable by steel-quench, harvest-loop, and sim-conductor. Use when you need adversarial pressure that a self-reviewing author cannot generate.
+---
+
+# challenger — Frontier Adversarial Evaluator
+
+> The original devil-advocate asks "what's wrong?" The challenger asks "what's wrong, where exactly, why does evidence support that claim, and what can I NOT see that might invalidate my attack?" Adversarial pressure with epistemic discipline.
+
+## Core Principle — Sandboxed Adversary Awareness
+
+The challenger operates from an explicitly constrained information position:
+
+```
+What challenger CAN see:
+  - Static artifact content (files, text, diagrams, claims)
+  - Internal consistency (do parts contradict each other?)
+  - Structural patterns (missing sections, undefined terms, circular references)
+
+What challenger CANNOT see:
+  - Runtime behavior (does this actually execute as described?)
+  - External adoption evidence (are others using this successfully?)
+  - Author intent beyond what's written
+  - Future ecosystem state
+```
+
+**Implication**: Attacks based on "I can't verify this" are valid attack signals — not dismissible. If the challenger cannot verify a claim, and the author cannot demonstrate it either, the claim is a phantom candidate.
+
+**Convergence signal**: If a new attack round produces only attacks the challenger itself flags as "low confidence due to information gap," convergence is approaching. Potency is declining — declare convergence direction.
+
+---
+
+## Artifact-Adaptive Attack Matrix
+
+Before attacking, challenger identifies the artifact type and loads the corresponding attack angles. Universal angles always apply.
+
+### Universal Angles (all artifact types)
+
+| # | Angle | Core question |
+|:---:|---|---|
+| U1 | **Existence justification** | Why does this exist? Is there a simpler alternative? |
+| U2 | **Self-referential closure** | Does this evaluate itself by its own criteria? |
+| U3 | **Evidence grounding** | Every quantitative claim: is there a measurement artifact? |
+| U4 | **Bus factor** | If the author is unavailable, does this still function? |
+| U5 | **Phantom detection** | Does any referenced capability, file, or behavior actually exist? |
+
+### Type-Specific Angles
+
+**SKILL.md / Agent definition**:
+- S1: Done-When defined and binary-evaluable?
+- S2: Trigger phrases reachable without internal vocabulary?
+- S3: Allowed-tools matches only actually-called tools?
+- S4: Dependencies explicitly documented or eliminated?
+- S5: Step sequence executable cold-start without author context?
+
+**Paper / Research document**:
+- P1: Every "X achieves Y" claim has a measurement artifact (not LLM reconstruction)?
+- P2: Related work covers systems that contradict the paper's claims?
+- P3: Self-application scenario (does the method validate itself)?
+- P4: Scope boundary clearly defined — what is NOT addressed?
+- P5: Citation chain: does citing a paper imply its claims are verified?
+
+**Design / Architecture document**:
+- D1: Implementation feasibility under stated constraints?
+- D2: Platform lock-in — what breaks if a dependency is removed?
+- D3: Simplification test — does this get simpler over time, or more complex?
+- D4: Failure mode coverage — what happens when each component fails?
+
+**Code / Prompt**:
+- C1: Edge cases and boundary conditions covered?
+- C2: Implicit assumptions that could fail silently?
+- C3: Security surface — injection, override, or bypass paths?
+- C4: Test coverage — is behavior verified, or assumed?
+
+---
+
+## Execution Protocol
+
+### Phase 1 — Context Mapping (before any attacks)
+
+State explicitly:
+```
+Artifact type: [SKILL / Paper / Design / Code]
+Information I have: [list what was provided]
+Information I lack: [list what I cannot see — runtime state, external evidence, etc.]
+Attack angles activated: Universal (U1-U5) + [type-specific list]
+```
+
+### Phase 2 — Attack Round
+
+For each attack:
+```
+Attack: [angle code + description]
+Location: [file:line / section / paragraph / claim — REQUIRED. Abstract attacks rejected.]
+Severity: S (blocks deployment) / A (required before sharing) / B (improvement recommended)
+Evidence: [what in the artifact supports this attack]
+Confidence: HIGH (artifact clearly shows this) / MED (inferred) / LOW (information gap)
+```
+
+LOW confidence attacks are still valid — they surface blind spots.
+
+### Phase 3 — Convergence Assessment
+
+After completing all attack angles:
+```
+New S-grade attacks this round: N
+Attack potency trend: [Increasing / Stable / Declining]
+Convergence signal: [Not yet / Approaching (LOW-confidence dominant) / Achieved (zero new S)]
+Residual risk: [List A/B items that remain unresolved]
+```
+
+---
+
+## Output Format
+
+```
+## challenger evaluation — [artifact name] ([date])
+
+### Context Map
+- Artifact type: ...
+- Angles active: U1-U5 + [type-specific]
+- Information gaps: [list]
+
+### Attacks
+
+| # | Angle | Location | Severity | Evidence | Confidence |
+|:---:|---|---|:---:|---|:---:|
+| 1 | U3: Evidence grounding | §4.6, "reduced token cost" | A | No measurement artifact; design property only | HIGH |
+| 2 | S2: Trigger reachability | SKILL.md trigger list | S | "run quench" not reachable via natural phrasing | MED |
+...
+
+### Convergence Assessment
+New S-grade: N | Trend: [Increasing/Stable/Declining]
+Signal: [Not yet / Approaching / Achieved]
+Residual risks: [list]
+```
+
+---
+
+## Invocation Modes
+
+| Mode | Command | When to use |
+|---|---|---|
+| **Sub-agent** (default) | Agent tool with `subagent_type="challenger"` | Standard — same session, prompt isolation |
+| **Cross-session CLI** | `claude --print "{prompt}"` | When same-session confirmation bias is a concern; spawns fresh process with zero history |
+| **External sidecar** | `gemini`, `gh copilot`, `ollama` pipe | Wave 5 — when different model blind-spot profile is needed |
+
+Cross-session mode eliminates accumulated session context — use when the main session has handled the artifact extensively and you want a truly cold-read adversary. Output is identical format to sub-agent mode.
+
+## Integration Hooks
+
+**steel-quench Wave 1** *(planned)*: challenger is designed to replace or supplement the devil agent. When wired, S-grade output feeds into Wave 2 defense round. Currently steel-quench calls `fh-commons:quench-challenger` for Wave 1 — explicit challenger wiring is a future integration step.
+
+**harvest-loop Step 3a**: challenger runs against existing skills using session findings. S-grade attacks on existing skills → HIGH synthesizer grade. LOW-confidence attacks on new proposals → MED grade (defer pending verification).
+
+**sim-conductor Area A/B**: challenger takes the role of the adversarial persona. Focuses on U5 (phantom detection) and S2 (trigger reachability) for Area A; D3 (simplification test) and U2 (self-referential closure) for Area B.
+
+---
+
+## Done When
+
+```
+All applicable angles attempted (Universal + type-specific)
++ Every attack has a Location citation (no abstract attacks)
++ Convergence assessment output
++ Residual risk list
+```
+
+Challenger does NOT defend — defense is the caller's responsibility (steel-quench Wave 2, human review gate).

package/AGENTS.md

@@ -0,0 +1,160 @@
+# AGENTS.md — forge-harness Sub-Agent Specs
+
+> **This file is the runtime agent specification registry for forge-harness.**
+> For session rules and orchestration protocol, see `CLAUDE.md`.
+> For skill descriptions and natural language triggers, see `plugins/fh-meta/` and `plugins/fh-commons/`.
+
+---
+
+## Relationship to CLAUDE.md
+
+| File | Scope | Audience |
+|---|---|---|
+| `CLAUDE.md` | Session rules, protocols, orchestration flow | AI (Claude Code) — operational ruleset |
+| `AGENTS.md` | Runtime agent specs — roles, tools, invocation | AI + humans — agent registry |
+
+CLAUDE.md governs *how* the session runs. AGENTS.md defines *what each agent does* when dispatched.
+
+---
+
+## Agent Registry
+
+forge-harness ships 5 tracked agents across `.claude/agents/` and plugin `agents/` directories. Four serve general harness operations; one (`quench-challenger`) is steel-quench-dedicated.
+
+| Agent | File | Role | Invoked by |
+|---|---|---|---|
+| `challenger` | `.claude/agents/challenger.md` | Frontier-grade adversarial evaluator — adapts attack vectors to artifact type, enforces evidence citation, models its own information asymmetry | `steel-quench`, `harvest-loop`, `sim-conductor`, or direct dispatch |
+| `fact-checker` | `plugins/fh-meta/agents/fact-checker.md` | Pre-recommendation deduplication — greps hub assets for existing skills/agents/patterns before main agent commits to a new recommendation; catches stale facts and duplicate work | Main agent before any new asset creation or recommendation |
+| `hub-persona-auditor` | `plugins/fh-meta/agents/hub-persona-auditor.md` | Pre-publication audit of external-facing assets — 3+ persona simulation, 4-axis review (resonance/confusion/resistance/supplement), 3-tier revision proposals | `hub-cc-pr-reviewer`, `sim-conductor`, or direct dispatch |
+| `quench-challenger` | `plugins/fh-commons/agents/quench-challenger.md` | Steel-quench dedicated adversary — 3-DNA synthesis of Devil + Innovator + Prescriber; every attack paired with a concrete fix direction | `steel-quench` Wave 1 (primary), `install-doctor`, `marketplace-gate` |
+| `persona-innovator` | `plugins/fh-meta/agents/persona-innovator.md` | Naming gap detection + frame proposals + external frontier absorption signals | `sim-conductor` Area A, `harvest-loop`, or direct dispatch |
+
+> Machine-readable mirror: `.claude/registry/agent_cards.json` (canonical capability cards, count-synced to tracked agent files — A2A Agent Card pattern).
+
+### Tool restrictions per agent
+
+| Agent | Allowed tools | Rationale |
+|---|---|---|
+| `challenger` | Read, Grep, Glob, WebSearch, WebFetch | Needs external evidence; no writes |
+| `fact-checker` | Read, Grep, Glob | Deduplication grep only — no modification |
+| `hub-persona-auditor` | Read, Grep, Glob | Audit only — no modification |
+| `quench-challenger` | Read, Grep, Glob | Attack+prescription only — no modification |
+| `persona-innovator` | Read, Grep, Glob, WebSearch, WebFetch | Frontier scanning requires web access |
+
+---
+
+## 2-Layer Architecture Context
+
+forge-harness is structured as two distinct layers:
+
+| Layer | Contents | AI compatibility |
+|---|---|---|
+| **Methodology layer** (model-agnostic) | `tracks/`, `knowledge/`, `SKILL.md` documents, session protocols | Any AI model |
+| **Automation layer** (Claude-native) | `.claude/agents/`, hooks, slash commands, `CLAUDE.md` rules | Claude Code only |
+
+Agents in this registry belong to the **Automation layer**. Skills (in `plugins/`) straddle both layers — their methodology is model-agnostic, but their invocation mechanism is Claude Code-native.
+
+> **Codex-compatible beta**: The Methodology layer (`tracks/`, `knowledge/`, skill documentation) is designated Codex-compatible beta. Gemini, Codex, and other AI users can apply FH methodology without the Automation layer — manual invocation replaces hook/agent dispatch.
+
+> **Multi-model sidecar (validated)**: Any FH user can delegate to other models via sidecar — Gemini CLI, OpenAI/Codex CLI, or Copilot CLI's model catalog — invoked with `Bash` from within the Claude Code session. FH is the orchestrating harness; the sidecar is a routing/access layer (not a second harness — different layer entirely). Validated empirically: `echo "prompt" | gemini` works inside a CC session and produces usable output. Sidecar calls are Bash invocations, not agent dispatches — they bypass this registry and are coordinated inline by the skill. See `knowledge/shared/harness-core/multi_model_sidecar_strategy.md` for the full pattern.
+
+---
+
+## Invocation patterns
+
+### Single agent dispatch
+
+```
+Analyze this SKILL.md for structural flaws before I commit it.
+```
+
+→ Claude dispatches `quench-challenger` automatically (description-triggered).
+
+### Parallel dispatch (2+ independent tasks)
+
+```
+Run fact-checker and persona-innovator in parallel.
+  First: check [asset path] for duplicates
+  Second: scan for naming gaps in the current harness
+```
+
+→ Both agents run concurrently in Agent View; results are integrated by the orchestrator.
+
+### Wave-based composition (via agent-composer)
+
+For complex multi-step tasks, run `/agent-composer` first to plan which agents to dispatch in which order (Wave 0 reconnaissance → Wave 1 execution → Wave 2 synthesis).
+
+---
+
+## Codex Compatibility (beta)
+
+The methodology layer (`tracks/`, `knowledge/`, `SKILL.md` docs) is Codex-compatible beta. Any AI model can follow skill workflows by reading SKILL.md files directly; the automation layer (hooks, `.claude/agents/`, `/model`) is Claude Code-native and requires manual adaptation.
+
+### Entry point for Codex users
+
+AGENTS.md is your starting point. Navigate from here to skill workflows:
+
+```bash
+# Read a skill's full workflow
+cat plugins/fh-meta/skills/steel-quench/SKILL.md
+
+# Apply via codex exec (validated pattern — codex-cli ≥ 0.135.0)
+cat plugins/fh-meta/skills/steel-quench/SKILL.md path/to/artifact.md \
+  | codex exec -m gpt-5.5 -
+
+# Or use FH's runtime adapter (preferred for Codex-primary workflows)
+FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-run \
+  --skill steel-quench \
+  --file path/to/artifact.md
+
+# Agent substitution for Claude Code Agent(...) calls
+FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-run \
+  --agent fh-commons:quench-challenger \
+  --file path/to/artifact.md
+
+# Or pipe explicitly
+echo "Apply the following skill to the artifact below." | \
+  cat - plugins/fh-meta/skills/{skill}/SKILL.md target.md \
+  | codex exec -m gpt-5.5 -
+```
+
+`codex exec -m gpt-5.5 -` reads from stdin in headless mode. `npx @openai/codex` (interactive) is not suitable — it requires TTY.
+
+### Skill compatibility tiers
+
+| 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`, `source-grounding-audit`, `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) |
+| **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.
+
+**Goal handling under Codex**: use Codex's native goal/session feature when available. FH's portable role is the quality gate after the goal completes: `FH_BACKEND=codex npx --package @chrono-meta/fh-gate fh-gate ...`. `fh-goal` exists only for non-interactive one-shot runs that should be followed automatically by `fh-gate`; it is not a replacement for Codex-native goal control.
+
+### Beta removal conditions
+
+| Condition | Status |
+|---|---|
+| Known limitation list published (`docs/codex-compat.md`) | ✅ done (2026-06-04) |
+| 5+ externally validated M1 skill runs (not FH author) | ⬜ pending — needs external users |
+| At least 1 external Codex user confirms methodology reproduces | ⬜ pending — needs external users |
+| README badge updated (`Codex-compatible` without `beta`) | ⬜ blocked on above |
+
+**Author M1 validation (2026-06-04, internal — does not satisfy the external conditions above):** `source-grounding-audit` (4/4 on a phantom-seeded fixture) and `asset-placement-gate` (correct Drop routing on a duplicate-skill proposal) ran end-to-end via `codex exec -m gpt-5.5 -` with no CC-native dependency, confirming the M1 tier assignments. Limitations observed (CC-native hook noise, no token accounting, etc.) are documented in `docs/codex-compat.md`.
+
+Tracking: open an issue at `chrono-meta/forge-harness` with label `codex-validation` to report a validated run.
+
+---
+
+## Adding new agents
+
+New agents must pass the **New Skill Creation Pre-Commit Gate** defined in `CLAUDE.md` before committing. Key requirements:
+
+1. Role duplication check via `/asset-placement-gate`
+2. Plain description — no self-marketing language
+3. At least 1 explicit `Done When` condition
+4. At least 3 natural language trigger examples
+5. Independently executable (or dependencies explicitly documented)
+
+After 2+ weeks of use: if `accepted ≥ 60%` of invocations → strengthen; if `rejected ≥ 40%` → redefine scope or deprecate. See `CLAUDE.md > Sub-agent Operations`.

package/CATALOG.md

@@ -0,0 +1,256 @@
+# Knowledge Catalog
+
+AI reads this file first when searching past work. Open individual files for detailed content.
+
+---
+
+## Sessions
+
+<!-- Add entries in reverse date order (newest at top) -->
+
+### 2026-06-04 | forge-harness | #skill, #public-private-split, #leak-prevention, #composability-gate
+**File:** plugins/fh-meta/skills/public-surface-audit/SKILL.md
+New meta-skill: scans git-tracked files for operator-private tokens (real username, absolute home paths, companion-store name, company asset names) that belong only in gitignored files. Closes the surface-sweep gap from the Gap-1 public/private split. Dogfoods its own rule — patterns live in a gitignored source, SKILL.md carries only placeholders.
+- Decision: tracked-only scan (git ls-files); configurable pattern table + tight allowlist; severity HIGH/MED/LOW.
+- Open: skill-count drift across plugin.json / local_fh_context (separate cleanup).
+
+### 2026-06-04 | forge-harness | #issue-69, #field-harvest, #mode-b, #detection-skip
+**File:** plugins/fh-meta/skills/field-harvest/SKILL.md
+Mode B extension (Proposal A): session-end auto-proposal for un-logged field-cwd commits (item1), detection-skip for already-logged commits (item2), templates/ hub-link footer (item6).
+- Decision: auto-trigger is proposal-only (no auto-run); harvest-loop keeps hub-cwd wrap-up ownership (collision guard).
+- Open: item2 bash detection-skip style pending sister-hub reply (inline-grep vs persisted-ledger).
+
+### 2026-06-04 | forge-harness | #4-axis-gate, #pre-commit-hook, #docs-scope
+**File:** templates/.git-hooks/pre-commit
+4-axis gate scope extension: docs/*.md + AGENTS.md added to the substantive carve-out (Axes 2-3 when diff adds fence/citation/version). Also implemented the previously-documented-but-missing knowledge/ carve-out in the hook. Gate hook activated (core.hooksPath → templates/.git-hooks; was physically inactive).
+- Decision: path-regex carve-out bucket + diff_is_substantive() helper.
+- Open: none.
+
+### 2026-06-03 | forge-harness | #goal-quench, #native-validation, #calibration, #stop-hook
+**File:** tracks/_meta/goal_quench_2026-06-03.md
+Run #1 native goal-quench validation (core mode): Stop hook `.active` → `.pending` confirmed working. pipeline-conductor --quick CLEAN (Step 3 ESCALATE resolved via option(a) inline fix).
+- Decision: GREEN estimate missed pipeline-conductor overhead (~6K); timestamp field used literal "now" — fixed to `date +"%Y-%m-%d %H:%M"` going forward.
+
+### 2026-06-03 | forge-harness | #context-bridge-dispatch, #done-when, #deprecated, #source-grounding
+**File:** plugins/fh-meta/skills/context-bridge-dispatch/SKILL.md
+Added Done When section (satisfies harness-doctor L2 M-tier for deprecated skill). Replaced informal "completeness gate" term with "L2 M-tier (CLAUDE.md §New Skill Creation Pre-Commit Gate)". All 22 fh-meta SKILL.md files now have Done When.
+- Decision: deprecated skills still require Done When — `deprecated: true` is not an exemption from the pre-commit gate.
+
+### 2026-06-03 | forge-harness | #goal-quench, #calibration, #run2, #catalog
+**File:** CATALOG.md
+Run #2 native goal-quench validation (core mode): added 3 CATALOG entries for today's session work. Established pipeline-conductor overhead correction (~6K) for GREEN-tier estimates.
+
+### 2026-06-03 | forge-harness | #goal-quench, #install-wizard, #calibration-schema, #done-when, #skill-evolution
+**File:** plugins/fh-meta/skills/goal-quench/SKILL.md, plugins/fh-meta/skills/install-wizard/SKILL.md
+PR #67: Calibration schema extended with `run_id`, `session_id`, `scope_hint` fields (R10 schema gaps). Phase 1.5 hand-off clarified: "update not re-create" `.active` file to preserve `start_commit`. install-wizard: Done When section added (6-step gate + `--dry-run` variant) — only active skill of 28 missing it (R07 M-tier).
+- Decision: schema fields added prospectively — backfilling retrospective N=10 rows with `mode`/`session_type` is a local companion-store task, not a SKILL.md change
+
+### 2026-06-03 | forge-harness | #catalog, #goal-quench, #skill-evolution
+**File:** CATALOG.md
+PR #66: Added CATALOG entries for PRs #61–64 (goal-quench evolution arc): mode-ladder refactor, micro R-tier cleanup, non-coercive guidance formalization, scope-driven sidecar routing + 4.7× overhead calibration.
+- Decision: tracks/** gitignored by design — calibration YAML records stay local; only CATALOG.md committed
+
+### 2026-06-03 | forge-harness | #goal-quench, #sidecar-routing, #step-d, #deprecated-refs, #return-path
+**File:** plugins/fh-meta/skills/goal-quench/SKILL.md, plugins/fh-meta/skills/install-wizard/SKILL.md, plugins/fh-meta/skills/frontier-digest/SKILL.md, plugins/fh-meta/skills/harvest-loop/SKILL.md
+PR #65: Fixed Step D return-path bug (all 3 sidecar chains were fire-and-forget → added Step 3-c blocking verdict gate). Added `estimation_error_pct` field to calibration schema. Removed 4 deprecated routing refs: `context-bridge-dispatch` (install-wizard Cluster C + frontier-digest core skills list) and `/self-marketing-lint` (harvest-loop P10 → `/harness-doctor --lint`). ESCALATE added to Done When conditions.
+- Decision: Step 3-c gate is blocking (not advisory) — sidecar verdict must resolve before Done When
+
+### 2026-06-03 | forge-harness | #goal-quench, #sidecar-routing, #token-calibration, #steel-quench, #skill-evolution
+**File:** plugins/fh-meta/skills/goal-quench/SKILL.md
+PR #64: Added scope-driven sidecar routing (Step D) to goal-quench Phase 1.5: task-type signals auto-route to steel-quench C3 (code review), agent-composer panel (architecture), or sim-conductor+steel-quench Wave 5 (external publish). Formalized session overhead calibration at 4.7× factor (N=10), adding `session_type`, `actual_vs_estimate_ratio`, and `sidecar` fields to the calibration schema. Resolved steel-quench meta-audit S+A+B findings: sub-goal loop rewritten as user-driven queue, pre-flight check added, Opus escalation cost disclosed.
+- Decision: overhead multiplier documented as empirical calibration constant; sidecar routing is scope-signal-driven, not mode-locked
+
+### 2026-06-03 | forge-harness | #goal-quench, #non-coercive, #companion-store, #ephemeral-handoff
+**File:** .claude/rules/modes_and_value.md
+Formalized two non-coercive guidances: companion-store recommendation conditioned on accumulating context into meta-harness without a local fork; ephemeral-environment handoff rule made mode-agnostic (Mode D → companion-store handoff/, all others → committed note or PR comment in working repo).
+- Decision: single-source preserved — rule lives in public mirror; companion store holds only outputs, never a rule copy
+
+### 2026-06-03 | forge-harness | #goal-quench, #skill-evolution, #meta-audit, #prompt-regression
+**File:** plugins/fh-meta/skills/goal-quench/SKILL.md
+Post-merge micro R-tier cleanup: corrected two prompt-regression probe expectations mis-FAILing correct skills (P-CHAIN-01/02). Made LOCAL_SKILL_REGISTRY trigger in cross-ecosystem-synergy-detection honestly optional. Closes full-harness refactor backlog.
+- Decision: leftover placeholder bash blocks and challenger wiring gap are verified non-defects
+
+### 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.
+- Decision: RED tier reframed as max-mode decomposition on-ramp, not hard block
+
+### 2026-06-02 | _audit | sister-asset, token-efficiency, compression, headroom
+**File:** tracks/_audit/session_2026_06_02_headroom_context_doctor.md
+Cross-audited Headroom (Netflix engineer's OSS token-compression tool, vendor-reported 60–95% reduction) against context-doctor's Compression Pass per sister_asset_protocol. Same goal, different layer: Headroom is the runtime executor FH lacks; context-doctor is the judgment Headroom lacks — they compose.
+- Decision: import redundancy-category targeting heuristic (MCP outputs ~70% → logs ~90% → DB → file trees) into context-doctor + name Headroom as the production-proven local option; no clone-and-own (reference + record only)
+- Open: actual proxy/agent-wrap routing is a local runtime setup (outside the FH repo); v0.22 maturity — pilot first
+
+### 2026-06-02 | frontier-digest, identity, propagation | harness-engineering, a2a, mcp, observability, context
+**File:** knowledge/shared/harness-core/harness_frontier_diagnosis_2026-06-02.md
+Frontier digest anchored on FH's 3-layer identity + Core Axis (WebSearch engine; curl blocked, no API key). 2026-06 signal: "Harness Engineering" named 4th AI-engineering paradigm (65% of AI failures = harness defects); A2A Agent Cards + MCP registry standardize agent discovery; AHE thesis — observability is the self-improvement bottleneck.
+- Decision: 6 strengthening candidates mapped per identity (agent-card registry + dispatch overhead budget → ①; harness-defect taxonomy + observability/eval hooks → ②; L1/L2/L3 context hierarchy + compression pass → ③)
+- Open: candidates are proposals only — none implemented yet. Raw signal + processing checklist held in a private companion store, not this public repo.
+
+### 2026-05-31 | multi-model, sidecar, adversarial, validated | orchestrator-swap, perspective-diversity, cross-cli
+**File:** knowledge/shared/harness-core/multi_model_sidecar_strategy.md
+외부 모델(Gemini/Codex/Copilot CLI)을 Claude Code/FH 세션 안에서 Bash tool로 sidecar 호출하는 검증된 패턴. Experiment 1(직접 sidecar 호출) + Experiment 2(3-round orchestrator-swap)로 실증 — 각 orchestrator가 비중복 findings 발견, cross-wave delta가 convergence를 개선. perspective diversity(1순위)·model-access fallback(2순위)·token economy(3순위). §Mechanism: agent dispatch 아닌 stateless 서브프로세스.
+- Decision: 하네스가 multi-model synthesis의 activation condition — sidecar는 quality compounding 메커니즘이지 단순 coverage 체크 아님
+
+### 2026-05-31 | anti-bias, multi-team, adversarial, token-coverage | steel-quench, sim-conductor, experiment, v2-paper
+**File:** tracks/_meta/fh_multiteam_token_coverage_2026_05_31.md
+Experiment 5 — Multi-Team Adversarial Panel measured on source-grounding-audit SKILL.md. 4 conditions (C1 single / C2 cross-session / C3 +gemini / C4 codex-TTY-fail=C3). Key results: C1→25% coverage, C2→75%, C3→100%. Claude blind spots: 3 findings (25% of total), 1 S-grade. Claude-side cost C2→C3: +0 tokens (H3 validated — Gemini billed to separate quota). Codex CLI present but headless-inoperable. Updated steel-quench/sim-conductor/source-grounding-audit/harness-doctor/harvest-loop with Multi-Team Panel design + human gates + synthesizer cross-session. v2 paper Experiment 5 section drafted with full metrics table.
+- Decision: decision rule confirmed — routine→C2 (cross-session), pre-publish→C3+ (zero Claude overhead)
+### 2026-05-31 | synergy, integration, playbook | opencode, hermes, openhuman, governance, marketing
+**File:** knowledge/shared/harness-core/fh_synergy_playbook.md
+Concrete workflow specifications for using FH with OpenCode/Hermes/OpenHuman — grounded only in recorded experiments. Three patterns: (1) OpenCode: fh-gate.sh after code gen → DONE→PENDING flip, 2 A-grade on arity.ts; (2) Hermes: skill audit before dispatch → 2 A-grade pre-exec/credential gaps; (3) OpenHuman: Memory Tree staleness audit → GROUNDED/STALE/BROKEN verdict. Includes honest finding-rate estimates, "no integration required" value prop, and compounding effect explanation.
+- Decision: no unverified claims — every stated outcome traces to a specific experiment or structural guarantee
+
+### 2026-05-31 | integration-contract, bridge-layer, governance-interface | opencode, hermes, openhuman, v2-paper
+**File:** knowledge/shared/harness-core/fh_integration_contract.md
+Formal v0.1 specification for how callers (OpenCode, Hermes, OpenHuman, CI) invoke FH governance gates and receive structured verdicts. Defines: input format (newline-separated files), FH_STATUS+verdict format, findings in YAML block, parse recipe. Includes caller-specific guidance + Stop hook pattern + record spec. Gemini adversarial review found 2 A-grade issues (space-separated paths, non-parseable multi-line fields) — both fixed in v0.1. Also includes `scripts/fh-gate.sh` prompt-generator wrapper.
+- Decision: findings use YAML block (not flat key-value) to prevent delimiter ambiguity; FH_STATUS mandatory for fail-safe parsing
+
+### 2026-05-31 | opencode, governance, usage-guide, synergy | pipeline-conductor, steel-quench, v2-paper
+**File:** knowledge/shared/harness-core/fh_opencode_governance_wrapper.md
+Step-by-step usage guide for FH + OpenCode governance integration. 3-step protocol (diff capture → steel-quench → pipeline-conductor). No API adapter required. Includes empirical baseline from arity.ts trial: CI=DONE, FH governance=PENDING, 2 A-grade security-adjacent findings caught. Stop hook automation pattern included.
+- Decision: governance wrapper documented as protocol (not API) — FH reads files OpenCode writes
+
+### 2026-05-31 | v2-paper, opencode, governance, controlled-experiment | steel-quench, pipeline-conductor, synergy
+**File:** tracks/_meta/fh_opencode_governance_experiment_2026_05_31.md
+FH governance (steel-quench + pipeline-conductor --quick) applied to OpenCode's AI-generated `arity.ts`. Baseline: CI green, DONE. FH governance: PENDING — 2 A-grade findings (short-token overflow in permission allowlist, npx/opencode missing from arity table) + 1 B-grade. Delta not attributable to model — attributable to methodology layer. v2 paper prototype: controlled experiment evidence for N-fold synergy claim.
+- Decision: governance layer catches issues CI misses; arity.ts short-token overflow is permission-critical and untested
+
+### 2026-05-30 | fh-meta | edit-manifest, predict-verify, validation-gate, skill-evolution, SkillOpt, AHE
+**File:** plugins/fh-meta/skills/edit-manifest/SKILL.md
+New skill: predict-verify loop for harness edits. Every SKILL.md/rules/CLAUDE.md edit records a falsifiable prediction; next session verifies against actual outcomes. Validation gate (SkillOpt pattern) accepts only edits with measurable improvement; rejected edits retained as negative-feedback buffer. Integrated as harvest-loop Step 0-c.
+- Decision: based on AHE (arXiv:2604.25850) change manifest + SkillOpt (arXiv:2605.23904) selection-split gate
+
+### 2026-05-30 | fh-meta | memory-hygiene, stale-memory, staleness-detection, verification
+**File:** plugins/fh-meta/skills/memory-hygiene/SKILL.md
+New skill: detects "stale-but-confident" memory entries (facts verified once but silently drifted). Classifies by type (project 14d / reference 30d / feedback 90d / user 180d), re-verifies live via gh CLI or WebFetch (FH online advantage), proposes archival. Integrated as harvest-loop Step 0-c.
+- Decision: based on Scaling the Harness (arXiv:2605.26112) §3.2 stale-but-confident failure mode
+
+### 2026-05-29 | harness-core | return-path-gate, skill-chain, conditional-pass, closed-loop
+**File:** knowledge/shared/harness-core/return_path_gate.md
+Pattern: downstream skill returns structured verdict (PASS/CONDITIONAL_PASS/FAIL/ESCALATE) back to caller, which gates next step on it. Verified in apex-review→sim-conductor and agent-composer↔deliberation.
+- Decision: promoted to knowledge/shared/ — same pattern appeared independently in 2 skill pairs
+
+### 2026-05-29 | harness-core | meta-harness-engineering, definition, frontier, academic-convergence
+**File:** knowledge/shared/harness-core/meta_harness_engineering_definition.md
+Formal definition of meta harness engineering + FH positioning vs. academic convergence (arXiv 2605.18747 "Code as Agent Harness", arXiv 2604.14228 98.4% finding). Maps FH 6-axis to 3-layer taxonomy; distinguishes human-in-loop (FH) vs automation-first vs automation-maximalist approaches.
+- Decision: FH differentiator = human judgment gate on all PRs, not automation maximization
+
+### 2026-05-29 | fh-commons | token-budget-gate, token-estimation, cost-guard, multi-agent
+**File:** plugins/fh-commons/skills/token-budget-gate/SKILL.md
+New skill: pre-task token cost estimation with Green/Yellow/Orange/Red gate verdict. Post-task calibration loop improves future estimates. Auto-proposed before agent-composer, sim-conductor, steel-quench, harvest-loop.
+- Decision: placed in fh-commons (project-agnostic, useful before any expensive multi-agent task)
+- Thresholds: <10K green / 10-30K yellow / 30-60K orange / >60K red (user-configurable)
+
+### 2026-05-29 | fh-commons | mcp-circuit-breaker, mcp-reliability, tool-failure, fallback
+**File:** plugins/fh-commons/skills/mcp-circuit-breaker/SKILL.md
+New skill: detects MCP tool failure patterns (3 consecutive fails = trip), blocks further calls, proposes 3-tier fallbacks, and resets via HALF-OPEN probe after cooldown.
+- Decision: placed in fh-commons (project-agnostic MCP guard, useful in any Claude Code project)
+- Circuit states: CLOSED → OPEN → HALF-OPEN → CLOSED
+
+### 2026-05-29 | fh-meta | prompt-regression, regression-detection, harness-quality
+**File:** plugins/fh-meta/skills/prompt-regression/SKILL.md
+New skill: detects harness behavioral regressions after CLAUDE.md / rule / skill edits by running standard probe suite and comparing against baselines.
+- Decision: placed in fh-meta (harness-specific behavioral testing, not general-purpose)
+- Chain: FAIL verdict → harness-doctor → verify-bidirectional
+
+### 2026-05-28 | _meta | install-wizard, plugin-autoinstall, deprecated-cleanup, fh-ops, external-validation
+**File:** tracks/_meta/session_2026_05_28_fh-external-ops.md
+First external run of FH — install-wizard (score 57/100) revealed 2 friction points, both fixed immediately. PR #7 (plugin auto-install) + PR #8 (deprecated refs cleanup) merged.
+- Decision: install-wizard FH plugin MISS → AI auto-runs via Bash (eliminates 3-turn manual flow) — "friction only visible when the builder actually uses it" pattern
+- Decision: deprecated refs must be updated alongside CHANGELOG — separate cleanup PR required
+
+### 2026-05-27 | _meta | two-layer-storage, memory-vs-tracks, cross-session-state
+**File:** tracks/_meta/fh_signal_2026_05_27_session-starter.md
+Two-layer storage principle formalized: `tracks/` = local work history (machine-bound), `memory/` = critical cross-session state (durable, survives re-clone). Gap: session starter files in tracks/ are lost on machine change.
+- Decision: Critical cross-session state must also be written to `~/.claude/projects/.../memory/` — tracks/ alone is insufficient for durability
+
+### 2026-05-26 | _audit | sister-asset, harness-evolver, meta-harness, stanford, arxiv
+**File:** tracks/_audit/session_2026_05_26_harness_evolver.md
+Sister asset cross-audit — harness-evolver (raphaelchristi) + Meta-Harness (Lee et al., arXiv:2603.28052, Stanford IRIS Lab). Independent architectural convergence confirmed: outer-loop field observation → adversarial critique → synthesis → integration → verification. Cross-reference links proposed; Issue #26 filed.
+- Decision: harness-evolver = direct complement (automation-first) vs FH (knowledge-accumulation-first) — mutual citation proposed
+
+### 2026-05-26 | _audit | sister-asset, sylph-ai, arxiv, simplification-principle
+**File:** tracks/_audit/session_2026_05_26_sylph_sister.md
+Sister asset cross-audit — "The Last Harness You'll Ever Build" (Sylph.AI, arXiv:2604.21003). Title resonates with FH simplification principle but approach diverges: Sylph = fully automated adversarial agent loops, FH = human-in-the-loop curated knowledge evolution.
+- Decision: Sylph.AI = automation-maximalist counterpart; FH distinction is human judgment layer
+
+### 2026-05-26 | _meta | external-network, wave3-validation, sase, install-wizard, frontier-digest
+**File:** tracks/_meta/external_network_verification_2026_05_26.md
+Wave 3 meta-validation: confirmed all previously restricted-network-blocked capabilities work on a standard network — install-wizard dry-run, plugin-recommender live GitHub search, frontier-digest fetch, git push. Baseline for external user environment parity.
+- Decision: All core FH capabilities verified functional on a standard (unrestricted) network
+
+### 2026-05-26 | forge-harness | v1.2, public-release, harness-evolver-absorb
+**File:** tracks/_meta/reference_next_session_starter.md
+v1.2 release complete (PR #1–#5): harvest-loop Step 0, agent-composer worktree isolation, steel-quench numeric scoring, README positioning. Repo made public.
+- Decision: harness-evolver 3대 혁신 흡수 — regression guard / worktree isolation / numeric scoring
+
+---
+
+## Reference Documents
+
+<!-- Time-independent reference documents -->
+
+### 2026-04-28 | template | maturity-roadmap, 3-phase-frame, frontier-tracking, simplification-gate
+**File:** `knowledge/shared/harness-core/hub_maturity_roadmap.md`
+Hub long-term evolution path frame. Phase I (entering maturity) → Phase II (frontier following (b)cadence) → Phase III (leading) 3-stage model + 5-criteria gate (audit automation·operations guide·external propagation·sub-agent judgment·self-diagnosis warning) + 6 indicators (seed repo·blog·citations·external adoption·self-evolving·industry original) + simplification gate (self-diagnosis + within 200 lines + unreferenced archive at each transition). General-purpose template derived from first verified operating instance.
+- Decision: (b) quarterly + monthly cadence recommended — if adopting other option, need to prove simplification gate passed
+- Decision: Phase III has no completion (ongoing state) — 3+ of 6 indicators continuously rising is the maintenance condition
+- Decision: Phase regression allowed — do not force linear progression (allow partial Phase I redo if frontier following routine is missed)
+
+---
+
+## Plugins
+
+### 2026-05-08 | fh-meta v0.5.0 | six-skills-operation, path-b-generalization, command-tower-gate, mode-c-user, beta-release
+**File:** plugins/fh-meta/.claude-plugin/plugin.json + .claude-plugin/marketplace.json
+Hub meta operations tool bundle — 6 skills operation. harvest-loop path B generalization + verify-bidirectional path B generalization + frontier-digest path B generalization + cross-ecosystem-synergy-detection + plugin-recommender + **hub-cc-pr-reviewer** command tower gate operations rule automation (new). 2 agents (hub-persona-auditor + fact-checker). Beta operation — harness core principle *"beta + public release = practical capability obligation"* followed.
+- Decision: hub-cc-pr-reviewer skill newly created — command tower gate operations rule automation + PR lifecycle 4-run accumulated + explicit decision trigger
+- Decision: plugin level v0.4.3 → v0.5.0 promoted — 6 skills operation baseline + path B generalization baseline followed
+- Decision: 3 skills path B generalization — harvest-loop + verify-bidirectional + frontier-digest / external user environment adaptation path enhanced
+- Note: audit-learnings deprecated from plugin (2026-05-xx) → transferred to hub-internal deprecated/; replaced by harvest-loop
+- Note: frontier-status-summary deprecated (2026-05-xx) → replaced by frontier-digest
+
+---
+
+## Skills
+
+### 2026-05-08 | fh-meta | harvest-loop, weekly-audit, self-evolution-pipeline, session-harvest, phase-2-plus
+**File:** plugins/fh-meta/skills/harvest-loop/SKILL.md
+Self-evolution pipeline — field-harvest → contention-layer → devil/innovator parallel → synthesizer → Critic Agent → harness-doctor → verify-bidirectional → curator (8 steps). Lightweight mode for weekly audit. Replaces deprecated audit-learnings.
+- Decision: harvest-loop = audit-learnings successor + full self-evolution pipeline integrated
+
+### 2026-05-08 | fh-meta | verify-bidirectional, layer-5-cross-verification, conscious-self-activation, diff-gate
+**File:** plugins/fh-meta/skills/verify-bidirectional/SKILL.md
+Bidirectional self-verification pattern automation — when user's precision counter-argument manifests after AI recommendation/agreement persistence, baseline update channel 6-step processing.
+- Decision: v0.5 official release — accumulated runs + mode C correction catch fully persisted
+
+### 2026-05-08 | fh-meta | hub-cc-pr-reviewer, command-tower-gate-automation, baseline-coherence-check, layer-5-self-catch
+**File:** plugins/fh-meta/skills/hub-cc-pr-reviewer/SKILL.md
+Command Tower Gate operations rule automation — on PR input, auto-generates baseline coherence check 8-matrix + Layer 5 self-catch matrix + review comment attachment + admin override merge recommendation.
+- Decision: v0.1 newly created — PR lifecycle 4-run accumulated + explicit decision trigger met
+
+### 2026-05-20 | fh-meta | context-bridge-dispatch, agent-view-context-blindness, parallel-dispatch, session-context-card
+**File:** plugins/fh-meta/skills/context-bridge-dispatch/SKILL.md
+Parallel agent dispatch pre-session context card injection pattern automation — sub-agents read files but cannot access main session living context. Context Card (purpose·completed·this agent's task·caution) generation and injection into each prompt before 2+ parallel dispatches. Simple file lookup agents can omit.
+- Decision: v0.1 newly created — agent view blindspot captured in the field → FH skill decision
+
+---
+
+## Agents
+
+### 2026-05-08 | fh-meta | hub-persona-auditor, persona-simulation, three-tier-revision, external-asset-pre-publication
+**File:** plugins/fh-meta/agents/hub-persona-auditor.md
+External-facing asset (briefing·card·public guide) pre-publication persona audit — 3+ virtual reader persona simulation + 4-axis (resonance·confusion·resistance·supplement) review + 3-tier (mandatory·strong·recommended) revision proposals.
+- Decision: fh-meta agent separate operation (not a skill / external-facing cadence activation)
+
+### 2026-05-08 | fh-meta | fact-checker, hub-asset-grep-verification, duplicate-detection, stale-fact-detection
+**File:** plugins/fh-meta/agents/fact-checker.md
+Hub asset grep verification — (1) hub asset duplicate check before recommending new asset/skill/agent (2) stale data detection in memory/docs (3) when duplicate work is suspected.
+- Decision: hub self-review circuit baseline established
+
+---
+
+## Learnings
+
+<!-- Accumulated feedback/lessons -->