@chrono-meta/fh-gate 1.2.2 → 1.4.0

package/plugins/fh-meta/skills/install-wizard/SKILL.md

@@ -26,15 +26,15 @@ category: Composability Gate
 > See `README.md > Advanced Settings > Plugin Install` for detailed guide.
 
 Run immediately after cloning forge-harness (FH), or when setting up a new project for the first time.
-Sets up periodic notification structure (zshrc hook) and weekly audit notifications within Claude Code (CC) sessions. The zshrc hook is permanently applied; CronCreate is valid only for the current session.
+Sets up the periodic-audit notification structure: a permanent zshrc hook (`fh_audit_check.zsh`, runs on terminal start) plus FH's session-start mtime detection. Both surface a weekly-audit reminder when 7+ days have elapsed since the last `weekly_audit` — no persistent cron is used (a session-scoped scheduler cannot survive to fire on a later day).
 
 ## Key Terms
 
 | Term | Definition |
 |---|---|
 | **sentinel** | An empty file that records whether a specific event (audit complete, install complete, etc.) has occurred. Created in `~/.cc_sentinels/`. |
-| **CronCreate** | Claude Code built-in command — schedules periodic tasks valid for the current session. Disappears when session ends. |
 | **zshrc hook** | Shell function added to `~/.zshrc`. Automatically runs on terminal start and applies permanently. |
+| **session-start detection** | FH's durable weekly-audit cadence — at session start the mtime of the latest `weekly_audit_*` is checked and `/harvest-loop` is proposed if 7+ days elapsed (see CLAUDE.md Cadence Rules). No persistent scheduler required. |
 
 ## Execution Modes
 
@@ -51,7 +51,7 @@ Sets up periodic notification structure (zshrc hook) and weekly audit notificati
 - **Per-item approval**: Select each item individually (Y approve / N skip / L later)
 - **Double-confirm irreversible changes**: Preview before file writes and zshrc modifications
 - **User review before PR creation**: Output PR parameters (title, base branch, included files, body) and get approval before execution. No automatic submission.
-- **Periodic audit structure setup**: zshrc hook (permanently applied on terminal start) + sentinel initialization + CronCreate (valid for current CC session)
+- **Periodic audit structure setup**: zshrc hook (permanently applied on terminal start) + sentinel initialization + session-start mtime detection (7-day threshold)
 
 ## Execution Steps
 
@@ -138,9 +138,13 @@ echo 'source ~/.cc_secrets/tokens.env' >> ~/.zshrc
 **The following are environment detection procedures that CC executes automatically. No need for users to run manually.**
 
 ```bash
-# Prompt injection pre-flight: check for AI instruction injection in external config files
-if grep -rE "^# CLAUDE:|^# AI:|<instructions>" ~/.zshrc .claude/settings.json 2>/dev/null | grep -q .; then
-  echo "⚠️  AI instruction pattern detected in external config files — injection risk. Manual check recommended."; fi
+# Prompt injection pre-flight: scan config AND the project's AI-instruction surfaces — CLAUDE.md,
+# AGENTS.md, .claude/rules/* — which are the higher-risk vectors in an unknown repo (not just shell/settings).
+# Injection-SPECIFIC patterns only (override/exfil), since instruction files legitimately carry directives;
+# advisory (recommend manual review), never an auto-block.
+if grep -rIE "ignore (all )?previous|disregard (the )?above|exfiltrat|^# CLAUDE:|^# AI:|<instructions>" \
+     ~/.zshrc .claude/settings.json CLAUDE.md AGENTS.md .claude/rules/ 2>/dev/null | grep -q .; then
+  echo "⚠️  AI-instruction / override pattern detected in config or instruction files — injection risk in an unknown repo. Review the listed files manually before proceeding."; fi
 
 # FH location
 echo "FH_DIR=${FH_DIR:-not set}"
@@ -164,13 +168,13 @@ python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude.json'
 # zshrc hook status
 grep -q "fh_audit_check.zsh" ~/.zshrc 2>/dev/null && echo "zshrc hook: present" || echo "zshrc hook: absent"
 
-# Framework detection (Streamlit) — must be specified in requirements.txt or pyproject.toml
-STREAMLIT_PROJECT=false
-if grep -q "streamlit" requirements.txt 2>/dev/null || \
-   grep -q "streamlit" pyproject.toml 2>/dev/null; then
-  STREAMLIT_PROJECT=true
-  echo "Framework: Streamlit detected"
-fi
+# Framework detection (optional) — only used to look for a matching OPTIONAL domain pattern pack.
+# Generic: capture the framework name; the pattern-pack path is derived as {framework}_patterns.md.
+# No pattern pack ships by default — this is a user-supplied extension point, absence is the normal state.
+FRAMEWORK=""
+for fw in streamlit django fastapi flask; do
+  if grep -qi "$fw" requirements.txt pyproject.toml 2>/dev/null; then FRAMEWORK="$fw"; echo "Framework: $fw detected"; break; fi
+done
 ```
 
 **Bootstrap guidance when FH_DIR is not set (stop immediately in Step 0):**
@@ -180,8 +184,10 @@ fi
   1. Clone FH repo:
      git clone https://github.com/chrono-meta/forge-harness ~/forge-harness
 
-  2. Set environment variable:
+  2. Set environment variables:
      export FH_DIR=~/forge-harness
+     export CC_HUB_DIR=$FH_DIR   # FH hub dir (holds tracks/_audit for the weekly-audit mtime check);
+                                 # equals FH_DIR unless you run a separate hub clone
 
   3. Install FH plugin in CC:
      Settings → Plugins → Add → {FH_DIR}/plugins/fh-meta
@@ -194,11 +200,12 @@ fi
 
 *(Run after Step 0-A·B pre-checks. Output results as environment card, then continue to Step 0-C.)*
 
-Output detection results as **environment card**. Activate CC pattern reference on Streamlit detection:
+Output detection results as **environment card**. If a framework was detected AND you maintain a matching
+optional domain pattern pack, reference it (none ship by default — absence is normal, never a gap):
 ```
-📌 Streamlit project detected → CC pattern reference activated
-   {CC_HUB_DIR}/knowledge/shared/streamlit_patterns.md loaded (if present — optional Streamlit pattern pack, not shipped by default)
-   Check: data_editor empty df / column nesting / async wrapper / CSS numeric variables
+📌 {FRAMEWORK} project detected → optional domain pattern pack check
+   {CC_HUB_DIR}/knowledge/shared/{FRAMEWORK}_patterns.md loaded (only if you supplied it; not shipped by default)
+   If absent: skip silently — no pack is the expected default state.
 ```
 
 ```
@@ -219,7 +226,7 @@ install-wizard — Environment Detection
 > **Core message**: FH is not something placed on top of an existing harness.  
 > It analyzes existing rules to remove duplicates — making things lighter.
 >
-> **Measured expectations** (--dry-run verified values):
+> **Illustrative single-run measurements** (n=1 per project, `--dry-run` verified — not benchmarks; your numbers will differ):
 >
 > | Project type | Example | Total volume | Reduction | Main cause |
 > |---|---|---|---|---|
@@ -323,9 +330,10 @@ Auto-check the following items based on detected environment. Each item classifi
 | MCP plugin | ~/.claude.json mcpServers contains entry | `python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude.json'))); print(list(d.get('mcpServers',{}).keys()))"` |
 | `deep-insight plugin` | settings.json plugins contains deep-insight | `grep -r "deep-insight" .claude/settings.json 2>/dev/null` |
 | `fh_env_context.jsonc` | `.claude/rules/fh_env_context.jsonc` exists | `ls .claude/rules/fh_env_context.jsonc` |
-| `Streamlit pattern applied` | (Streamlit projects only, if the pattern pack is present) data_editor empty df branch/async wrapper/CSS numeric variables | CC `knowledge/shared/streamlit_patterns.md` Pattern 1-5 check (skip if file absent) |
+| `phantom-gate` | **(Python + AI-output projects only)** `phantom-gate` present in `requirements.txt` / `pyproject.toml` | `grep "phantom.gate" requirements.txt pyproject.toml 2>/dev/null` |
+| `Domain pattern pack applied` | (optional — only when a `{framework}_patterns.md` pack is present; none ship by default) framework-specific pattern checks | `knowledge/shared/{framework}_patterns.md` check (skip if file absent — the normal default) |
 
-**Score calculation**: PASS = 1 point / MISS = 0.5 points / FAIL = 0 points → converted to 100-point scale.
+**Score calculation**: PASS = 1 / MISS = 0.5 / FAIL = 0. Formula: `score = round( Σ(points) ÷ (applicable item count) × 100 )`. Conditional items (domain pattern pack / phantom-gate / MCP / deep-insight) are excluded from the denominator when not relevant, so always print the denominator next to the score (e.g. `{score}/100 over {n} applicable items`) — the percentage is reproducible only when the item count is shown.
 
 ### Step 2. Diagnosis Report + Proposal List
 
@@ -356,13 +364,21 @@ install-wizard — Diagnosis Results ({score}/100)
   [6] Add MCP plugin — activate integrations (if MCP plugin MISS)
       Run: claude mcp add <your-mcp-plugin> -- npx -y <your-mcp-plugin>
       CC restart required after completion
-  [7] Install deep-insight plugin — activate sim-conductor multi-persona simulation (if deep-insight MISS)
-      Settings → Plugins → Add → {deep-insight plugin path}
-      Without install, /sim-conductor persona branching disabled (single-point simulation only)
+  [7] (Optional — field plugin, NOT required) Install deep-insight — adds the field's domain personas to sim-conductor
+      deep-insight is a private/field marketplace plugin. sim-conductor already ships the built-in
+      user-mastery spectrum (beginner · main-player · expert · challenger), so multi-persona simulation
+      works WITHOUT it. If you have access: Settings → Plugins → Add → <your deep-insight path>.
+      If not: skip — sim-conductor falls back to the built-in spectrum agents (no capability lost).
   [8] Create fh_env_context.jsonc — org/network/Git environment context file (if fh_env_context.jsonc MISS)
       Copy: {FH_DIR}/templates/fh_env_context.jsonc → .claude/rules/fh_env_context.jsonc
       Then manually update with actual values for org name, Jira URL, environment status, etc.
       Effect: Each skill references common environment context → eliminate individual setting duplication
+  [9] Install phantom-gate — AI output hallucination detection (Python + AI-output projects only, if MISS)
+      Run: pip install git+https://github.com/chrono-meta/phantom-gate.git
+      Usage: phantom-gate scan output.txt / phantom-gate scan . --project
+      Detectors: M1 (phantom claims) · M2 (self-reference loops) · M3 (unvalidated external-dep claims) · M4 (temporal) · M5 (cross-file version mismatch)
+      Skip condition: non-Python project OR no AI-generated output in pipeline
+
 
 Each item: Y (approve) / N (skip) / L (later) / A (approve all)
 ```
@@ -470,9 +486,16 @@ source "$FH_DIR/templates/fh_audit_check.zsh"
 EOF
 fi
 
-# 4-axis verification gate — install the FH pre-commit hook on the forge-harness clone (idempotent)
-# Git does NOT set core.hooksPath automatically on clone, so this one-time step is required for the gate to enforce (otherwise it stays advisory).
+# 4-axis verification gate (Mode D / FH-self-development only — OPT-IN, double-confirm required)
+# SCOPE (state this before asking): this gates commits IN YOUR FH CLONE ($FH_DIR) — git commit there is
+#   blocked until the 4-axis markers pass. It is FH-internal infra (hardcodes hub paths/markers) and is
+#   NEVER installed into field projects (see auto_project_mapping.md §6). Skip unless you develop FH itself.
+# Per Core Principles (Per-item approval + Double-confirm irreversible changes): this is NOT auto-run —
+#   it is a separate explicit Y/N, not folded into the baseline-setup batch.
 if [ -d "$FH_DIR/templates/.git-hooks" ]; then
+  echo "Enable the 4-axis pre-commit gate on your FH clone ($FH_DIR)? It will block commits there until"
+  echo "markers pass (Mode D / FH-development only). Skip if you are not developing FH itself. (Y/N)"
+  # → On explicit Y only:
   git -C "$FH_DIR" config core.hooksPath templates/.git-hooks
   chmod +x "$FH_DIR/templates/.git-hooks/pre-commit" 2>/dev/null
   echo "4-axis pre-commit gate: installed (core.hooksPath -> templates/.git-hooks)"
@@ -482,8 +505,9 @@ fi
 mkdir -p ~/.cc_sentinels
 touch ~/.cc_sentinels/$(basename "$(pwd)")_wizard_done
 
-# Weekly audit schedule in CC (CronCreate — valid for this session)
-# → auto-call /harvest-loop (lightweight mode) every Monday at 9:03
+# Weekly audit cadence — NO cron needed (a session-scoped scheduler cannot fire on a later day).
+# Durable mechanism = the zshrc hook above (fh_audit_check.zsh warns on terminal start when 7+ days
+# since last weekly_audit) + FH session-start detection (proposes /harvest-loop lightweight when overdue).
 ```
 
 ### Step 5. Completion Report + Contribution Guidance
@@ -496,7 +520,7 @@ install-wizard — Complete
   From now on:
   · Periodic audit auto-check on terminal start
   · Yellow warning output when weekly_audit exceeds 7 days
-  · Auto /harvest-loop (lightweight) at 9am Monday when CC is open
+  · /harvest-loop (lightweight) proposed at session start when 7+ days since last weekly_audit
 
   Next step skills:
   · Not sure which plugin you need → /plugin-recommender
@@ -559,7 +583,7 @@ ls ~/.cc_sentinels/${PROJECT_NAME}_wizard_done 2>/dev/null && echo "Inspection m
 |---|---|
 | Structural anomaly detected | `/harness-doctor` |
 | Token waste pattern detected | `/context-doctor` |
-| External user simulation needed | `/sim-conductor Area A` |
+| External user simulation needed | `/sim-conductor` |
 | Install conflict suspected | `/install-doctor` |
 
 ## Per-Cluster Deferred Loading (Progressive Disclosure)

package/plugins/fh-meta/skills/marketplace-gate/SKILL.md

@@ -187,7 +187,7 @@ All steps 0–2 completed
 + Overall verdict output (🟢 Recommended / 🟡 Conditional / 🔴 On hold)
 ```
 
-**→ Mandatory before 🟢 Recommended verdict: `source-grounding-audit`** — forward axis check on all citations, external URLs, and file path references in the asset being reviewed. A 🟢 verdict without source-grounding-audit is incomplete. If source-grounding-audit finds phantom refs → verdict downgrades to 🟡 Conditional automatically.
+**→ Mandatory before 🟢 Recommended verdict: `phantom-quench`** — forward axis check on all citations, external URLs, and file path references in the asset being reviewed. A 🟢 verdict without phantom-quench is incomplete. If phantom-quench finds phantom refs → verdict downgrades to 🟡 Conditional automatically.
 
 > When `agent-composer` receives a "comprehensive marketplace listing audit" request,
 > recommend: Wave 0 `fact-checker` → Wave 1 `marketplace-gate` + `hub-persona-auditor` in parallel.

package/plugins/fh-meta/skills/phantom-quench/SKILL.md

@@ -0,0 +1,248 @@
+---
+name: phantom-quench
+description: The grounding member of the quench series — extracts proper nouns, numerical values, and branching conditions from artifacts (TCs, analysis reports, design documents), back-traces them to declared source files, and marks anything not found as a Phantom Claim (ungrounded — present in the artifact but not traceable to a declared source; not a claim that it is necessarily false). If steel-quench attacks output patterns (self-declarations, cushion language), phantom-quench attacks input tracing (where did this come from?). Renamed from source-grounding-audit (2026-06-06, quench-series); `/source-grounding-audit` still resolves as an alias. Triggered by "phantom detection", "phantom-quench", "phantom claim", "hallucinated claim detection", "source back-trace", "source audit", "verify source", "TC evidence tracing", "where did this come from", "grounding audit", "source grounding audit", "false claim detection".
+user-invocable: true
+allowed-tools: ["Read", "Write", "Edit", "Bash", "Grep", "Glob"]
+model: sonnet
+---
+
+# phantom-quench — Input Tracing Grounding Audit
+
+> Just because an artifact looks plausible doesn't mean it's grounded in source. plausible ≠ grounded.
+
+> **Renamed from `source-grounding-audit` (2026-06-06)** — the grounding member of the quench series
+> (steel-quench · phantom-quench · goal-quench). Same skill, same ruleset; only the label changed to fit
+> the family. The **v1 paper (Zenodo 10.5281/zenodo.20397566) cites the old name** — that is the
+> historical record, not a phantom. `/source-grounding-audit` still resolves via the deprecated redirect
+> stub at `plugins/fh-meta/skills/source-grounding-audit/SKILL.md` (`successor: phantom-quench`).
+> This is a **label rename, not a capability change** — phantom-quench does not fuse steel-quench or
+> inject faults; those remain separate (orthogonality is deliberate — see Role Separation below).
+>
+> **Quench-series semantics** (resolves the "quench *what*?" question): each member subjects a different
+> thing to the forge — steel-quench hardens an **existing output**; phantom-quench hardens the system
+> against **mistaking the absent for present** (the phantom illusion — *not* the phantom as a material to
+> harden); goal-quench hardens the **goal itself** into an advanced version. Same verb, consistent grammar.
+>
+> **Not the same as `phantom-gate`.** `phantom-gate` is the *productized standalone* phantom detector — a
+> PyPI package run against any repo from the shell. `phantom-quench` is the *in-harness skill* — the same
+> detection lineage as a method invoked inside a Claude session against a declared source set. Tool vs
+> skill; different delivery, shared idea.
+
+When AI generates artifacts without reading the source, those artifacts look like domain knowledge but are actually **Phantom Claims** coming from LLM weights. This skill back-traces each claim in the artifact to the declared source to explicitly mark Phantoms.
+
+## Role Separation from steel-quench
+
+| Dimension | steel-quench | phantom-quench |
+|---|---|---|
+| **Attack target** | Output patterns (self-declarations, cushion language, reason for existence) | Input tracing (is the claim in the source?) |
+| **Core question** | "Is this structure flawed?" | "Where did this content come from?" |
+| **Activation timing** | All-angle quench just before completion | Immediately after source-based artifact generation or at point of suspicion |
+| **Primary attack vector** | Bus factor, self-reference, platform obsolescence | Phantom Claim, source not read, fabricated branching conditions |
+| **Representative pattern** | "Declaration only, no evidence" | "Number in TC that doesn't exist in source" |
+
+**Can be used together**: steel-quench Wave 1 real-code-based attack + phantom-quench Phantom marking can be run sequentially in the same session. But do not mix the roles of the two skills.
+
+---
+
+## Trigger Phrases
+
+| Phrase | Situation |
+|---|---|
+| "phantom detection", "phantom claim", "false claim detection" | Full artifact Phantom scan (primary trigger) |
+| "source back-trace", "source audit" | Analysis report, design document verification |
+| "verify source", "where did this come from" | Suspecting origin of a specific claim |
+| "TC evidence tracing", "TC source verification" | Post-TC-generation source consistency check |
+| "grounding audit", "source grounding audit" | Full artifact Phantom scan |
+| "verify evidence files" | Analysis report, design document verification |
+| `/phantom-quench` | Explicit call |
+
+---
+
+## Core Concept — Phantom Claim
+
+**Phantom Claim**: A claim that appears in the artifact but cannot be found in the declared source files.
+
+3 paths through which Phantoms are produced:
+
+| Path | Description | Risk |
+|---|---|:---:|
+| **Source not read** | AI generates artifact using domain knowledge without Read-ing source | S |
+| **Partial reading** | Source partially read, rest filled in with inference | A |
+| **Reconstruction contamination** | Source was read but LLM modified values/conditions during paraphrase | A |
+
+---
+
+## Execution Steps
+
+### Step 0. Confirm Audit Target
+
+If not provided by user, explicitly confirm: artifact file path, declared source files, and audit scope. Source not declared = S-grade blocker registered immediately.
+
+> **Detail**: See `SKILL_detail.md §Step0-Detail` — confirmation output format and simplification guard — read when audit target or source list is ambiguous.
+
+---
+
+### Step 0.5. Claim Distribution Profile
+
+> **Schema**: `knowledge/shared/harness-core/tpa_schema.md` — `phantom_risk` derivation rule, gate trigger conditions, §Gate Routing Table.
+
+Runs after Step 0 (target + source confirmed). Skip if user specifies scope explicitly.
+
+Scan artifact quickly to classify claim distribution:
+
+| Dimension | Signal → Audit depth shift |
+|---|---|
+| `claim_density` | > 10 claims → full Step 1-4 audit; ≤ 3 claims → light (S+A only) |
+| `artifact_type` | SKILL.md/design-doc → prioritize Branch/State-transition claims; code → prioritize Proper-noun/API claims |
+| `risk_level` | external publish / arXiv citations → all claim types, max depth |
+| `source_count` | 0 declared sources → S-grade blocker immediately (skip to Step 3 prescription) |
+| `quantitative_density` | > 3 numerical claims → focus numerical+range types first |
+
+Scope recommendation output:
+```
+Claim types to prioritize: [list]
+Audit depth: [full | prioritized | light]
+Immediate blockers detected: [yes/no — 0 sources = immediate S-grade]
+```
+
+**0-source behavioral rule**: When artifact has 0 declared sources, skip Steps 1-2 entirely and go directly to Step 3 with S-grade blocker: "Source not declared — all claims unverifiable."
+
+---
+
+### Step 1. Claim Extraction (Artifact Scan)
+
+Extract claims from the artifact that require source back-tracing. Claim types: Proper nouns (highest), Numerical/range values (highest), Branching conditions (highest), State transitions (high), Preconditions (high), Actors (medium). Exclude generic test methodology descriptions and generic UI patterns.
+
+> **Detail**: See `SKILL_detail.md §Step1-Detail` — full claim types table with examples, exclude list, and Step 1 output format template — read when deciding which claims to include or format the extraction results.
+
+---
+
+### Step 2. Source Read + Back-Trace
+
+Back-trace each claim to the declared source files using Read + Grep directly — no inference judgment. Partial match is not treated as match.
+
+Back-tracing classification:
+
+| Classification | Criteria | Marking |
+|---|---|:---:|
+| **Grounded** | Claim directly confirmed in source | ✅ |
+| **Partial** | Similar content in source but not exact match — needs re-confirmation | ⚠️ |
+| **Phantom** | Cannot be found in source | ❌ |
+| **Source-Missing** | Source itself cannot be Read or was not declared | 🔴 |
+
+> **Detail**: See `SKILL_detail.md §Step2-Detail` — back-tracing execution procedure, classification decision rules, and Step 2 output format template — read when handling edge cases or formatting results.
+
+---
+
+### Step 3. Phantom Classification + Prescription
+
+Classify Phantom and Partial claims by severity and provide prescriptions.
+
+**Severity classification criteria**:
+
+| Severity | Criteria | Examples |
+|:---:|---|---|
+| **S** (Immediate blocker) | If this claim is wrong, TC could Pass-judge incorrect behavior | Monetary boundary values, branching conditions, status values |
+| **A** (Must fix) | If this claim is wrong, TC cannot execute or runs wrong path | API endpoint names, field names, preconditions |
+| **B** (Improvement recommended) | If this claim is wrong, TC can execute but intent may differ | Descriptive text, non-critical names |
+
+Prescriptions: (1) Source Re-read — precisely re-read the relevant source section and fix; (2) Request source specification — when source doesn't exist or wasn't declared; (3) Delete/rewrite — delete claims without source grounding and rewrite from source.
+
+> **Detail**: See `SKILL_detail.md §Step3-Detail` — prescription procedures and Step 3 output format template — read when writing the classification table or applying a prescription.
+
+**S-grade Immediate Human Gate** — if 1+ S-grade Phantoms found, pause before Step 4/5 and surface:
+
+```
+⚠️  phantom-quench: N S-grade Phantom(s) found:
+  - [claim 1 — one-line summary, location]
+  - [claim 2 — one-line summary, location]
+
+Options:
+  (a) Continue — AI proceeds to Step 4 pattern diagnosis + Step 5 re-audit
+  (b) Human review first — inspect Phantoms directly, then proceed
+  (c) Abort — fix sources manually and re-run audit
+
+Waiting for input. (Default: a)
+```
+
+Rationale: S-grade Phantoms that enter Step 5 re-audit without human review risk LLM reconstruction contamination — the same pattern that originally produced the Phantoms can "verify" its own fixes. Human review at this threshold breaks the loop.
+
+---
+
+### Step 4. Source Not-Read Pattern Detection (Meta Diagnosis)
+
+Analyze Phantom distribution to diagnose structural problems in the artifact generation process. Reveal "why were these Phantoms produced", not just "this TC is wrong".
+
+**Pattern detection criteria**:
+
+| Pattern | Detection Condition | Meaning |
+|---|---|---|
+| **Source not read** | 3+ Phantoms and no or partial source Read history | AI generated using domain knowledge without reading source |
+| **Partial reading contamination** | Partial items exceed 30% of total | AI read source partially and filled rest with inference |
+| **Reconstruction modification** | Source value exists but unit/format/range modified in TC | LLM paraphrase process contamination |
+| **Source declaration absent** | Source file not specified when generating artifact | Process design stage problem |
+
+**Simplification guard**: If 0 Phantoms, skip Step 4 entirely. Replace with one line: "Source grounding adequate."
+
+> **Detail**: See `SKILL_detail.md §Step4-Detail` — Step 4 output format template — read when writing the pattern diagnosis section.
+
+---
+
+### Step 5. Post-Fix Re-audit (Optional)
+
+Re-run back-trace for S-grade blocker claims after fixes are complete. Activate when 1+ S-grade blockers exist and fix is immediately possible.
+
+**Done When (re-audit)**: Back-trace results for fixed claims all show Grounded (✅) status.
+
+---
+
+## Completion Declaration Format
+
+> **Template**: See `SKILL_detail.md §Report-Template` — full completion declaration format — read when producing the final audit summary.
+
+---
+
+## Connected Skills
+
+| Situation | Connected Skill |
+|---|---|
+| Simultaneously verify output patterns (self-declarations, cushion language) | `/steel-quench` Wave 1 "real-use verification" angle |
+| Re-verify Phantom patterns from external user perspective | `/sim-conductor Area A` |
+| Source not-read is a harness structure problem | `/harness-doctor` |
+| Phantom pattern is a candidate for new rule items | `fh-meta:persona-innovator` |
+| Redesign the artifact generation prompt itself | `/meta-prompt-builder` |
+
+---
+
+## External User Environment Adaptation
+
+This skill can be used independently without the full meta-harness structure.
+
+**How to declare source files**: When generating artifacts, specify "source: [file path list]", or provide source files when invoking this skill.
+
+**External environment fallback**:
+- If no `tracks/_meta/` → skip persistence step
+- If no project-specific rules (like PFD) → output Phantom pattern summary only
+
+---
+
+## Done When
+
+```
+Step 1 claim extraction complete
++ Step 2 all claims back-traced (using Read tool — no inference judgment)
++ Step 3 Phantom severity classification + prescription output
++ Step 4 process pattern diagnosis complete (skip if 0 Phantoms)
++ "phantom-quench Complete" declaration output
+```
+
+Verdict: PASS (0 Phantom claims) | CONDITIONAL_PASS (LOW-severity Phantoms only, prescriptions noted) | FAIL (1+ HIGH/MEDIUM Phantom — broken path, phantom file, or stale external link) | ESCALATE (scope unclear or claim extraction impossible)
+
+---
+
+## Operating Notes
+
+- **Never back-trace by inference**: Judging "this value is probably in the source" treats it as Partial not Phantom. Always directly confirm with Read + Grep.
+- **Partial is not Grounded**: Processing similar-value-in-source as Grounded misses the reconstruction modification pattern.
+- **Source not declared itself is S-grade**: If source is not declared when making an artifact, no claim can subsequently be verified. Recommend mandating source declaration in the process design stage.
+- **Recommended to use with steel-quench**: steel-quench quenches structural flaws, phantom-quench ensures source consistency. The two skills are orthogonal and artifact quality assurance is strengthened when used together.

package/plugins/fh-meta/skills/{source-grounding-audit → phantom-quench}/SKILL_detail.md

@@ -1,4 +1,4 @@
-# source-grounding-audit — Execution Detail
+# phantom-quench — Execution Detail
 
 On-demand reference. Load the section indicated by the pointer in SKILL.md.
 
@@ -153,7 +153,7 @@ Process prescription:
 **Completion Declaration Format**
 
 ```
-## source-grounding-audit Complete
+## phantom-quench Complete
 
 Audit scope: {artifact file} / source {N files}
 {N} total claims audited
@@ -179,4 +179,4 @@ Next actions:
 
 **Evidence Record**
 
-- **Verified in practice**: TC generation without reading source files → steel-quench passes → source-grounding-audit back-trace detects numerous Phantoms (notifications vs. push notifications, version names vs. non-enrolled, bottom sheet vs. screen navigation). **Procedure**: Read sources in order then regenerate → replace with source-based TCs. **Recurrence prevention**: Source gate implementation — FileNotFoundError if required source files absent. steel-quench misses this because: outputs look logically sound so pattern attacks cannot identify Phantoms — only source back-tracing can detect them.
+- **Verified in practice**: TC generation without reading source files → steel-quench passes → phantom-quench back-trace detects numerous Phantoms (notifications vs. push notifications, version names vs. non-enrolled, bottom sheet vs. screen navigation). **Procedure**: Read sources in order then regenerate → replace with source-based TCs. **Recurrence prevention**: Source gate implementation — FileNotFoundError if required source files absent. steel-quench misses this because: outputs look logically sound so pattern attacks cannot identify Phantoms — only source back-tracing can detect them.

package/plugins/fh-meta/skills/pipeline-conductor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pipeline-conductor
-description: Chains the four core FH verification pipelines (harvest-loop → steel-quench → source-grounding-audit → sim-conductor) into a single gated sweep. Accepts a scope (single skill, specific asset, full harness) and aggregates results into one structured report. Supports --quick mode (steps 2+3 only) and --full mode (all four steps). Triggered by "run the full pipeline", "chain all verifications", "end-to-end sweep", "pipeline-conductor", or "verify everything".
+description: Chains the four core FH verification pipelines (harvest-loop → steel-quench → phantom-quench → sim-conductor) into a single gated sweep. Accepts a scope (single skill, specific asset, full harness) and aggregates results into one structured report. Supports --quick mode (steps 2+3 only) and --full mode (all four steps). Triggered by "run the full pipeline", "chain all verifications", "end-to-end sweep", "pipeline-conductor", or "verify everything".
 user-invocable: true
 allowed-tools: ["Read", "Write", "Bash", "Grep", "Glob", "Agent"]
 model: sonnet
@@ -10,7 +10,7 @@ model: sonnet
 
 Chains the four standalone FH verification pipelines into a gated sequence. Each step receives the previous step's verdict before proceeding. Aggregates all findings into a single structured report at the end.
 
-The gap this closes: harvest-loop, steel-quench, source-grounding-audit, and sim-conductor are each invocable independently but have no automatic hand-off between them. Running them sequentially by hand loses inter-step signal — a FAIL in step 2 should block step 3 rather than silently continuing. pipeline-conductor enforces that ordering.
+The gap this closes: harvest-loop, steel-quench, phantom-quench, and sim-conductor are each invocable independently but have no automatic hand-off between them. Running them sequentially by hand loses inter-step signal — a FAIL in step 2 should block step 3 rather than silently continuing. pipeline-conductor enforces that ordering.
 
 ## Triggers
 
@@ -92,7 +92,7 @@ Do not infer scope — a wrong scope produces misleading verdicts.
 
 The four constituent skills use heterogeneous scope models. Translate the pipeline scope to each skill's invocation form before running any step:
 
-| Pipeline scope | harvest-loop (Step 1) | steel-quench (Step 2) | source-grounding-audit (Step 3) | sim-conductor (Step 4) |
+| Pipeline scope | harvest-loop (Step 1) | steel-quench (Step 2) | phantom-quench (Step 3) | sim-conductor (Step 4) |
 |---|---|---|---|---|
 | Single SKILL.md | Check session findings relevant to this skill; propose mode only | Adversarial attack on this SKILL.md | Back-trace claims in this SKILL.md to declared sources | Area D (artifact review) on this SKILL.md |
 | Specific directory | Check session findings in this domain | Attack all SKILL.md files in directory | Back-trace all claims in directory | Area A + Area D on the domain |
@@ -219,13 +219,13 @@ Run steel-quench against the target scope.
 
 ---
 
-## Step 3. source-grounding-audit — Phantom Claim Detection
+## Step 3. phantom-quench — Phantom Claim Detection
 
-Run source-grounding-audit against the target scope.
+Run phantom-quench against the target scope.
 
 **What it checks**: Proper nouns, numerical values, file paths, and branching conditions back-traced to declared source files. Claims not found in source are marked Phantom.
 
-**Invocation**: Run source-grounding-audit scoped to the same target as Steps 1 and 2.
+**Invocation**: Run phantom-quench scoped to the same target as Steps 1 and 2.
 
 **Load-bearing Phantom** (binary test — apply mechanically):
 
@@ -238,7 +238,7 @@ All other locations (§Triggers, advisory §Chains language, frontmatter descrip
 
 **Verdict criteria**:
 
-| source-grounding-audit result | pipeline-conductor verdict |
+| phantom-quench result | pipeline-conductor verdict |
 |---|---|
 | 0 Phantoms, all claims grounded | `PASS` |
 | Phantom claims found, none load-bearing (binary test) | `CONDITIONAL_PASS` — list Phantoms |
@@ -246,12 +246,12 @@ All other locations (§Triggers, advisory §Chains language, frontmatter descrip
 | Grounding ambiguous (source file exists but content unclear) | `ESCALATE` |
 
 **On FAIL**: Output the load-bearing Phantom(s). Ask:
-> "source-grounding-audit found a load-bearing Phantom claim. Fix and re-run Step 3, or abort the sweep?"
+> "phantom-quench found a load-bearing Phantom claim. Fix and re-run Step 3, or abort the sweep?"
 
 **On CONDITIONAL_PASS**: Capture non-load-bearing Phantoms. Continue to Step 4.
 
 ```
-[Step 3 — source-grounding-audit]
+[Step 3 — phantom-quench]
   Verdict: {verdict}
   Basis:   {one-line}
   Phantoms: {count} — {load-bearing: Y/N} — {top item or "none"}
@@ -320,7 +320,7 @@ pipeline-conductor — Sweep Report
   Step 0.5 — return-path-gate:       {PASS / CONDITIONAL_PASS / FAIL / SKIPPED / degraded}
   Step 1   — harvest-loop:           {PASS / CONDITIONAL_PASS / FAIL / ESCALATE / SKIPPED}
   Step 2   — steel-quench:           {verdict}
-  Step 3   — source-grounding-audit: {verdict}
+  Step 3   — phantom-quench: {verdict}
   Step 4   — sim-conductor:          {verdict}
 
   Overall: {CLEAN (--full) / CLEAN (--quick) / CLEAN (--no-sim) / PENDING / BLOCKED}