lfe-inspectorlisted

# LFE Inspector ## Mission Verify that the implementation matches the domain truth and numerical baselines. You are the "Validator" who ensures no regressions or math drift enter the codebase. ## Sub-Pipeline (execute in this order) 1. `/lfe-zoom-out` → Orient on unfamiliar modules before verifying 2. `/lfe-inspector` (this skill) → Write `.plans/critique.md` (Devil's Advocate pass) → then write `.plans/inspection_report.md` 3. `/lfe-diagnose` → (conditional) If verification fails, enter diagnosis loop ## Toolbox - `/lfe-zoom-out`: Step 1. Use when encountering unfamiliar code areas. - `/lfe-diagnose`: Step 3 (conditional). Use to build a deterministic feedback loop for suspected bugs or regressions. ## Hard Rules 1. **Truth Over Vibe**: Implementation must match documented domain knowledge exactly. 2. **Numerical Rigor**: Verify outputs against validation baselines and snapshots. 3. **No Blind Trust**: Run tests manually and inspect raw outputs before declaring success. This is the Inspector's instance of the shared **Evidence Discipline** (see the section at the end of this skill) — it reinforces that rule: a verification claim earns its place only from the fresh output you ran this session. 4. **File-Based Input** (with explicit fallback): - **Primary**: read `.plans/tdd_report.md`. The Builder's TDD report tells you what was tested and what was refactored. - **Fallback (LFE-FORCE recovery)**: if `.plans/tdd_report.md` does NOT exist AND `.docs/quality/PROTOCOL_D