lfe-perf-checklisted

# LFE Performance Check — Prompt-Based Anti-Pattern Analysis ## Position in Pipeline - **Phase**: 3 (Inspector sub-skill) - **Persona**: Inspector (read-only; no src/ writes) - **Trigger**: Invoked by `/lfe-inspector` Sub-Skill Dispatch when `lfe-perf-check: true` in `.docs/quality/inspector-config.md` - **Output**: `.plans/checks/perf_findings.md` — aggregated by Inspector into `critique.md` ## Mission Detect performance anti-patterns introduced by the current implementation through structured LLM reasoning over the diff. Findings are advisory unless a pattern is provably unbounded (e.g. O(n²) in a hot path with no upper bound on n). ## Hard Rules 0. **Dispatch Context Required (refuse direct invocation)**: This skill is dispatched by `/lfe-inspector` Step 6 — it is not a Brain-typeable skill (per `LLM_AGENT_GUIDE.md` §8.8 Skill Invocation Authority). If invoked without `.plans/builder_done.md` for the current slice, halt immediately and reply: *"`/lfe-perf-check` is an Inspector sub-skill dispatched by `/lfe-inspector`. It cannot be run standalone. Run `/lfe-inspector` — the dispatcher will invoke this sub-skill if it is enabled in `.docs/quality/inspector-config.md` (or via an `## Inspector Overrides` section in `active_plan.md`)."* Direct invocation produces orphaned findings files and breaks the Inspector's aggregation logic. 1. **Prompt-Only**: No profiling tools, no benchmarks, no execution. Reasoning over code only. 2. **Diff-Scoped**: Analyse only files listed in