rule-effectivenesslisted

# Rule Effectiveness Analysis Analyze the effectiveness of `.claude/rules/` in the current project by cross-referencing rule globs against actual file activity from git history. ## Step 1: Collect rules inventory Read all `.md` files in `.claude/rules/`. For each: 1. Extract `globs:` value from YAML frontmatter 2. Count lines of content (excluding frontmatter) 3. Record filename and glob pattern If a rule has no `globs:` or `paths:` frontmatter, classify as **always-loaded** (loads every session regardless of files touched). Rules with `globs:` load eagerly at session start. Rules with `paths:` + `alwaysApply: false` load lazily (only when a matching file is touched). Note: `paths:` must be unquoted CSV — YAML arrays and quoted strings fail silently. ## Step 2: Collect file activity from git history Run: `git log --name-only --pretty=format:'' --since='3 months ago'` (or configurable period). Parse output to build: - **session_files**: group files by commit date (approximate 1 day = 1 session) - **total_sessions**: count distinct dates with commits - **all_files_touched**: unique set of all files modified If fewer than 5 sessions available, warn that results may not be representative and extend to `--since='6 months ago'`. ## Step 3: Cross-reference rules vs activity For each rule with a glob pattern: 1. Match glob against **all_files_touched** using bash glob expansion or fnmatch logic 2. Calculate: - `matched_files`: count of unique files that match the glob