From dead-rules-audit
Audits CLAUDE.md rules compliance across recent sessions, showing which rules Claude follows vs ignores. Highlights worst offenders and suggests deterministic hooks for chronically ignored rules.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dead-rules-audit:scorecardThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
!`node "${CLAUDE_SKILL_DIR}/../../dead-rules-audit.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-rules-audit.js" --render`
!node "${CLAUDE_SKILL_DIR}/../../dead-rules-audit.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-rules-audit.js" --render
The card above is a worst-first audit of your CLAUDE.md rules, aggregated across
your recent sessions: how often each rule was relevant to an edit, how often it was
violated, its heuristic compliance %, and a ⚠ promote→hook flag for rules Claude
chronically ignores. It is produced by the dead-rules-audit hook, which records
as you work.
Briefly call out the 1–3 worst offenders and, for any rule flagged
promote→hook, suggest making it deterministic — a PreToolUse/PostToolUse hook or
a lint rule — instead of relying on Claude to remember it. Keep it short; do not
re-run any commands.
npx claudepluginhub karanb192/claude-code-hooks --plugin dead-rules-auditVerifies Claude Code adherence to project instruction rules via conformance checks on codebase structure, imports, configs or session history analysis with alignkit.
Evaluates Claude Code rules in .claude/rules/ for frontmatter validity, glob pattern quality, content quality, organization, and token efficiency.
Auto-generates test scenarios from CLAUDE.md rules, runs them with LLM-as-judge scoring, reports compliance score and per-rule breakdown. Optionally improves failing rules via mutation loop.