Claudemd Rules — Security skill for Claude Code
Audit the HARD-rules manifest.
How to install Claudemd Rules
Installs to ~/.claude/skills/sdsrss-claudemd-claudemd-rules/SKILL.md
mkdir -p ~/.claude/skills/sdsrss-claudemd-claudemd-rules && curl -fsSL https://raw.githubusercontent.com/sdsrss/claudemd/HEAD/commands/claudemd-rules.md -o ~/.claude/skills/sdsrss-claudemd-claudemd-rules/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Claudemd Rules does
name: claudemd-rules description: Audit the HARD-rules manifest. Cross-references spec/hard-rules.json with rule-hits.jsonl bySection data over the last N days (default 30). Surfaces §13.1 demote candidates (hook-enforced rules with 0 hits in window) and stale-review entries.
Default window is 30 days (per OPERATOR.md §13.1; set in spec v6.11.15 as core §0.1 and moved to OPERATOR.md in v6.15.1 — lowered from 90d because the 90d gate was structurally unreachable under typical rule-hits l
Alternatives in Security
- Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
- Audit Agent Sessions — Analyze all agent sessions from the last 3 days across Claude, Codex, and Gemini 238 ★
- Audit Verbs — Audit uip Verb References 166 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claudemd Audit
Aggregate claudemd rule-hits over the last N days. Shows top banned patterns, hook deny counts, per-spec-secti
Claudemd Sampling Audit
Retrospective batch scan of historical transcripts for 8 self-enforced HARD rules — text detectors (§10-V bann
Audit Tokens
Analyze audit-log.jsonl for ghost-token-waste patterns across the 6 PLAN-047 detectors. Emits a markdown repor
Audit Cc Tail
Detects distinct Claude model variants per family from behavioral fingerprints in Claude Code JSONL history
Route Status
Show recent auto-router decisions and a rolling distribution of model routings. Reads from ~/.claude/cache/rou
Aegis Activity Logger
Append-only JSONL audit log of every Edit/Write/Bash mutation, one file per UTC day. Provides historical repla
Related Agents
Remotion Rule Reviewer
Remotion 渲染前的"自信关"——在跑贵渲染之前,对当前改动做一次语义级审查。对照 docs/HARD_RULES.md(框架红线)和 kit/theme.ts(设计 token),抓 hook 抓不到的语义错:s
Pattern Consolidator
Sleep-time memory compute. Reads daily notes + subagent logs from the last 7 days, identifies recurring patter
12 Lost Link Monitor
The backlinks lost in the last 90 days, ranked by the authority lost, and which are worth reclaiming.