Clawlint Rule Expert — Development agent for Claude Code
Use this agent to answer deep questions about clawlint rules — what a rule actually checks, how its thresholds work, why it exists, what false positives to watch for, and how to configure it.
How to install Clawlint Rule Expert
Installs to ~/.claude/agents/dotbeeps-clawlint-clawlint-rule-expert.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dotBeeps/clawlint/HEAD/agents/clawlint-rule-expert.md -o ~/.claude/agents/dotbeeps-clawlint-clawlint-rule-expert.md Restart Claude Code, or start a new session, for it to be picked up.
What Clawlint Rule Expert does
name: clawlint-rule-expert description: Use this agent to answer deep questions about clawlint rules — what a rule actually checks, how its thresholds work, why it exists, what false positives to watch for, and how to configure it. Dispatch when the user asks about a specific rule id, asks "what rules does clawlint ship", or wants to tune a threshold. model: haiku tools: Bash, Read, Grep, Glob
You are the clawlint rule expert. You know the catalog cold, and you can answer rule-level que
Alternatives in Development
- Docs Impact Agent — Finds repository documentation made false by a change and missing documentation required to use or operate a n 2.2k ★
- PR Check Watcher — Watches a GitHub PR's CI checks to completion via gh pr checks --watch and reports a concise pass/fail summary 289 ★
- Rule Reviewer — Internal agent for reviewing draft rules 150 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Rules Master
D&D 5e rules, mechanics, and judgments expert. Use PROACTIVELY when rule questions arise, mechanics need clari
Dead Code Hunter
Verifies dead code findings from knip/grep. Reads actual source files to filter false positives. Cites file:li
Markdown Investigator
Autonomous analyzer that determines if markdown errors are fixable or false positives
Light Review Step2
Stage 2 of the Delphi review pipeline — counter-analyze the findings of a prior light-review-step1 run. Drops
Review Bug
Review: Bug/Logic Error Detection (coverage-first) — report all findings with confidence and severity tags; do
Claim Auditor
Adversarial verifier for proposed genealogical matches. Tries to break each proposed match with evidence, kill
Related Skills
Enforcement Contradiction Rules
Always-on. When the enforcement system itself produces contradictions — gates blocking their own prerequisites
Makoto
When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deed
Audit Strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Agg