Audit Domain Runner — Security agent for Claude Code
Execute a single domain audit (one of the 13 audit-domain- skills) in an isolated context window.
How to install Audit Domain Runner
Installs to ~/.claude/agents/wolverin0-clawtrol-audit-domain-runner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/wolverin0/clawtrol/HEAD/.claude/agents/audit-domain-runner.md -o ~/.claude/agents/wolverin0-clawtrol-audit-domain-runner.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Domain Runner does
name: audit-domain-runner description: Execute a single domain audit (one of the 13 audit-domain-* skills) in an isolated context window. Spawned by audit-runner once per domain. Loads the domain skill + audit rules, runs against the audit scope, returns a ~2K-token findings report. Generic — works for any of the 13 domains. tools: Read, Grep, Glob, Bash model: opus
You are a domain auditor running in a focused context window. The audit-runner spawned you to handle exactly one domain. B
Alternatives in Security
- Security Verifier — You write and execute PoC tests to PROVE bugs exist 215 ★
- Release Auditor — Pre-release audit for a single plugin in the monorepo — takes a plugin slug and cross-references plugin.json v 72 ★
- Blue Team — Defensive security and hardening specialist 72 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Multi Perspective Reviewer
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage
Prism
Parallel bias-isolated review with 4 specialized single-domain reviewers (security, performance, test coverage
Electron Architect
Use this agent for Electron main process work, IPC handler design, preload bridge changes, window management,
Mauro Context Verifier
Adversarially verifies Mauro knowledge candidates against code, tests, human decisions, scope, and security ru
Cortex Auditor
Read-only vault auditor for the Cortex second-brain. Dispatched by the /cortex-audit ritual to scan the WHOLE
Finding Chain Synthesizer
Chains confirmed audit findings into multi-step, cross-domain exploit candidates and searches for a unique eme
Related Skills
Claude Code Practices
Interactive AI installer for Claude Code: setup once, keep context across sessions, enforce critical rules wit
Tails Verdict
The quality stage. Runs the single gate, then the one isolated review, once. Use when a build is finished, nev
Spec Template
Template for a project's own spec skill — definition, domains, states and transitions, cross-domain rules, flo