OrodruinLabs

Self Audit — Security agent for Claude Code

Security community

Post-loop, proposes-only self-audit — mines objective cost/perf/correctness signals via ${CLAUDE_PLUGIN_ROOT}/scripts/self-audit.sh and appends structured findings to the main worktree's improvements.

How to install Self Audit

Installs to ~/.claude/agents/orodruinlabs-nazgul-self-audit.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/OrodruinLabs/nazgul/HEAD/agents/self-audit.md -o ~/.claude/agents/orodruinlabs-nazgul-self-audit.md

Restart Claude Code, or start a new session, for it to be picked up.

What Self Audit does

name: nazgul:self-audit description: Post-loop, proposes-only self-audit — mines objective cost/perf/correctness signals via ${CLAUDE_PLUGIN_ROOT}/scripts/self-audit.sh and appends structured findings to the main worktree's improvements backlog. Never edits code or approves anything; writes only its own completion marker. tools:

  • Read
  • Glob
  • Grep
  • Bash maxTurns: 15 model: sonnet

Self-Audit

You are a proposes-only, non-blocking post-loop gate. You mine cost/perf/correctnes

Alternatives in Security

  • Retool Endpoint Audit — Checks a migration slice against the main app's API surface — whether a local implementation duplicates an exi 7.2k ★
  • Perf Deep Audit — Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f 358 ★
  • Electron Ipc Engineer — Use this agent for any change that touches Electron IPC — adding/removing channels, modifying main.ts ↔ preloa 204 ★

Full documentation available on GitHub

View Source Repository

Related Agents

Analysis Orchestrator — Security agent for Claude Code

Analysis Orchestrator

Use when the root orchestrator needs a read-only codebase audit — selects a subset of its 6 lenses by objectiv

Security community
Tripwire Author — Security agent for Claude Code

Tripwire Author

Use when an audit finding or post-mortem identifies a class of bug that should be caught by CI. Authors a Semg

Security community
Commit Archaeologist — Security agent for Claude Code

Commit Archaeologist

Phase 1 intelligence gathering agent that proactively mines git history for security-relevant commits with no

Security community
GitHub Actions Auditor — Security agent for Claude Code

GitHub Actions Auditor

Use this agent when you need to review GitHub Actions workflow files for issues, errors, inconsistencies, or p

Security community
Docker Sandbox — Security agent for Claude Code

Docker Sandbox

Isolated autonomous scanning agent — runs in a temporary worktree with restricted Bash access. Requires ROE au

Security community
Worktree Agent Security — Security agent for Claude Code

Worktree Agent Security

Implementer agent specialized in security/hardening, working in ITS OWN git worktree. Launched by the orchestr

Security community

Related Skills

Audit Implementation — Security skill for Claude Code

Audit Implementation

POST-IMPLEMENTATION AUDIT — analyzes what the implementing agent did wrong and why, proposes specific changes

Security community
Review Wave — Security skill for Claude Code

Review Wave

4 specialized reviewers examine changes simultaneously — security, perf, correctness, style

Security community
Dsh Auto Evolve — AI skill for Claude Code

Dsh Auto Evolve

A self-evolving plugin for DeepSeek Harness (dsh). It observes how the agent runs, proposes improvements to it

AI community