Audit Init — Security skill for Claude Code
Scaffold dual-AI audit-handoff infrastructure for a project - out-of-repo audit gate + protocol and in-repo 5-lens self-audit.
How to install Audit Init
Installs to ~/.claude/skills/scottconverse-agent-pipeline-codex-audit-init/SKILL.md
mkdir -p ~/.claude/skills/scottconverse-agent-pipeline-codex-audit-init && curl -fsSL https://raw.githubusercontent.com/scottconverse/agent-pipeline-codex/HEAD/commands/audit-init.md -o ~/.claude/skills/scottconverse-agent-pipeline-codex-audit-init/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Init does
description: Scaffold dual-AI audit-handoff infrastructure for a project - out-of-repo audit gate + protocol and in-repo 5-lens self-audit. For projects where one AI implements and a different AI audits. argument-hint: (none - interactive)
audit-init - scaffold dual-AI audit infrastructure
You are setting up the audit-handoff discipline for a project that uses two AI systems: one implements, the other audits. This complements `pipeline-init`'s execution-side discipline (research -> p
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Code Review Intense Flow
Heavy code review - fans out to all applicable specialized reviewers (security, frontend, seo, geo, playwright
Adversarial Audit Engine
Cross-model audit engine for documents and technical artifacts: hallucination gate on verbatim quotes, claim v
Audit History
Pull past public audits (Code4rena, Sherlock, Spearbit, etc.) for a deployed contract or known protocol.
Rule Autopsy
Audits a CLAUDE.md or rules folder and reports how many blocks claim an effect without a reproducible receipt,
LLM Lens
Audit your Claude CLI history. Visualize, browse, edit -- all with one command, all local, no auth
Audit Strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Agg
Related Agents
Disc Reviewer Boundary
The boundary lens of the stage-1 discovery review — audits the In/Out fence and reports everything left in lim
Evidence Basis
Probe lens 3 of 6. Audits every claim for its source, flags the unsourced and the self-contradicting, and name
Feature Implementer
Implement a ReviewFlow feature via TDD inside-out. Receives a validated plan (docs/plans/ .plan.md) and spec (