Module Audit — Security skill for Claude Code
Pre-ship module audit pipeline (rev 4).
How to install Module Audit
Installs to ~/.claude/skills/fire-farmer-red-line-toolkit-module-audit/SKILL.md
mkdir -p ~/.claude/skills/fire-farmer-red-line-toolkit-module-audit && curl -fsSL https://raw.githubusercontent.com/fire-farmer/red-line-toolkit/HEAD/commands/module-audit.md -o ~/.claude/skills/fire-farmer-red-line-toolkit-module-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Module Audit does
description: Pre-ship module audit pipeline (rev 4). 7-stage matrix audit covering form components × 4 lenses + 10 cross-cutting axes + adversarial layer + SHA-anchored verification. Recon freezes one AUDIT_SHA; the Stage 4.5 verifier checks findings against that commit via git show (not HEAD) to catch snapshot incoherence. Use ONLY for module-completion sweeps with ≥3 form components. For single-page work use /page-design or /page-code; for changes meeting the project's Heavy-rigor trigger
Alternatives in Security
- Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
- Release Audit — Use right before cutting a release — it spawns ONE fresh sibling session via CCC that audits only the JUDGMENT 130 ★
- Audit Claude Components — Comprehensive audit of .claude folder 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
UI Iteration
Full-Spectrum Test Verification: Autonomous test execution covering unit tests, integration, combination matri
Exploit Confirm
Prove a SUSPECTED finding with one targeted, SOC-stealth, operator-supervised confirmation probe (confirm_ too
LaptopAI Agent
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local
Fan Out Audit
Fan-out audit: spawn one agent per small file batch, each writing structured findings to its own file. Three p
Sota Deep Audit
The heavy audit — a hostile review of a whole repository by someone who will inherit it: the threat model reco
Auth Flows
Read-only audit of app-layer auth — route×gate matrix, getSession vs getUser, middleware-as-only-gate
Related Agents
Brahe
Read-only recon agent producing evidence packets instead of prose tours. Maps how a system works, traces a sym
AI Verify
Evidence-first verification orchestrator. Dispatches specialist agents via the Agent tool: 1 deterministic age
Brigade Recon
Proactively maps repositories and gathers evidence before designs cross-cutting or high-risk changes.
