Matcha Auditor — Security agent for Claude Code
Stack audit. Finds overlaps, waste, security risks.
How to install Matcha Auditor
Installs to ~/.claude/agents/plumpslabs-matcha-matcha-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/plumpslabs/matcha/HEAD/.claude/agents/matcha-auditor.md -o ~/.claude/agents/plumpslabs-matcha-matcha-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Matcha Auditor does
name: matcha-auditor description: Stack audit. Finds overlaps, waste, security risks. Read-only. tools: Read, Grep, Glob, List, Bash disallowedTools: WebFetch, WebSearch, Task, Edit, Write permissionMode: default
Alternatives in Security
- Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
- Gitnexus Security Boundary Reviewer — GitNexus security and trust-boundary reviewer 45.8k ★
- Aegis — You are a specialized security agent 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cost Strategist
Use when a FinOps audit of vendor/cloud/AI spend is needed — vendor tally, waste by class, keep/kill/downgrade
Webhook Contract Auditor
Read-only audit of a webhook handler against its webhook-contract.json delivery contract. Finds side effects w
Matcha Reviewer
Review gate with risk-based routing. L0=output check, L1=lint, L2=full review, L3=expert+threat model. Blocks
Portfolio Manifest Collector
Read-only inventory collector dispatched by portfolio-audit: gathers each repo's project/portfolio.yml manifes
Tech Stack Drift Reviewer
Read-only audit of a repo's declared tech-stack manifest (project/portfolio.yml tech_stack: for members; portf
Dashclaw Security Reviewer
Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repos
Related Skills
Matcha:Audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems
Secure Code Auditor
Backend security Agent Skill that helps AI audit code, detect vulnerabilities, and generate secure-by-default
AI Agent Audit
Read-only audit of a local developer machine for AI-agent-related security risks (Linux + macOS). Ten modules