matcha:audit

matcha:audit is a command for Codex from plumpslabs/matcha. It costs 17 tokens per session (959 once invoked), scanned A, original, MIT.

A command that checks a software project's dependencies, services, configuration, security posture, and architecture. It looks for duplicate tools, unused packages, and outdated or unnecessary setup.

In plain words
What is it for?
Use it to review package manifests, Docker files, environment examples, build files, and tool settings for overlap, waste, and dead configuration.
Why use it?
It helps reveal technical clutter and risks before they cause conflicts, maintenance work, or security problems.

Command for Codex

Part of the matcha plugin — 1 skill, 7 commands, 6 agents, 3 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/plumpslabs/matcha/matcha-audit
Clone the repo
git clone --depth 1 https://github.com/plumpslabs/matcha

Made for: Codex.

Or install matcha, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 6 agents, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for matcha:audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-audit.svg)](https://agentmods.dev/commands/plumpslabs/matcha/matcha-audit)
Your own site
<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-audit"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00959
Opus 5 $0.00009 $0.00479
Sonnet 5 $0.00003 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 4d ago against content hash cd3341a023d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

matcha:audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/commands/matcha:audit.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/matcha:audit

Stack health check. Find overlaps, waste, and risks before they become problems.

Scope

Audit covers: dependencies, services, config, security posture, and architecture health.

Process

Step 1 — Inventory

Scan all manifests and config:

  • package.json, go.mod, Cargo.toml, pyproject.toml, requirements.txt
  • docker-compose*.yml, Dockerfile*
  • .env.example, .env.sample
  • Makefile, justfile
  • tsconfig.json, .eslintrc*, prettier*

For each: what does it actually do? Not just "it exists."

Step 2 — Overlap Detection

Check How
Duplicate functionality Two deps doing the same thing? (e.g., moment + dayjs, lodash + native)
Redundant services Two containers/services handling same concern?
Conflicting configs ESLint + Prettier fighting? Multiple linters?
Dead dependencies Installed but never imported/used?

Step 3 — Waste Detection

Check How
Unused deps Check dependency list vs actual imports. Grep for usage.
Over-abstracted code Abstractions used <2 times. Inline them.
Dead config Config files for tools not installed.
Stale migrations DB migrations that are backward-compatible but still present.

Step 4 — Security Posture

Check How
Known vulnerabilities Run package manager audit (npm audit, pip audit, cargo audit, etc.)
Outdated deps Major versions behind? Security patches missing?
Secret exposure .env in git? Secrets in config files?
Missing security deps No rate limiting? No input validation library?

Step 5 — Architecture Health

Check How
Circular deps Module A → B → A. Break the cycle.
God modules Single file doing too much. Split.
Inconsistent patterns Mixed error handling, mixed logging, mixed auth.
Missing abstractions Same boilerplate in 3+ places. Extract.

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 111 lines · 17 tokens per session scan A cd3341a023d6

Subscribe to this mod's changes

matcha:audit is a command published in the GitHub repository plumpslabs/matcha (1 stars, last pushed 24d ago), licensed MIT. It adds 17 tokens to every session and 959 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.