agent-audit

agent-audit is a command for coding agents from phazurlabs/install-labs. It costs 15 tokens per session (3,511 once invoked), scanned A, original, Apache-2.0.

A readiness review for an AI agent or automation before packaging it for distribution.

In plain words
What is it for?
Use it to inspect a local project, repository, or description and assess whether its files, entry points, dependencies, configuration, and README are ready to package.
Why use it?
It identifies missing dependencies, configuration problems, structural issues, and documentation gaps that could make installation fail.

Command

Part of the install-labs plugin — 12 skills, 10 commands 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/phazurlabs/install-labs/agent-audit
Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs

Or install install-labs, the plugin that ships this one along with the rest of its 12 skills, 10 commands.

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 agent-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/phazurlabs/install-labs/agent-audit.svg)](https://agentmods.dev/commands/phazurlabs/install-labs/agent-audit)
Your own site
<a href="https://agentmods.dev/commands/phazurlabs/install-labs/agent-audit"><img src="https://agentmods.dev/badge/commands/phazurlabs/install-labs/agent-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,511 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 $0.00015 $0.03511
Opus 5 $0.00008 $0.01755
Sonnet 5 $0.00003 $0.00702
Haiku 4.5 $0.00002 $0.00351

Measured 4d ago against content hash ad19f38d019f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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.

commands/agent-audit.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/agent-audit — Packaging Readiness Audit

Purpose

Audit an AI agent or automation for packaging readiness BEFORE generating any packaging files. Identifies structural blockers, dependency gaps, configuration problems, and documentation holes that would cause install failures if shipped as-is.


Protocol

When the user invokes /agent-audit, follow this process exactly:

Step 1: Identify the Agent to Audit

Ask the user to point to their agent. Accept any of these:

  • A local directory path — Read the directory structure, key files (requirements.txt, package.json, pyproject.toml, Dockerfile, .env.example, README.md, entry point files), and infer the agent's architecture.
  • A GitHub repository URL — Clone or browse the repo to examine the same files.
  • A verbal description — If the user describes their agent without pointing to code, audit based on what they describe. Flag anything you cannot verify as "Unable to assess — no code provided."
  • Context from a prior /agent-guide conversation — If the user already ran /agent-guide in this session, use the assessment from that step. Do not re-ask questions already answered.

If examining code, look for these files to understand the agent:

File What It Tells You
requirements.txt / pyproject.toml / Pipfile Python dependencies, version pinning
package.json / package-lock.json Node.js dependencies, scripts, entry point
Dockerfile / docker-compose.yml Containerization strategy
.env / .env.example Configuration and secrets pattern
.gitignore Whether secrets and build artifacts are excluded
README.md Documentation quality
crew.yaml / agents.yaml / tasks.yaml CrewAI configuration
langgraph.json LangGraph configuration
main.py / app.py / index.ts / server.ts Entry point clarity
tests/ directory Test coverage
Makefile / justfile / taskfile.yml Task runner / build system

Read the full file on GitHub · 285 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 · 285 lines · 15 tokens per session scan A ad19f38d019f

Subscribe to this mod's changes

agent-audit is a command published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 3,511 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.