fat-audit

fat-audit is a command for Claude Code from spruikco/fat-agent-skill. It costs 31 tokens per session (443 once invoked), scanned A, original, MIT.

A command for running a FAT Agent audit on a deployed website. FAT means Fix, Audit, Test, and the audit checks areas such as search visibility, security, accessibility, speed, content, and analytics.

In plain words
What is it for?
Use it to gather site details, inspect a live URL, create a prioritized report, and recheck the site after fixes.
Why use it?
It gives a repeatable way to find and prioritize post-launch website problems instead of checking them manually one by one.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the fat-agent plugin — 1 skill, 1 command shipped together

Good fit Use it to gather site details, inspect a live URL, create a prioritized report, and recheck the site after fixes.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add spruikco/fat-agent-skill
Claude Code
/plugin install fat-agent

Made for: Claude Code.

Or install fat-agent, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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 fat-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/spruikco/fat-agent-skill/fat-audit.svg)](https://agentmods.dev/commands/spruikco/fat-agent-skill/fat-audit)
Your own site
<a href="https://agentmods.dev/commands/spruikco/fat-agent-skill/fat-audit"><img src="https://agentmods.dev/badge/commands/spruikco/fat-agent-skill/fat-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00443
Opus 5 $0.00015 $0.00221
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured 8d ago against content hash 76109340753b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fat-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 8d 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.

plugins/fat-agent/commands/fat-audit.md · 39 lines

What it actually says

/fat-audit — Run a FAT Agent Audit

You have been asked to run a FAT Agent (Fix, Audit, Test) audit.

Setup

  1. Bootstrap dependencies (runs once, skips if already installed):
    cd ${CLAUDE_PLUGIN_ROOT} && (command -v uv >/dev/null 2>&1 && uv pip install -q -r pyproject.toml 2>/dev/null || pip install -q matplotlib python-docx python-pptx Pillow 2>/dev/null) && echo "deps ready"
    
  2. Load the FAT Agent skill instructions from ${CLAUDE_PLUGIN_ROOT}/skills/fat-agent/SKILL.md
  3. If a URL argument was provided, use it as the live URL and skip that question in Phase 0

Workflow

Follow the full FAT Agent workflow:

  1. Phase 0 — Gather Context — Ask for any missing details (site type, tech stack, hosting platform). If the URL was provided as an argument, skip the URL question.
  2. Phase 1 — Audit — Run all check categories against the live URL. Use the analysis scripts at ${CLAUDE_PLUGIN_ROOT}/scripts/ and reference files at ${CLAUDE_PLUGIN_ROOT}/references/ as needed.
  3. Phase 2 — Fix — Generate the prioritised FAT Report and offer to fix issues.
  4. Phase 3 — Test — After fixes are deployed, re-verify and generate the final scorecard and badge.

Scripts

  • ${CLAUDE_PLUGIN_ROOT}/scripts/analyse-html.py — HTML analysis helper
  • ${CLAUDE_PLUGIN_ROOT}/scripts/calculate-score.py — Scoring calculator
  • ${CLAUDE_PLUGIN_ROOT}/scripts/generate-badge.py — SVG badge generator
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. 8d ago First seen · 39 lines · 31 tokens per session scan A 76109340753b

Subscribe to this mod's changes

fat-audit is a command published in the GitHub repository spruikco/fat-agent-skill (38 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 443 once invoked, about $0.0002 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 2026-08-30.