Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/spruikco/fat-agent-skillnpx agentmods add skills/spruikco/fat-agent-skill/fat-agentWrote 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.
[](https://agentmods.dev/skills/spruikco/fat-agent-skill/fat-agent)<a href="https://agentmods.dev/skills/spruikco/fat-agent-skill/fat-agent"><img src="https://agentmods.dev/badge/skills/spruikco/fat-agent-skill/fat-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/spruikco/fat-agent-skill/fat-agent"><img src="https://agentmods.dev/badge/skills/spruikco/fat-agent-skill/fat-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00164 | $0.30401 |
| Opus 5.5 | $0.00066 | $0.12160 |
| Sonnet 5.5 | $0.00033 | $0.06080 |
| Haiku 4.5 | $0.00016 | $0.03040 |
Grade C, and why
fat-agent scanned grade C with 3 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`.aws/credentials`) are **P0 — rotate and remove immediately**; source-control Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://ctx.rs/install | sh # macOS / Linux Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Save the **raw server response** (the shell): `curl -sL <url> -o served.html` How it starts
The opening of the file, as written. The whole thing — 2,270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FAT Agent with Superpowers — Fix, Audit, Test
A post-launch quality assurance agent that performs a comprehensive, modular audit of deployed websites and guides users through fixing every issue found.
FAT stands for Fix -> Audit -> Test — the three phases the agent cycles through until the site scores clean.
Philosophy
Most post-launch issues fall into predictable categories. Rather than relying on the user to know what to check, FAT Agent with Superpowers takes the lead — it asks targeted questions, auto-detects which modules are relevant, runs automated checks where possible, and builds a prioritised punch list. Think of it as a seasoned QA engineer sitting beside you after every deploy.
When to Trigger
Activate FAT Agent with Superpowers when:
- A user says "run FAT agent", "audit my site", "post-launch check", etc.
- A deploy just succeeded (on any hosting platform) and the user asks "is it good?" or similar
- The user pastes a URL and asks Claude to "check it" or "review it"
- After any deploy, if the user hasn't mentioned running QA
Phase 0 — Gather Context & Module Detection
Before auditing anything, FAT Agent with Superpowers needs to understand the project and determine which audit modules to run.
Step 1: Collect Project Details
Ask the user for the following (skip anything already known from conversation context or memory):
Required
- Live URL — The production URL to audit (e.g.,
https://example.com)
That's the only thing FAT Agent needs. Everything below is helpful but optional — if the user doesn't know or doesn't have the codebase, infer what you can from the live response and proceed (see Remote / From-Afar Mode below).
Helpful (optional — auto-detected when not provided)
- Site type — marketing site, SaaS app, e-commerce, blog, portfolio, landing page, web app, local business. Infer from the page: product schema/cart → e-commerce; LocalBusiness/NAP → local business;
<article>/blog paths → blog. - Tech stack — Framework/CMS. Infer from response headers (
Server,X-Powered-By,X-Generator),<meta name="generator">, cookies (e.g.wordpress_*), and asset paths (/_next/,/_nuxt/, Vite/assets/index-*.js,/wp-content/). - Hosting platform — Infer from headers (
Server,Via,X-Vercel-*,CF-Ray/Server: cloudflare,X-Served-ByFastly/Netlify,X-Amz-*). Used only to tailor config-format fixes; when unknown, give stack-agnostic fixes (the HTML/JSON-LD/header to add).
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.
- 8d ago Changed · +57 lines 456cd37361af
- 17d ago Changed · +49 lines 7f41e5fbaaca
- 28d ago Changed · +14 lines 24d0ed23568c
- 1mo ago Changed · +298 lines ed729e3badfc
- 2mo ago First seen · 1,852 lines · 164 tokens per session scan C 3eca4bb42860
fat-agent is a skill published in the GitHub repository spruikco/fat-agent-skill (40 stars, last pushed 7d ago), licensed MIT. It adds 164 tokens to every session and 30,401 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it C with 3 findings (reaches for credential files, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
fat-agent compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fat-agentspruikco/fat-agent-skill | Skill | 40 | 7d ago | MIT | C | 164 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 57k | 29d ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| test-warp-uiwarpdotdev/warp | Skill | 66k | yesterday | AGPL-3.0 | A | 55 | Claude Code |