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.svg" alt="Measured on agentmods" 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 | $0.22926 |
| Opus 5 | $0.00082 | $0.11463 |
| Sonnet 5 | $0.00033 | $0.04585 |
| Haiku 4.5 | $0.00016 | $0.02293 |
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 — 1,852 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 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 (38 stars, last pushed 21d ago), licensed MIT. It adds 164 tokens to every session and 22,926 once invoked, about $0.0008 per session on Opus 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.
Other skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…