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.
npx skills add MadAppGang/magus --skill setupgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/setup)<a href="https://agentmods.dev/skills/madappgang/magus/setup"><img src="https://agentmods.dev/badge/skills/madappgang/magus/setup/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/madappgang/magus/setup"><img src="https://agentmods.dev/badge/skills/madappgang/magus/setup.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 | $0.00050 | $0.03812 |
| Opus 5.5 | $0.00020 | $0.01525 |
| Sonnet 5.5 | $0.00010 | $0.00762 |
| Haiku 4.5 | $0.00005 | $0.00381 |
Grade B, and why
setup scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `user` | `~/.claude/settings.json` | every project on this machine | How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up code-search
Goal: the project ends in a state the user chose, and they know whether to restart.
| End state | Meaning |
|---|---|
| ready | an engine is installed, configured and indexed, and verify passed |
| none | no engine, by choice; code_search stays but says so, and Grep, Glob and Read work as they come |
| dismissed | "ignore for this project"; nothing prompts again until /code-search:setup is run |
Done when the step 10 report is printed.
Every change goes through the setup CLI. Never edit a settings file or type an install command yourself. The CLI refuses the unsafe cases a hand edit walks into: a malformed settings file, a value another settings layer overrides.
Setup installs nothing for ripgrep and never sets USE_BUILTIN_RIPGREP. The one ripgrep
change it can make is removing the rg shim code-search 8.1 shipped, and only when the user
says yes (step 8).
Names used below
<root>: the plugin root, two directories above this file (this file is<root>/skills/setup/SKILL.md). Use the absolute path you read it from.<project>: the project root, the directory this Claude Code session was started in.<cli>:bun --env-file=/dev/null --config=/dev/null "<root>/scripts/setup.ts"
Every CLI call passes --project "<project>". Steps that say --json read the fields they
name. Exit codes: 0 done, 1 failed or refused, 2 usage error or nothing measured.
On exit 1: show the user failure.message and failure.remedy verbatim, plus, for a
process failure, failure.process (command, exit code or signal, stderr tail). Stop that
step. Do not retry with other flags, work around a refusal, or run a remedy without asking.
How to ask
- Explain first, then ask. Before every AskUserQuestion, say in text what is being decided, what each option does, and what it costs. The widget is not the explanation.
- One decision per question, with the options the step names.
- A step with nothing to decide (already installed, already indexed) gets one line in the conversation and no question.
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.
- 2d ago Changed · +44 lines 4ea8c9c04301
- 14d ago First seen · 262 lines · 50 tokens per session scan B 2bb5762c40fa
setup is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 3,812 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…