mags-setup

mags-setup is a skill for Claude Code, Codex from doancan/mags. It costs 20 tokens per session (1,026 once invoked), scanned A, original, MIT.

A setup-analysis skill for Claude Code projects. It examines a project's files and dependencies, then recommends useful skills, hooks, and instruction files.

In plain words
What is it for?
Detecting project technologies, reviewing configuration, and recommending a tailored Claude Code setup and workflow.
Why use it?
It reduces the guesswork involved in configuring an AI coding workflow for a particular programming language, framework, and set of tools.

Skill for Claude CodeCodex

Part of the mags plugin — 17 skills, 2 agents 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 skills/doancan/mags/mags-setup
Any agent
npx skills add doancan/mags --skill mags-setup
Clone the repo
git clone --depth 1 https://github.com/doancan/mags

Made for: Claude Code, Codex.

Or install mags, the plugin that ships this one along with the rest of its 17 skills, 2 agents.

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 mags-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/doancan/mags/mags-setup.svg)](https://agentmods.dev/skills/doancan/mags/mags-setup)
Your own site
<a href="https://agentmods.dev/skills/doancan/mags/mags-setup"><img src="https://agentmods.dev/badge/skills/doancan/mags/mags-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,026 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 $0.00020 $0.01026
Opus 5 $0.00010 $0.00513
Sonnet 5 $0.00004 $0.00205
Haiku 4.5 $0.00002 $0.00103

Measured 4d ago against content hash 0abd6cdb6916, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mags-setup 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.

skills/mags-setup/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAGS Setup

Analyze the current project and recommend an optimal setup for Claude Code workflows.

Steps

1. Analyze project

Gather project signals in parallel:

  • Read .mags/config.yaml to check for a locale field. If present, use this locale value when calling mags_create_doc and mags_scaffold_module throughout this flow.
  • Call mags_project_summary for overall context.
  • Use Glob to detect project type:
    • package.json — Node/JS project
    • Cargo.toml — Rust project
    • go.mod — Go project
    • pyproject.toml or requirements.txt — Python project
    • pom.xml or build.gradle — Java project
    • *.sln or *.csproj — .NET project
  • Use Glob to detect frameworks and tools:
    • next.config.* — Next.js
    • nest-cli.json or src/main.ts with NestJS imports — NestJS
    • prisma/schema.prisma — Prisma ORM
    • docker-compose.* — Docker
    • .github/workflows/ — GitHub Actions CI
    • tailwind.config.* — Tailwind CSS
  • Read package.json or equivalent manifest for dependencies.

2. Recommend skills and agents

Based on the detected stack, recommend Claude Code slash commands and workflows. Present as a checklist:

== Recommended Setup for <project name> ==

Detected: <framework> + <language> + <key tools>

SKILLS (slash commands to install)
  [x] /commit        — You have this (from MAGS)
  [ ] /review-pr     — PR review automation
  [ ] /test          — Test generation for <framework>
  [ ] /deploy        — Deploy workflow for <detected CI>

HOOKS (automation triggers)
  [ ] pre-commit     — Lint + typecheck before commit
  [ ] post-save      — Auto-format on save
  [ ] pre-push       — Run tests before push

MCP SERVERS
  [ ] mags           — Already active
  [ ] <db tool>      — Database introspection for <detected DB>
  [ ] <api tool>     — API testing for <detected framework>

Mark items already present with [x]. Only recommend what makes sense for the detected stack.

3. Audit CLAUDE.md

Call mags_audit_claude_md to check the current CLAUDE.md (if it exists) against the project's actual state.

Read the full file on GitHub · 111 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 · 111 lines · 20 tokens per session scan A 0abd6cdb6916

Subscribe to this mod's changes

mags-setup is a skill published in the GitHub repository doancan/mags (3 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 1,026 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.

Related

Other skills, from other repositories

video-perception

Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.

jordanrendric/claude-video-vision · 51 tokens

portable-text-serialization

Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…

sanity-io/agent-toolkit · 85 tokens

sanity-best-practices

Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…

sanity-io/agent-toolkit · 164 tokens

prior-art-search

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.

RobThePCGuy/Claude-Patent-Creator · 26 tokens

bigquery-patent-search

Fast, cloud-based patent searching across 100 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval.

RobThePCGuy/Claude-Patent-Creator · 34 tokens

development-assistant

Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.

RobThePCGuy/Claude-Patent-Creator · 24 tokens