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 agentmods add instructions/fschifone/claude-setup-wizard/claude-mdgit clone --depth 1 https://github.com/fschifone/claude-setup-wizardWrote 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/instructions/fschifone/claude-setup-wizard/claude-md)<a href="https://agentmods.dev/instructions/fschifone/claude-setup-wizard/claude-md"><img src="https://agentmods.dev/badge/instructions/fschifone/claude-setup-wizard/claude-md.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 | $0.01449 | $0.01449 |
| Opus 5 | $0.00724 | $0.00724 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade E, and why
claude-setup-wizard CLAUDE.md scanned grade E 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **`permissions.allow` patterns are prefix-matched, not glob.** `Bash(curl * | sh:*)` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Use `rm -rf`, `sudo`, or any destructive command anywhere in this repo. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`permissions.allow` patterns are prefix-matched, not glob.** `Bash(curl * | sh:*)` How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Setup Wizard — contributor context
This repo IS a Claude Code plugin, AND uses its own output to configure the contributor experience. Eat your own dog food.
Stage: production · Team: open source · Primary chat language: English
What this project is
A Claude Code plugin distributed as a GitHub-hosted marketplace. Users install
it with /plugin marketplace add <this-repo> and then get /setup-wizard and
/audit available everywhere.
Stack
- Language: Bash (hooks, status line) + Markdown (skills, templates)
- No build step. Plain files, version-controlled.
- Dependencies at runtime:
jq(optional, all scripts have a fallback),git(optional, for status line branch display). - CI: GitHub Actions — validates JSON schema + bash syntax on every PR.
Commands
| Purpose | Command |
|---|---|
| Validate all files | ./scripts/validate.sh |
| Test a hook locally | echo '<json>' | bash templates/hooks/<n>.sh |
| Test status line | echo '<json>' | bash statusline/rich.sh |
| Lint shell scripts | shellcheck templates/hooks/*.sh statusline/*.sh |
Architecture
The repo is a marketplace with a single plugin.
claude-setup-wizard/ ← marketplace root
├── .claude-plugin/marketplace.json ← lists the plugin(s) below
└── plugins/setup-wizard/ ← one plugin
├── .claude-plugin/plugin.json ← plugin manifest
├── skills/ ← SKILL.md files (setup-wizard, audit, fix)
├── templates/hooks/ ← hook scripts copied to user projects
├── statusline/ ← bash scripts that read stdin JSON
└── templates/ ← placeholders filled by the wizard
The wizard itself is a single skill (skills/setup-wizard/SKILL.md)
that reads templates, asks questions, and writes files into the user's project.
No executable code runs at install time — Claude interprets the markdown
skill and orchestrates everything.
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.
- 5d ago First seen · 135 lines · 1,449 tokens per session scan E 3a52b9f756e3
claude-setup-wizard CLAUDE.md is an instructions file published in the GitHub repository fschifone/claude-setup-wizard (2 stars, last pushed 4mo ago), licensed MIT. It adds 1,449 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).