auto-setup

A project inspection command that identifies the programming languages, package tools, and available lint, type-check, and test commands. It proposes additions to CLAUDE.md, a file of project instructions, and settings.json without applying them.

In plain words
What is it for?
Use it when setting up coding-agent instructions for Node.js, Python, Rust, Go, JVM, or mixed projects such as a monorepo.
Why use it?
It removes the need to manually discover how a project should be checked and avoids guessing command names from the toolchain.

Command for Claude Code

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 commands/hautc-it/cil/auto-setup
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 780 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 $0.00044 $0.00780
Opus 5 $0.00022 $0.00390
Sonnet 5 $0.00009 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 2d ago against content hash 6bd073ddf97f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-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 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.

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.

.claude/commands/auto-setup.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/auto-setup

Inspect the current project and propose configuration additions for the detected toolchain. Apply nothing without user approval at the end.

Step 1 — Detect

Check for these manifests in the project root and immediate subdirectories:

  • package.json → Node.js / TypeScript
  • pyproject.toml, setup.py, requirements.txt, Pipfile → Python
  • Cargo.toml → Rust
  • go.mod → Go
  • pom.xml, build.gradle → JVM
  • Multiple of the above → Monorepo / mixed

For each detected stack, identify:

  • Package manager (npm/pnpm/yarn/poetry/pip/cargo/go/etc.)
  • Lint command (e.g. npm run lint, ruff check, cargo clippy, golangci-lint run)
  • Typecheck command (e.g. tsc --noEmit, mypy, none for Rust/Go which check at build)
  • Test command (e.g. npm test, pytest, cargo test, go test ./...)

Read the actual scripts from package.json / pyproject.toml / etc. — don't assume names exist.

Step 2 — Propose CLAUDE.md additions

Show a diff block of what should be appended to the project's CLAUDE.md under a ## Project Toolchain heading:

## Project Toolchain

- **Stack:** <detected>
- **Lint:** `<command>`
- **Typecheck:** `<command>` (or "n/a — checked at build")
- **Test:** `<command>`
- **Run before commit:** `<lint && typecheck && test>`

Step 3 — Propose settings.json additions

If the project has .claude/settings.json, show a diff block adding permissions.allow entries for the detected commands so they don't prompt every time:

{
  "permissions": {
    "allow": [
      "Bash(<lint command>)",
      "Bash(<typecheck command>)",
      "Bash(<test command>)"
    ]
  }
}

Step 4 — Present and wait for approval

Output a single message containing:

  1. Detected: the stack(s) found and where (paths to manifests).
  2. Proposed CLAUDE.md addition: the markdown diff block from Step 2.
  3. Proposed settings.json addition: the JSON diff block from Step 3.
  4. Verification commands to run after applying (e.g. <lint command> should exit 0 on a clean tree).
  5. Ask: "Apply both changes? (yes / only CLAUDE.md / only settings.json / no)"

Read the full file on GitHub · 76 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. 2d ago First seen · 76 lines · 44 tokens per session scan A 6bd073ddf97f

Subscribe to this mod's changes

auto-setup is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 780 once invoked, about $0.0002 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.