setup

A command that bootstraps a repository with AI-oriented continuous integration, Git hooks, templates, and maintenance checks. It adds protections and working conventions for projects written in any language, with extra workflows for Python and TypeScript/Node.js.

In plain words
What is it for?
Use it when starting a project, adding CI and hooks to an existing one, or filling gaps found by AgentLint. It can install security scans, test gates, commit checks, templates, and helper scripts.
Why use it?
It saves time when a repository is missing consistent checks for secrets, dependencies, tests, commits, and pull requests. It also provides shared files for planning, testing, handoffs, and change tracking.

Command

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/0xmariowu/agentlint/setup
Clone the repo
git clone --depth 1 https://github.com/0xmariowu/AgentLint
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 522 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 $0.00000 $0.00522
Opus 5 $0.00000 $0.00261
Sonnet 5 $0.00000 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured 2d ago against content hash 49f24ae38e28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/setup.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentLint Setup

Bootstrap a repository with AI-native CI/CD, hooks, and templates in one command.

When to use

  • Starting a new project and want the full AI-native development stack
  • Adding CI/CD and hooks to an existing project
  • After agentlint check shows missing workflows or hooks

What gets installed

Universal CI workflows (all languages): gitleaks · semgrep · trivy · test-required (blocking) · pr-lint · release · author-email · commit-message-scan · hygiene · stale · workflow-sanity · lock

Language-specific workflows (Python / TypeScript / Node): CI matrix · CodeQL · labeler · autofix

Git hooks:

  • Pre-commit: author identity (noreply email) + PII scan + secrets detection + staged-file lint
  • Pre-push: rebase on main before push
  • Commit-msg: conventional commits enforcement

Templates:

  • CLAUDE.md with Local test section, Session Checklist, Harness architecture
  • plan.md atomic task format
  • tests/compliance_check.sh (SECURITY.md / gitleaks / git email / paths)
  • HANDOFF.md, CHANGELOG.md

Scripts:

  • scripts/committer — atomic commit wrapper (prevents git add .)
  • scripts/check-deps.sh — dependency checker

Usage

# Bootstrap a Python project
agentlint setup --lang python ~/Projects/my-repo

# Bootstrap a TypeScript project (public repo)
agentlint setup --lang ts --visibility public ~/Projects/my-repo

# Add only workflows to existing project
agentlint setup --lang python --workflows-only ~/Projects/my-repo

Non-git directories are refused by default. Use --init-git only when the user explicitly wants setup to initialize the target as a git repo.

The auto-fix workflow that commits and pushes formatting changes is not installed by default. Use --with-auto-push only after the user opts in.

Steps

  1. Detect language from args (--lang ts|python|node)
  2. Run bash ${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh --lang <lang> [options] <path>
  3. Report what was installed
  4. Suggest next steps: pre-commit install, first commit, agentlint check

Read the full file on GitHub · 63 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 · 63 lines · 0 tokens per session scan A 49f24ae38e28

Subscribe to this mod's changes

setup is a command published in the GitHub repository 0xmariowu/AgentLint (53 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 tokens. 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 2026-08-30.