ai-kit CLAUDE.md

ai-kit CLAUDE.md is an instructions file for coding agents from smicolon/ai-kit. It costs 6,131 tokens per session, scanned A, original, MIT.

A project-specific instruction file for Claude Code, an AI coding assistant. It explains the ai-kit repository, its purpose, development environment, layout, and common scripts.

In plain words
What is it for?
Helping Claude Code navigate ai-kit, use its scripts, and make repository changes with the right context.
Why use it?
It gives the assistant the project background and working conventions it would otherwise need to discover.

Instructions file

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 instructions/smicolon/ai-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/smicolon/ai-kit

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 ai-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/smicolon/ai-kit/claude-md.svg)](https://agentmods.dev/instructions/smicolon/ai-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/smicolon/ai-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/smicolon/ai-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,131 This file is loaded in full into every session.
When invoked 6,131 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.06131 $0.06131
Opus 5 $0.03066 $0.03066
Sonnet 5 $0.01226 $0.01226
Haiku 4.5 $0.00613 $0.00613

Measured today against content hash 4393839d3da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-kit CLAUDE.md 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 today.

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.md · 628 lines

How it starts

The opening of the file, as written. The whole thing — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Purpose

This repository is an open-source toolkit maintained by Smicolon that ships convention packs (agents, skills, commands, hooks, rules) for popular stacks (Django, NestJS, Next.js, Nuxt.js, Hono, TanStack Router, Better Auth, Flutter, system architecture, dev loops, and more). Each pack bundles best-practice defaults teams can adopt or override.

It can be consumed in two ways:

  1. As a Claude Code marketplace/plugin marketplace add github.com/smicolon/ai-kit then /plugin install <pack>. Picks up updates through Claude Code's plugin system.
  2. As a standalone CLI (@smicolon/ai-kit)bunx @smicolon/ai-kit add <pack> (or via npm/Homebrew binary) installs packs per-project into .claude/, .cursor/, .windsurf/, .codex/, etc. Works with any AI coding tool listed in packages/cli/src/tools.ts, not just Claude Code. Per-project state lives in .ai-kit.json.

Both consumption paths read the same source of truth: .claude-plugin/marketplace.json and the pack contents in packs/.

Development Environment

Notes for any AI agent (Claude Code, Cursor Cloud, Codex, etc.) working in this repo. The same content is exposed as AGENTS.md (symlink to this file) so tools that look for AGENTS.md see it too.

Repo shape

  • Bun workspaces + Turborepo monorepo. Bun is the only supported package manager — do not use npm, yarn, or pnpm. The lockfile is bun.lock.
  • packages/cli/ is the only buildable package: a TypeScript CLI (@smicolon/ai-kit) built with tsup, ESM-only ("type": "module"), targeting Node 22+. Do not introduce CommonJS patterns.
  • packs/ holds convention packs as Markdown (agents, skills, commands, rules, hooks). They are consumed by AI coding tools, not executed directly — editing them only requires Markdown.

Common scripts

Task Command
Install deps bun install
Typecheck CLI bun run --filter @smicolon/ai-kit typecheck
Build CLI bun run --filter @smicolon/ai-kit build
Watch / dev mode bun run --filter @smicolon/ai-kit dev
Smoke-test built CLI node packages/cli/dist/index.js --help
Validate marketplace claude plugin validate .

Read the full file on GitHub · 628 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. today Changed · +55 lines · +941 tokens per session 4393839d3da3
  2. 4d ago First seen · 573 lines · 5,190 tokens per session scan A 06cc58070e14

Subscribe to this mod's changes

ai-kit CLAUDE.md is an instructions file published in the GitHub repository smicolon/ai-kit (6 stars, last pushed today), licensed MIT. It adds 6,131 tokens to every session, about $0.0307 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.