claude-code-toolkit: Instructions file for Claude Code

CLAUDE.md

claude-code-toolkit CLAUDE.md is an instructions file for Claude Code from sergei-aronsen/claude-code-toolkit. It costs 8,644 tokens per session, scanned D, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, covering a documentation and template project. They describe the project and the checks that code changes must pass.

In plain words
What is it for?
Use them to understand the repository, run all checks with `make check`, or run separate shell, Markdown, and template checks.
Why use it?
They give the assistant and contributors shared rules for keeping Markdown, shell scripts, and templates consistent and valid.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is sergei-aronsen/claude-code-toolkit's own configuration. It tells Claude Code how to work on claude-code-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sergei-aronsen/claude-code-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sergei-aronsen/claude-code-toolkit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

Made for: Claude Code.

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 claude-code-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sergei-aronsen/claude-code-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/sergei-aronsen/claude-code-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sergei-aronsen/claude-code-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/sergei-aronsen/claude-code-toolkit/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-code-toolkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sergei-aronsen/claude-code-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/sergei-aronsen/claude-code-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,644 This file is loaded in full into every session.
When invoked 8,644 The same file — it is already loaded in full.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.08644 $0.08644
Opus 5.5 $0.03458 $0.03458
Sonnet 5.5 $0.01729 $0.01729
Haiku 4.5 $0.00864 $0.00864

Measured 2mo ago against content hash 42694f93e5d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

claude-code-toolkit CLAUDE.md scanned grade D 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 2mo 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.

- **Compatibility**: install scripts must work under `curl ... | bash` (no stdin assumptions without `< /dev/tty`); macOS BSD `head`/`sed`/`tail` (no GNU-only flags).

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Safety**: never overwrite `~/.claude/settings.json` without backup and JSON merge; never delete user files without confirmation; every destructive action prompts.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Compatibility**: install scripts must work under `curl ... | bash` (no stdin assumptions without `< /dev/tty`); macOS BSD `head`/`sed`/`tail` (no GNU-only flags).
CLAUDE.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Toolkit — Claude Code Instructions

Project Overview

Type: Documentation / Templates Repository Purpose: Collection of CLAUDE.md templates, components, and examples for Claude Code projects Stack: Markdown, Shell scripts, YAML configs


Quality Checks (MUST PASS)

This project has CI/CD checks. All PRs must pass before merge.

Run All Checks Locally

make check

Individual Checks

# Shell scripts
make shellcheck

# Markdown lint
make lint

# Validate templates
make validate

Markdown Formatting (CRITICAL)

All markdown files MUST pass markdownlint checks.

Common Errors to Avoid

  1. MD040 — Always specify language for code blocks

    <!-- WRONG -->
    ` ` `
    code here
    ` ` `
    
    <!-- CORRECT -->
    ` ` `bash
    code here
    ` ` `
    
  2. MD031/MD032 — Add blank lines around code blocks and lists

    <!-- WRONG -->
    Text
    - item
    Text
    
    <!-- CORRECT -->
    Text
    
    - item
    
    Text
    
  3. MD026 — No punctuation at end of headings

    <!-- WRONG -->
    ## What is this?
    
    <!-- CORRECT -->
    ## What is This
    

Quick Fix

npx markdownlint-cli "**/*.md" --ignore node_modules --fix

Project Structure

claude-guides/
├── templates/           # CLAUDE.md templates (base, laravel, nextjs)
│   └── */CLAUDE.md     # Template files
│   └── */settings.json # VS Code settings
├── components/          # Reusable sections for CLAUDE.md
│   └── *.md            # Individual components
├── examples/            # Complete project examples
│   └── */CLAUDE.md     # Example configurations
├── commands/            # Claude Code slash commands
│   └── *.md            # Command definitions
├── scripts/             # Utility scripts
└── .github/             # CI/CD workflows

File Naming Conventions

  • Components: kebab-case.md (e.g., plan-mode-instructions.md)
  • Templates: Directory with CLAUDE.md inside
  • Commands: kebab-case.md in commands/ directory

Read the full file on GitHub · 617 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. 2mo ago First seen · 617 lines · 8,644 tokens per session scan D 42694f93e5d1

Subscribe to this mod's changes

claude-code-toolkit CLAUDE.md is an instructions file published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 8,644 tokens to every session, about $0.0346 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

claude-code-toolkit CLAUDE.md compared with instructions from other repositories

claude-code-toolkit CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-code-toolkit CLAUDE.mdsergei-aronsen/claude-code-toolkitInstructions file52mo agoMITD8,644Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280k2d agoMITA4,325Codex, OpenCode