claudekit: Instructions file for Claude Code

AGENTS.md

claudekit AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from carlrannaberg/claudekit. It costs 6,892 tokens per session, scanned B, original, MIT.

Repository instructions for claudekit, a collection of shell scripts, commands, hooks, and configuration tools for Claude Code. They explain how to map a codebase and find its files, relationships, and structure.

In plain words
What is it for?
Use them to inspect a repository with tree or relationship views, focus the inspection on selected paths, and follow claudekit's development workflow.
Why use it?
They give AI coding assistants a consistent way to understand an unfamiliar project before changing it. The guide also points to the project's workflow and quality tools.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: $ARGUMENTS substitution, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is carlrannaberg/claudekit's own configuration. It tells Claude Code, Codex and OpenCode how to work on claudekit 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 claudekit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to carlrannaberg/claudekit. 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/carlrannaberg/claudekit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/carlrannaberg/claudekit

Made for: Claude Code, Codex, OpenCode.

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 claudekit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/carlrannaberg/claudekit/agents-md/github.svg)](https://agentmods.dev/instructions/carlrannaberg/claudekit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/carlrannaberg/claudekit/agents-md"><img src="https://agentmods.dev/badge/instructions/carlrannaberg/claudekit/agents-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 claudekit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/carlrannaberg/claudekit/agents-md"><img src="https://agentmods.dev/badge/instructions/carlrannaberg/claudekit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,892 This file is loaded in full into every session.
When invoked 6,892 The same file — it is already loaded in full.
Security scan B 2 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 $0.06892 $0.06892
Opus 5 $0.03446 $0.03446
Sonnet 5 $0.01378 $0.01378
Haiku 4.5 $0.00689 $0.00689

Measured 12d ago against content hash 43f7ed8e41e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

claudekit AGENTS.md scanned grade B with 2 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 12d 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.

Reads agent configuration directoriesmediumAgent snooping

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

- User-level settings (`~/.claude/settings.json`) should only contain environment variables, not hooks

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { exec } from 'node:child_process';
AGENTS.md · 760 lines

How it starts

The opening of the file, as written. The whole thing — 760 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This file provides guidance to AI coding assistants working in this repository.

Note: CLAUDE.md is a symlink to AGENTS.md in this project.

claudekit

A toolkit of custom commands, hooks, and utilities for Claude Code. This project provides powerful development workflow tools including git checkpointing, automated code quality checks, specification generation, and AI assistant configuration management. The toolkit is designed to be project-agnostic and enhances Claude Code functionality through shell scripts, commands, and hooks.

Use the codebase-map tool to understand and navigate the project structure:

Recommended formats:

  • dsl - For understanding code relationships, imports/exports, functions, and classes
  • tree - For exploring directory structure and finding files

Example usage:

# Get code overview with DSL format (shows functions, classes, imports)
codebase-map format --format dsl

# Get directory/file structure with tree format
codebase-map format --format tree

# Focus on specific areas
codebase-map format --format dsl --include "cli/**" --exclude "**/*.test.ts"

The codebase map is automatically provided at the start of each session and can be configured in .claudekit/config.json to filter what's shown.

For complete setup and configuration details, see the Codebase Map Guide.

Build & Commands

This is a TypeScript-based toolkit. Key commands:

  • Install: npm install -g claudekit - Install claudekit globally
  • Setup: claudekit setup - Initialize claudekit in your project
  • Build: npm run build - IMPORTANT: Run after any code changes to compile TypeScript
  • Symlinks: npm run symlinks - Create/update symlinks from .claude/ to src/ for development
  • Test hooks: Manually trigger by editing files or using Claude Code
  • Check shell syntax: bash -n script.sh
  • Validate JSON: jq . settings.json

Important: After making any changes to TypeScript files (hooks, commands, or library code), you MUST run npm run build before testing. The project uses compiled JavaScript from the dist/ directory, not the source TypeScript files.

Read the full file on GitHub · 760 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. 12d ago First seen · 760 lines · 6,892 tokens per session scan B 43f7ed8e41e0

Subscribe to this mod's changes

claudekit AGENTS.md is an instructions file published in the GitHub repository carlrannaberg/claudekit (761 stars, last pushed 5mo ago), licensed MIT. It adds 6,892 tokens to every session, about $0.0345 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens