What is context-kit CLAUDE.md?

Repository instructions for ContextKit, a command-line tool that creates specification files for AI coding agents. The project uses templates and connected data sources such as ticketing systems, databases, and design tools.

Understanding ContextKit's files, configuring its connections, creating specification files, and following the project's development workflow.

It gives an agent the project background, architecture, and common commands it needs before changing the code. This reduces guesswork about how the repository is organized and operated.

How eyalzh/context-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to eyalzh/context-kit. 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/eyalzh/context-kit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/eyalzh/context-kit

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/eyalzh/context-kit/claude-md/github.svg)](https://agentmods.dev/instructions/eyalzh/context-kit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/eyalzh/context-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/eyalzh/context-kit/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/eyalzh/context-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/eyalzh/context-kit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 849 This file is loaded in full into every session.

When invoked 849 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00849	$0.00849
Opus 5.5	$0.00340	$0.00340
Sonnet 5.5	$0.00170	$0.00170
Haiku 4.5	$0.00085	$0.00085

Measured 2mo ago against content hash 5b2c81b0dd8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-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 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.

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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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.

Project Overview

ContextKit is a CLI tool and MCP (Model Context Protocol) client for creating spec files for AI coding agents. It uses reusable spec templates with context variables that can be automatically filled from various MCP sources (ticketing systems, databases, design tools, etc.).

Architecture

Entry point: cxk.py - Main CLI with argparse-based command routing
State management: state.py - Handles project initialization, config loading, and git repo detection
Command handlers: commands/ directory contains handlers for each CLI command:
- init.py - Project initialization (creates .cxk/ config directory)
- mcp.py - MCP server management (add-sse, add-stdio, add-http)
- create_spec.py - Template rendering with variable collection
Template engine: engine/ - Jinja2-based template processing with async support and MCP tool integration
- engine/globals.py - Global Jinja2 functions including call_tool() for calling MCP tools from templates
MCP client: mcp_client/ - MCP protocol client implementation
- mcp_client/config.py - Pydantic models for MCP server configs (stdio, SSE, HTTP)
- mcp_client/client_session_provider.py - Connection management for MCP servers
User prompts: prompt/ - Interactive variable collection

Core Concepts

Project state: Must be initialized with cxk init (creates .cxk/mcp.json)
MCP servers: Configured via CLI commands, stored in .cxk/mcp.json
Spec templates: Jinja2 templates with variables that get filled from MCP resources
Context variables: Can be automatic MCP resources or user-provided values
MCP tool functions: Templates can call MCP tools directly using {{ call_tool('server', 'tool', args) }} syntax

Common Commands

Development

# Install dependencies
uv sync

# Run tests
uv run pytest

# Run specific test
uv run pytest tests/test_specific.py


# Linting and formatting
uv run ruff check
uv run ruff format

Read the full file on GitHub · 86 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.

2mo ago First seen · 86 lines · 849 tokens per session scan A 5b2c81b0dd8c

Subscribe to this mod's changes

context-kit CLAUDE.md is an instructions file published in the GitHub repository eyalzh/context-kit (12 stars, last pushed 1y ago), licensed MIT. It adds 849 tokens to every session, about $0.0034 per session on Opus 5.5. 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.

cli-tool mcp-client spec-generator

context-kit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context-kit CLAUDE.mdeyalzh/context-kit	Instructions file	12	1y ago	MIT	A	849	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

context-kit: Instructions file for Claude Code