What is context42 CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, covering a TypeScript command-line project that creates code style guides with Google Gemini. They describe the project, development commands, and CLI use.

Use it when working on Context42, especially for following its project plan, keeping work logs, running tests and builds, and using its command-line tools.

It gives the assistant project-specific rules and commands, reducing guesswork when planning, testing, formatting, linting, or running the code.

How zenbase-ai/context42 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zenbase-ai/context42. 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/zenbase-ai/context42/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/zenbase-ai/context42

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/zenbase-ai/context42/claude-md/github.svg)](https://agentmods.dev/instructions/zenbase-ai/context42/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/zenbase-ai/context42/claude-md"><img src="https://agentmods.dev/badge/instructions/zenbase-ai/context42/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/zenbase-ai/context42/claude-md"><img src="https://agentmods.dev/badge/instructions/zenbase-ai/context42/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,044 This file is loaded in full into every session.

When invoked 1,044 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	$0.01044	$0.01044
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 2mo ago against content hash b93fb0e133c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context42 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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 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.

Principles

Frequently refer to PLAN.md for the project plan.
As you work, create a new log in .claude/logs/{plan-name}/{int}.md, where int is an increasing integer. You can reference previous logs. You'll have to create the directory.

Project Overview

Context42 is a TypeScript CLI that generates style guides for codebases using Google Gemini AI. It analyzes code files, generates language-specific style documentation, and provides an interactive terminal UI built with Ink (React for CLIs).

Development Commands

All commands use just (justfile). Key commands:

just dev - Run tests in watch mode
just build - Production build with esbuild
just cli [args] - Build and run the CLI
just test [args] - Run tests with vitest (can pass file paths)
just fmt - Format code with Biome
just lint - Lint code with Biome
just claude [args] - Run Claude CLI via bunx
just gemini [args] - Run Gemini CLI via bunx
just publish <version> - Bump version and publish to npm

CLI Usage

# Basic usage
just cli -i ./src -o ./docs

# Resume failed run
just cli --run <run-id>

# Debug mode (shows run ID)
just cli --debug

# Custom concurrency
just cli -c 8

Architecture

Core Modules

Explorer (src/lib/explorer.ts)
- Discovers files using globby
- Groups by language extension
- Filters common ignore patterns
- Returns structured FileInfo objects
Processor (src/lib/processor.ts)
- Worker pool pattern with abort support
- Dependency-aware processing (children before parents)
- Automatic cleanup via file registry
- Configurable concurrency (default: 4)
- Task distribution and result collection
Generator (src/lib/generator.ts)
- Creates Gemini prompts for style analysis
- Executes via ZX shell commands
- Handles rate limiting and errors
- Parses AI responses

Read the full file on GitHub · 150 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 · 150 lines · 1,044 tokens per session scan A b93fb0e133c1

Subscribe to this mod's changes

context42 CLAUDE.md is an instructions file published in the GitHub repository zenbase-ai/context42 (48 stars, last pushed 8mo ago), licensed MIT. It adds 1,044 tokens to every session, about $0.0042 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 2026-08-30.

context42 CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
context42 CLAUDE.mdzenbase-ai/context42	Instructions file	48	8mo ago	MIT	A	1,044	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	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	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
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

context42: Instructions file for Claude Code