What is cclint CLAUDE.md?

A project instruction file for cclint, a TypeScript and Node.js tool that checks and improves CLAUDE.md context files. It documents the project structure, commands, and strict production checks.

Use it when working on cclint, including running Vitest tests, using tsx during development, running the TypeScript compiler, and building for production.

It gives an AI coding assistant the repository-specific information needed to develop, test, lint, type-check, and build the project correctly.

How felixgeelhaar/cclint configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to felixgeelhaar/cclint. 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/felixgeelhaar/cclint/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/felixgeelhaar/cclint

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/felixgeelhaar/cclint/claude-md/github.svg)](https://agentmods.dev/instructions/felixgeelhaar/cclint/claude-md)

Your own site

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

Per session 1,263 This file is loaded in full into every session.

When invoked 1,263 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	$0.01263	$0.01263
Opus 5.5	$0.00505	$0.00505
Sonnet 5.5	$0.00253	$0.00253
Haiku 4.5	$0.00126	$0.00126

Measured 1mo ago against content hash 34665f2eb211, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cclint 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 1mo 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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 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

This is the CC Linter project - a TypeScript/Node.js tool designed to validate and optimize CLAUDE.md context files. The project follows a hexagonal architecture with a Core Linting Engine that is independent from its delivery mechanisms (CLI, IDE extensions).

Development Commands

# Development (uses tsx for fast execution)
npm test                # Run tests with Vitest
npm run test:watch      # Run tests in watch mode

# Production checks (uses tsc for strict type checking)
npm run typecheck      # Type check with TypeScript compiler
npm run lint           # Lint code
npm run build          # Build for production

# Package management
npm ci                 # Install dependencies (CI)
npm install            # Install dependencies

Architecture

The project uses a Domain-Driven Design approach with hexagonal architecture:

Core Domain Model

ContextFile: In-memory representation of a file being linted
Rule: Self-contained service that inspects a ContextFile and returns Violations
Violation: Entity representing a broken rule with Location and Severity
Location: Value object defining position of a Violation
Severity: Value object (Error, Warning, Info)
LintingResult: Root aggregate containing all Violations for a file

Architecture Layers

CLI  (cclint)      ──┐
MCP  (cclint-mcp)  ──┼──► Core Linting Engine (npm package)
LSP  (cclint-lsp)  ──┤     ├── Rules Engine (aggregates violations)
GitHub Action      ──┘     ├── createRules(config) factory + rule descriptors
                           ├── Individual Rules (implement Rule interface)
                           └── File System I/O (reads CLAUDE.md, config files)

All four entry points build their rule set from the single createRules(config) factory (src/rules/registry/), driven by canonical RULE_DESCRIPTORS — one source of truth for each rule's id, default-enabled flag, and metadata — so every entry point runs an identical, in-lock-step rule set.

Read the full file on GitHub · 126 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.

1mo ago Changed 34665f2eb211
2mo ago First seen · 126 lines · 1,263 tokens per session scan A a5bc869b28e8

Subscribe to this mod's changes

cclint CLAUDE.md is an instructions file published in the GitHub repository felixgeelhaar/cclint (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,263 tokens to every session, about $0.0051 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.

cclint CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cclint CLAUDE.mdfelixgeelhaar/cclint	Instructions file	12	1mo ago	MIT	A	1,263	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cclint: Instructions file for Claude Code