1,298 real files from 1,290 public GitHub repos, each analyzed by a script and linked to its source. Search them, filter by language, license and rules, and copy the ones whose license allows it.
Want the short list instead? Our curated guide walks through 12 of the best files and what each one does well.
CommandsArchitectureCode styleTestingGit workflowDo and do not
Rules sections in this file
Architecture Rules
**No DOM.** This package must never import browser APIs. It runs in Node, WASM, and browser alike.
**Pure functions preferred.** State lives in the controller (vanilla package); core provides stateless transforms.
**`GridOptions` is the source of truth.** Every feature is toggled via `enable*` booleans on `GridOptions`.
Do NOT
Add DOM or browser imports
Mutate input arrays — always return new arrays/objects
Add default exports — use named exports only
Full file, 53 lines
# @ornery/ui-grid-core — Agent Instructions
Pure TypeScript grid engine. Zero DOM dependencies. Provides the pipeline, sorting, filtering, grouping, pagination, cell editing, validation, export/import, infinite scroll, selection, tree-view, and i18n systems.
## Build & Test
```bash
npm run build:core # tsup → dist/
npm test --prefix projects/ui-grid-core # vitest (154 tests)
CLI tool for configuring and monitoring Claude Code
30,854PythonMITCLAUDE.md620 linesCompleteness 100
CommandsArchitectureCode styleTestingGit workflowDo and do not
Rules sections in this file
⛔ CRITICAL: NEVER Hardcode Secrets or IDs
Use `process.env` (Node.js) or `os.environ.get()` (Python)
Critical Endpoints
Tracks component downloads for analytics
Used by CLI on every installation
Database: Supabase (component_downloads table)
Important Notes
**Component catalog**: Always regenerate after adding/modifying components
**API tests**: Required before production deploy (breaks download tracking)
**Secrets**: Never commit API keys (use environment variables)
Excerpt, 65 lines
# CLAUDE.md
This file provides guidance to Claude Code when working with this repository.
## Project Overview
Node.js CLI tool for managing Claude Code components (agents, commands, MCPs, hooks, settings) with a static website for browsing and installing components. The dashboard and its API routes are deployed on Cloudflare Pages, with supporting cron and monitoring tasks running as Cloudflare Workers.
CommandsArchitectureCode styleTestingGit workflowDo and do not
Excerpt, 65 lines
# CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Project Overview
Gravity is a dynamically typed, embeddable programming language written in portable C99 with no external dependencies (except stdlib). It features Swift-like syntax and supports procedural, OOP, functional, and prototype-based programming paradigms. Originally developed for the Creo project for cross-platform iOS/Android scripting.
## Build Commands
```bash
make # Build the gravity CLI executable
make mode=debug # Debug build (-g -O0 -DDEBUG)
make lib # Build shared library (libgravity.dylib/so/dll)
Like Vercel, but open source and for all languages.
4,747PythonMITAGENTS.md333 linesCompleteness 100
CommandsArchitectureCode styleTestingGit workflowDo and do not
Excerpt, 56 lines
# AI Agent Guidelines for /dev/push
This document provides comprehensive guidelines for AI agents working on the /dev/push codebase. It covers scripts, FastAPI application code, Docker/Compose, and project-wide conventions.
CommandsArchitectureCode styleTestingGit workflowDo and do not
Rules sections in this file
Never Touch Real User Config/Journals
First 25 lines only (license: GPL-3.0)
# CLAUDE.md
IMPORTANT: ALWAYS prefer contributing to the `main` branch with a PR.
## Project Overview
jrnl is a command-line journal application written in Python. It supports plain text and encrypted (AES) journals, multiple journal types, and various export formats. The main branch for development is `main`
CommandsArchitectureCode styleTestingGit workflowDo and do not
Excerpt, 27 lines
# Hyperframes
Open-source video rendering framework: write HTML, render video.
## Skills
This repo ships 21 AI agent skills via [vercel-labs/skills](https://github.com/vercel-labs/skills). Install them before writing compositions — they encode framework-specific patterns that generic docs don't cover. **Default to the core set**: the `/hyperframes` router installs each creation workflow on demand; install all 21 only when the user explicitly asks for the full set.
```bash
npx hyperframes skills update # default: installs/refreshes the core set — workflows install on demand
npx hyperframes skills # all 21 published skills at once — only on explicit request
npx skills add heygen-com/hyperframes # interactive picker (terminal only; --all also pulls the 6 repo-internal skills under .claude/skills)
npx skills add heygen-com/hyperframes --skill <name> # just one (bare name, no leading slash)
CommandsArchitectureCode styleTestingGit workflowDo and do not
Rules sections in this file
Important Notes
Before making any changes, clearly identify the target module along with its complete call chain and upstream/downstream dependencies. For c
If Kafka, Redis, MinIO, or authentication is involved, evaluate the impact on other services first.
**Always prioritize official frameworks, SDKs, and APIs.** When an official framework, SDK, or API exists for a task, you MUST use it instea
Context7 Usage Rules
**Library/framework/SDK API usage** - Querying the syntax, component APIs, method signatures, parameter details, or usage patterns of any li
**Version migrations** - Any framework or SDK upgrade or breaking-change question, such as Next.js 14 to 15, AWS SDK v2 to v3, or Pydantic v
**Configuration and installation** - Configuration-file syntax, CLI flags, environment setup, or installation steps for a specific tool or l
Excerpt, 65 lines
# CLAUDE.md
## Project Overview
Astron Agent is an enterprise-grade Agentic Workflow development platform. It includes the console frontend and backend, multiple core microservices, a plugin system, and deployment and infrastructure configuration. The repository uses a multi-language, multi-module structure. The primary languages are TypeScript, Java, Python, and Go.
## Repository Structure
### Console
- `console/frontend`
- React 18 + TypeScript + Vite frontend application
- Responsible for the console UI, agent creation, chat interface, workflow visualization, model management, plugin marketplace, and related features
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes CLI, local MCP, catalo
46,641PythonMITCLAUDE.md95 linesCompleteness 50
CommandsArchitectureCode styleTestingGit workflowDo and do not
Excerpt, 90 lines
# dbos-python
> **Note:** `CLAUDE.md` is a symlink to this file.
## Overview
DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
CommandsArchitectureCode styleTestingGit workflowDo and do not
Rules sections in this file
Key Business Rules
Gotchas
Constraints
First 25 lines only (license: None)
# FitTrack
> Gamified fitness platform with sweepstakes rewards and tiered competitions.
## Overview
FitTrack transforms fitness activity into a competitive, rewarding experience. Users connect fitness trackers, earn points from physical activities, then spend points on sweepstakes tickets for prize drawings. Tiered competition brackets ensure fair competition among users with similar demographics and fitness baselines.
**Target Market**: US only, 18+, sweepstakes-compliant states (excludes NY, FL, RI)
Rainbond is an open-source container platform that requires no Kubernetes expertise. Its core capabilities are 100% open source. It abstracts away infrastructure complexity and provides a unified way
CommandsArchitectureCode styleTestingGit workflowDo and do not
First 25 lines only (license: NOASSERTION)
# Rainbond — Go Core Services
## Overview
Rainbond is a cloud-native application management platform. This repository contains the Go backend services that interface directly with Kubernetes. It is called by `rainbond-console` (Django) via HTTP REST APIs.
Answer five questions and get both files with the six sections that strong files share. No signup. Edit the result before you commit it.
# This project
Describe what this project does and who uses it in one or two sentences.
## Commands
```bash
pnpm install # install dependencies
pnpm dev # run locally
pnpm build # production build
pnpm lint # lint and format check
pnpm test # run the test suite
```
Run lint and tests before you say a task is done.
## Architecture
- Project type: web app.
- Layout: src/app or src/pages for routes, src/components for UI, src/lib for shared code.
- Put shared code in one place and import it. Do not copy code between folders.
## Code style
- TypeScript strict mode, no any
- Use named exports
- Prefer small pure functions
## Testing
- Add or update a test for every behavior change and every bug fix.
- Run the single relevant test file while you work, then the full suite once at the end (`pnpm test`).
- Do not delete or skip a failing test to make the suite pass. Fix the cause or report it.
## Git workflow
- Work on a branch, never directly on main.
- One logical change per commit. Write the message as a short imperative sentence.
- Do not push, force-push or rewrite history unless asked.
## Do and do not
- Do read the surrounding code before you edit it.
- Do keep changes small and limited to the task.
- Do not add a dependency without asking.
- Do not commit secrets, .env files or generated build output.
- Do not reformat files you were not asked to change.
## Working with Claude Code
- Keep this file short. Move detail into files under .claude/rules/ and link to it from here.
- Plan before large changes. Show the plan, then wait for approval.
- If a command in this file fails, say so and fix this file instead of working around it.
Methodology
Finding files. We ran GitHub code search on the filenames CLAUDE.md and AGENTS.md, split by language and by topic terms, and collected 4,631 candidate repos. We then read metadata for each and kept public, non-fork, non-archived repos with at least 10 stars. We also ran Google queries for curated lists and added the repos they pointed to.
Licensing. When the repo license is MIT, Apache-2.0, BSD, ISC, CC0 or the Unlicense, we show an excerpt of up to about 90 lines and allow copying. For any other license, including no license, we show only the first 25 lines with no copy button, and we never store the full file. Every card names the repo, owner and license and links to the file at the commit we read.
Analysis. A script counts lines, detects sections from headings and keywords, lists mentioned tools (pnpm, npm, uv, pytest, vitest, docker, MCP, subagents, hooks, skills) and guesses the project type from the file, repo description and topics. The rules summary on each card lists the file's own headings about rules and, for permissive repos, the first bullets under them. Nothing is written by us.
Detection is keyword based, so some files are misfiled. Report a wrong card through our contact page and we will fix the rule.
Completeness, 0 to 100
This counts which topics a file covers. It does not judge whether the advice is right.
Commands section
15
Architecture or structure section
15
Code style or conventions section
15
Testing rules
15
Git workflow
10
Do and do-not rules
10
Concrete commands or a code block
10
Length, full marks at 60 lines
10
Sources used to find repos beyond code search
Google query "CLAUDE.md example": surfaced ArthurClune/claude-md-examples
Google query "AGENTS.md example": surfaced agentsmd/agents.md
Google query "best CLAUDE.md": surfaced josix/awesome-claude-md
Google query "CLAUDE.md template": surfaced abhishekray07/claude-md-templates and davila7/claude-code-templates
FAQ
CLAUDE.md and AGENTS.md questions
What the files are, which one Claude Code reads, and how we built this library.
It is a markdown file that Claude Code reads at the start of every session. It holds project instructions such as build and test commands, architecture notes and coding rules. Claude treats it as context, not as enforced configuration.
02What is an AGENTS.md file?
AGENTS.md is a plain markdown file with instructions for coding agents, used by several tools besides Claude Code. This library lists both file types, and you can filter by either one.
03Does Claude Code read AGENTS.md?
Yes, since Claude Code v2.1.277. By default it reads AGENTS.md only when there is no CLAUDE.md or CLAUDE.local.md in your working directory or any directory above it. If a CLAUDE.md exists, Claude reads that and ignores AGENTS.md unless the CLAUDE.md imports it. This comes from the memory page of the Claude Code docs, checked on September 20, 2026.
04Can I use both files in one repo?
Yes. Put the shared rules in AGENTS.md and create a CLAUDE.md that imports it with an @AGENTS.md line, then add Claude-only notes below. You can also set Project instructions to claude-md-and-agents-md so Claude loads both files. The docs list the exact setting and its limits.
05How long should a CLAUDE.md be?
The files in this library range from a few lines to well over a thousand. The line-count badge and the completeness number on each card let you compare. Shorter files that state exact commands and rules tend to be easier to keep correct, but we have not measured that, so treat it as our reading of the files and not as a finding.
06What should I put in a CLAUDE.md?
The sections that show up most in strong files are commands, architecture, code style, testing, git workflow and a list of things Claude must not do. The generator below builds a starter with each of those, and the completeness score checks for the same six.
07How is the completeness score calculated?
It is a rules-based number from 0 to 100. Six sections are worth 15 points each for commands, architecture, testing and code style, and 10 each for git workflow and do-not rules. Concrete commands or code blocks add 10, and length adds up to 10 points, reaching the maximum at 60 lines. The full method is in the methodology section on this page. It measures coverage, not whether the advice is good.
08Can I copy these files into my project?
Only where the repo license allows it. For repos under MIT, Apache-2.0, BSD, ISC, CC0 or the Unlicense we show a longer excerpt with a Copy button. For every other repo we show at most the first 25 lines, with no copy button, plus a link to the full file at its commit. Keep the original attribution and license notice when you reuse anything.
09Where do the files come from?
Public GitHub repos found through GitHub code search on the filenames CLAUDE.md and AGENTS.md, plus curated lists that turned up in Google results. Repos with fewer than 10 stars, forks and archived repos are left out. Every card links to the file at the exact commit we read.
10Where is the curated guide to the best examples?
We wrote one. It picks 12 files from real repos and explains what each does well. This page is the searchable library, and the guide is the short list.
