Starter template for AI-first development. Scaffolds AGENTS.md, CLAUDE.md, CHANGELOG, and README so coding agents like Claude Code, Cursor, and Copilot have the right context from day one.
# agentic-template [](https://github.com/greynewell/agentic-template/actions) [](./LICENSE) A starter template for AI-first development. Scaffolds `AGENTS.md`, `CLAUDE.md`, `CHANGELOG`, and `README` so coding agents like Claude Code, Cursor, and Cursor have the right context from day one. ## Quick Start Click **[Use this template](https://github.com/greynewell/agentic-template/generate)** on GitHub, or: ```bash gh repo create my-project --template greynewell/agentic-template --clone ``` ## What's Included | File | Purpose | |------|---------| | `README.md` | Structured project README with badges, architecture diagram, and contribution guide | | `AGENTS.md` | Guidelines and hard rules for AI coding agents | | `CLAUDE.md` | Entry point for Claude Code — references `AGENTS.md` | | `CHANGELOG.md` | [Keep a Changelog](https://keepachangelog.com) format with `[Unreleased]` section | | `.cursor/settings.json` | Sandbox settings for Claude Code — auto-sandboxes bash commands | | `.github/workflows/build.yml` | CI that validates project structure on every push and PR | ## How It Works **`CLAUDE.md`** is the first file Claude Code reads when it enters your project. It points to **`AGENTS.md`**, which contains the rules any AI coding agent should follow — changelog discipline, commit conventions, code style expectations, and PR requirements. The **build workflow** enforces the structure: required files must exist, the changelog must have an `[Unreleased]` section, and `CLAUDE.md` must reference `AGENTS.md`. This keeps agents and humans aligned from the first commit. ## Customizing After creating your repo from this template: 1. **`README.md`** — Replace the placeholder sections with your project's name, description, architecture, and build commands 2. **`AGENTS.md`** — Add project-specific rules (language conventio
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.