Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.
# Agentic Code — AGENTS.md Workflow Framework for AI Coding Agents
Agentic coding workflows for Cursor, Codex, Cursor CLI, and any
AGENTS.md-compatible tool. Zero config, test-first, language-agnostic.
[](LICENSE)
[](https://agents.md)
[](package.json)

*AI builds a Slack bot with tests & docs — in 30s*
## How Agentic Code Works
```
You: "Build a Slack bot with Cursor API"
AI: ✓ Reads AGENTS.md
✓ Analyzes requirements
✓ Plans architecture
✓ Writes tests first
✓ Implements with best practices
✓ Verifies everything works
```
**Works out of the box — no configuration required.**
## Quick Start (30 seconds)
```bash
npx agentic-code my-project && cd my-project
# Ready to go
```
That's it. Works with **Cursor, Codex, Cursor CLI**, and [many AGENTS.md-compatible tools](https://agents.md).
## Compatible Tools
| Tool | Support | Notes |
|------|---------|-------|
| [Cursor](https://cursor.com) | Primary | Skills installation via `npx agentic-code skills --cursor` |
| [Codex](https://github.com/openai/codex) | Primary | Skills installation via `npx agentic-code skills --codex` |
| [Cursor CLI](https://github.com/google-cursor/cursor-cli) | Primary | Reads AGENTS.md automatically |
| Any AGENTS.md tool | Compatible | [See full list at agents.md](https://agents.md) |
## Using Codex?
If you mainly use Codex, see [codex-workflows](https://github.com/shinpr/codex-workflows) for a more Codex-specific setup.
It includes subagents-based isolation for review and verification tasks, improving reliability by separating context inside the same working session.
## Problems with AI Coding Agents
Every AI coding tool has the same problems:
- Forgets your project structure after 10 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.