|
| 1 | +# AGENTS.md and CLAUDE.md |
| 2 | + |
| 3 | +`AGENTS.md` and `CLAUDE.md` are project-level instruction files that AI coding assistants read when they enter your repository. They give the assistant durable, repository-specific context so it follows Reflex conventions instead of generic defaults. |
| 4 | + |
| 5 | +- `AGENTS.md` is read by agents that follow the [AGENTS.md convention](https://agents.md), including Cursor, OpenCode, OpenAI Codex, and Pi. |
| 6 | +- `CLAUDE.md` is read by [Claude Code](https://code.claude.com/docs/en/memory). Claude Code does not read `AGENTS.md` directly — see [Sharing With Claude Code](#sharing-with-claude-code) below. |
| 7 | + |
| 8 | +A Reflex project should have at least one of these files at the project root, next to `rxconfig.py`. |
| 9 | + |
| 10 | +## Recommended Content |
| 11 | + |
| 12 | +The [reflex-dev/agent-skills](https://github.com/reflex-dev/agent-skills) repository ships an `AGENTS.md` template that points assistants at the [Reflex Agent Skills](/docs/ai/integrations/skills/) for environment setup, documentation lookup, and process management. Use it as the starting point, then add anything specific to your codebase. |
| 13 | + |
| 14 | +```md alert info |
| 15 | +# `AGENTS.md` references skills by name, so it works once the [Reflex Agent Skills](/docs/ai/integrations/skills/) are installed in the assistant. |
| 16 | +``` |
| 17 | + |
| 18 | +## Installation |
| 19 | + |
| 20 | +Download the template into your project root, next to `rxconfig.py`: |
| 21 | + |
| 22 | +```bash |
| 23 | +curl -fsSL https://raw.githubusercontent.com/reflex-dev/agent-skills/main/AGENTS.md -o AGENTS.md |
| 24 | +``` |
| 25 | + |
| 26 | +Or copy it manually from a local clone of the [reflex-dev/agent-skills](https://github.com/reflex-dev/agent-skills) repository. |
| 27 | + |
| 28 | +## Sharing With Claude Code |
| 29 | + |
| 30 | +Claude Code reads `CLAUDE.md`, not `AGENTS.md`. To avoid duplicating content, create a `CLAUDE.md` that [imports](https://code.claude.com/docs/en/memory#import-additional-files) `AGENTS.md` using the `@` syntax: |
| 31 | + |
| 32 | +```md |
| 33 | +@AGENTS.md |
| 34 | + |
| 35 | +## Claude Code |
| 36 | + |
| 37 | +Add any Claude-specific instructions here. |
| 38 | +``` |
| 39 | + |
| 40 | +Claude Code expands the `@AGENTS.md` import at session start, then appends anything you write below it. Both files stay in sync from a single source. |
| 41 | + |
| 42 | +After installation, your project root looks like: |
| 43 | + |
| 44 | +```text |
| 45 | +my_app/ |
| 46 | + AGENTS.md |
| 47 | + CLAUDE.md |
| 48 | + rxconfig.py |
| 49 | + my_app/ |
| 50 | + my_app.py |
| 51 | +``` |
| 52 | + |
| 53 | +## Project-Specific Additions |
| 54 | + |
| 55 | +The template covers Reflex-wide setup. Below it, add anything else the assistant should know about your project: |
| 56 | + |
| 57 | +- Internal conventions and code style. |
| 58 | +- Required lint, type-check, or test commands. |
| 59 | +- Folder layout and where new code should go. |
| 60 | +- Hosting or deployment notes. |
| 61 | + |
| 62 | +Keep entries short and imperative — assistants follow concise, direct instructions more reliably than long paragraphs. |
| 63 | + |
| 64 | +## Keeping Files Updated |
| 65 | + |
| 66 | +Reflex evolves quickly. If you used `curl` to download the template, re-run the same command to refresh it: |
| 67 | + |
| 68 | +```bash |
| 69 | +curl -fsSL https://raw.githubusercontent.com/reflex-dev/agent-skills/main/AGENTS.md -o AGENTS.md |
| 70 | +``` |
| 71 | + |
| 72 | +If you cloned the [reflex-dev/agent-skills](https://github.com/reflex-dev/agent-skills) repository, pull the latest changes and copy the file again: |
| 73 | + |
| 74 | +```bash |
| 75 | +cd agent-skills |
| 76 | +git pull |
| 77 | +``` |
| 78 | + |
| 79 | +## Combining With Skills and MCP |
| 80 | + |
| 81 | +`AGENTS.md` and `CLAUDE.md` anchor the assistant in your project. Pair them with the other onboarding tools for deeper Reflex knowledge: |
| 82 | + |
| 83 | +- [Reflex Agent Skills](/docs/ai/integrations/skills/) provide reusable workflows that the file references by name. |
| 84 | +- [Reflex MCP](/docs/ai/integrations/mcp-overview/) provides structured documentation lookup at runtime. |
| 85 | +- The [llms.txt index](/llms.txt) gives a broad map of the documentation in one file. |
0 commit comments