---
title: "Set up your coding agent"
description: "One line gives your coding agent the whole documentation, as plain text it reads before it writes the integration."
canonical: https://www.charitips.com/docs/get-started/coding-agent
---

# Set up your coding agent

> One line gives your coding agent the whole documentation, as plain text it reads before it writes the integration.

## Give your agent the docs

Paste this line in Claude Code, Cursor, Codex or any agent that reads a URL. The index lists every page, so the agent opens the ones it needs instead of guessing. Nothing to install.

```prompt
Read https://www.charitips.com/docs/llms.txt before you write any Charitips code. Build and test on the Charitips sandbox.
```

Every page an agent needs is also plain Markdown: add `.md` to its URL. The **Build with AI** button at the top of a page writes the prompt for that page.

## Keep it in the project

Agents read a file at the root of the project before every task. One line there, and every session starts from the docs. The file depends on the agent.

**Claude Code**

In `CLAUDE.md`:

```text
Before writing any Charitips code, read https://www.charitips.com/docs/llms.txt. Build and test on the Charitips sandbox.
```

**Codex and Cursor**

In `AGENTS.md`, which Codex and Cursor both read:

```text
Before writing any Charitips code, read https://www.charitips.com/docs/llms.txt. Build and test on the Charitips sandbox.
```

**VS Code**

In `.github/copilot-instructions.md`:

```text
Before writing any Charitips code, read https://www.charitips.com/docs/llms.txt. Build and test on the Charitips sandbox.
```

## Install the Charitips skill

The skill teaches your agent how to integrate Charitips well: the order of the calls, the rules that keep a payment flow safe, the fix for each error the API returns, and the check to run before saying the work is done. It is one Markdown file, `SKILL.md`, that the agent loads when the task mentions Charitips.

**Prompt**

```prompt
Install the Charitips skill from https://www.charitips.com/docs/skill.md, then use it for any Charitips work in this project.
```

**Claude Code**

Claude Code reads the skills of the project in `.claude/skills/<name>/SKILL.md`, and your own in `~/.claude/skills/`:

```bash
mkdir -p .claude/skills/charitips
curl -fsSL https://www.charitips.com/docs/skill.md -o .claude/skills/charitips/SKILL.md
```

**Codex**

Codex reads the skills of the repository in `.agents/skills/<name>/SKILL.md`, and your own in `~/.agents/skills/`:

```bash
mkdir -p .agents/skills/charitips
curl -fsSL https://www.charitips.com/docs/skill.md -o .agents/skills/charitips/SKILL.md
```

## Go further with the MCP server

With [the MCP server](https://www.charitips.com/docs/get-started/mcp.md), your agent searches the docs and reads any operation with its fields, its errors and their fixes, without leaving the editor. The server is read-only: the calls themselves run from your code, with your sandbox credentials.

## What the agent still needs from you

The docs do not replace an account. Give the agent your sandbox client id and secret as environment variables: see [Sandbox](https://www.charitips.com/docs/get-started/sandbox.md) and [Authentication](https://www.charitips.com/docs/get-started/authentication.md).

- Build and test on the sandbox. Sandbox credentials start with `test_`.
- Credentials are read from environment variables, never written in code.
- One access token per hour, reused for every call: asking for a new one before each call slows the integration down.