<!-- generated by epythet -->

# For AI agents

`enlace_auth` ships artifacts for coding agents alongside its code. This page lists
them, says where each lives in the repository, and points at the
machine-readable copies of this documentation.

## Skills

Skills are folders holding a `SKILL.md` (the [Agent Skills](https://agentskills.io) format): a description that tells an agent when to use it and a body with the procedure. Install one into your agent with `gh skill` (any host: `--agent claude-code`, `copilot`, `cursor`, `codex`, `gemini`), or use the copy bundled in the wheel.

### `enlace-auth-usage`

How to add sign-in, sessions, CSRF protection, admin accounts, per-app access levels, runtime grants and per-user storage to an enlace multi-app platform with the enlace_auth plugin. Use when the user mentions enlace_auth, the enlace-auth CLI, protected:user or protected:shared apps, ENLACE_SIGNING_KEY, ENLACE_ADMIN_EMAILS, X-CSRF-Token or /auth/csrf, request.state.store, add-user, reset-link, grant, or share; or wants to put login in front of apps served by enlace.

```bash
gh skill install i2mint/enlace_auth enlace-auth-usage --agent claude-code
```

Source: [`enlace_auth/data/skills/enlace-auth-usage`](https://github.com/i2mint/enlace_auth/tree/HEAD/enlace_auth/data/skills/enlace-auth-usage) (bundled with the pip package).

### `enlace-auth-dev`

How to work on the enlace_auth codebase itself: run and write tests, change the auth, CSRF, session, grant, share or admin code safely, and what a change must keep true. Use when editing files in enlace_auth/, fixing an enlace_auth issue, reviewing a pull request to it, or when asked how enlace_auth is organized or tested.

```bash
gh skill install i2mint/enlace_auth enlace-auth-dev --agent claude-code
```

Source: [`skills/enlace-auth-dev`](https://github.com/i2mint/enlace_auth/tree/HEAD/skills/enlace-auth-dev).

The bundled skills are also on disk after `pip install enlace_auth`, under the package’s `data/skills/` directory; link them into an agent without network access with `skill link-skills <that directory>`.

## Instruction files

Files agents read before working in this repository.

- [`CLAUDE.md`](https://github.com/i2mint/enlace_auth/tree/HEAD/CLAUDE.md): read by Claude Code

## Machine-readable documentation

This site publishes the same documentation in forms that fit an agent’s context window:

- [`llms.txt`](https://i2mint.github.io/enlace_auth/llms.txt): an index of every page with a one-line description ([llms.txt](https://llmstxt.org) format)
- [`enlace_auth.md`](https://i2mint.github.io/enlace_auth/enlace_auth.md): the whole documentation as one Markdown file
- `<page>.html.md`: a rendered Markdown twin of every page, advertised from each page’s `<head>` with `<link rel="alternate" type="text/markdown">`
- [`objects.inv`](https://i2mint.github.io/enlace_auth/objects.inv): the Sphinx inventory: a symbol-to-URL index (`sphobjinv convert plain objects.inv -`)
