---
title: The CLI and Agent Skills
description: Let your own AI work in VIABLE as you: build a course, set up a study or connect an app, with one message to set it up.
updated: 2026-10-30
---

> All VIABLE docs, for people and their agents: https://developers.viablelab.org/llms.txt

# The CLI and Agent Skills

Your own AI can do VIABLE work for you: build a course, set up a study, connect an app. The VIABLE CLI (`viable`) acts as you, with your access, and its Agent Skill teaches your AI to use it safely.

## Let your AI set it up

Paste this one message into your AI:

```text
Read https://www.viablelab.org/downloads/viable-cli.md and set up VIABLE CLI and its Agent Skill for your environment. Help me sign in securely.
```

Where to paste it:

- **If you don't code**: Claude Cowork in the Claude desktop app, ChatGPT Work in the ChatGPT app, or Gemini with **Task** chosen under the prompt box. Start a new task and paste the message.
- **If you build software**: Claude Code, Codex, Google Antigravity, or any agent with a terminal.

::: steps
1. **It installs the CLI and the Skill.** The guide tells your AI what to install where it works, and how to check it.
2. **You approve the sign-in.** It shows you a link and a code; you approve in your own browser. It never sees your password.
3. **Then ask in your own words.** The Skill knows VIABLE's commands, its safety rules and the API guide.
:::

> [!NOTE]
> The CLI needs somewhere to run commands, with Node.js 22 and internet access. If your assistant can't run commands where it works, it says so; then do the task in the dashboard, or ask it to read the [API guide](https://developers.viablelab.org/agents/viablelab-api.md) and guide you.

## What to ask it

| You | Ask, for example |
| --- | --- |
| Teacher | "Make a course for Period 2 with a writing activity and a tutor that gives hints only, then send me the preview link." |
| Researcher | "Set up an observational study on that course with consent, and upload our approved consent form." |
| App developer | "Connect our server to VIABLE: name each user, tag our requests, send learning data, then check Build → Apps." |
| Owner | "Show last week's cost by key and model." |

It can't do more than your role allows, since VIABLE checks every request. Every change needs an exact `--confirm` value, and the Skill tells your agent to show you what will happen and wait for a clear yes. Keys are written to a file only you can read, never to the chat.

## Install it yourself

Prefer the terminal? You need Node.js 22 or newer.

```bash
npm install --global --prefer-online https://www.viablelab.org/downloads/viable-cli.tgz
viable auth login
viable agent install
```

- On a remote machine or a cloud agent, sign in with `viable auth login --device`.
- `viable agent install --target` takes `codex`, `claude`, `kimi` or `qwen`.
- `viable help` lists the commands. `viable doctor` checks the setup, and `viable update --with-skill` keeps both current.

::: figure stage-code

Signing in never creates an account: register at https://developers.viablelab.org first. [Resources → CLI & Agent Skills](/dashboard/cli) has the same steps.

## Agents and these docs

The Skill reads the [API guide](https://developers.viablelab.org/agents/viablelab-api.md) for current routes, fields and errors. Any agent can start from [llms.txt](https://developers.viablelab.org/llms.txt), which lists every page here as Markdown. The CLI and its Skill are open source under the MIT License.

::: cards
- [Members and roles](/docs/project/members-and-roles): what your role lets your AI do.
- [Send learning data](/docs/connect/learning-data): connect an app, or let your AI do it.
- [Your first class](/docs/teach/first-class): what your AI builds, step by step.
:::