Skip to content

Let a coding agent add Configure ​

A skill is a page written for an agent. You paste its link into the agent, and the agent does the work. Nothing to install. Configure publishes two.

Add Configure to your project ​

In the project you want to add Configure to, send this message to Claude Code, Cursor, or Codex:

text
Read https://configure.dev/skill.md and add Configure to this project.

The agent reads the skill and builds the Quickstart in your code, in six steps:

  1. It reads your code and decides two things without asking: where your chip goes (onboarding, an empty chat, or settings), and whether your app has its own users. If it does, each user's context is keyed by your user id. Only an app with no accounts at all gets Sign in with Configure.
  2. It installs the SDK. If your credentials are not in the environment yet, it asks you to run npx configure setup --users, because that step opens a browser and needs you.
  3. It adds a chip linked to a route on your server. The route mints the link with profile.connect({ returnUrl }) and redirects to Configure's page.
  4. It adds the return route: it refreshes the user's stored context and sends them to the chat. A user who did not finish goes back home.
  5. It adds the profile.updated webhook that keeps the stored context current, the first-turn injection, a commit at the end of every turn, and the configure_* tools on your model call (Anthropic, OpenAI, or Vercel).
  6. It writes a test against the sandbox, runs it, and shows you the result.

You run setup when asked, read the diff, and run the app. It takes a few minutes.

The skill forbids it to build a Configure link by hand, keep its own connected flag, expose your secret key to a browser, or leave the refresh and the commit to the model.

TIP

No account yet? The skill starts from the sandbox, so the agent can build and test everything before you sign up.

Make your agent use what it knows ​

A model with the Configure tools does not always use them. It searches when it wants an answer, but rarely checks what it knows about the user. This skill adds three habits to your agent's instructions:

  • Search the user's context before saying you do not know something about the user.
  • Save a durable fact the moment the user states it, without asking permission.
  • Keep project conventions and code style out of the user's context.
text
https://docs.configure.dev/skill/agents-block.md

Append it to your agent's system prompt or rules file. Claude Code has its own installer instead. It installs the configure-memory skill (a SKILL.md) and a hook that loads a short digest of the user at the start of every session:

bash
curl -fsSL https://docs.configure.dev/skill/install.mjs | node -

Per-client steps for Codex, Cursor, Windsurf, and Gemini CLI are on the coding agents page.

For platforms that host agents ​

If you run a platform that hosts other people's agents, your platform provisions the keys and every agent on it gets Configure. Maritime has a skill for this today.

text
https://configure.dev/configure-maritime-skill.md

How the skills are tested ​

Every skill on this page is tested two ways before it ships:

  • A quiz. A small model gets only the skill and must answer a developer's questions correctly: where the chip goes, what its route and the return route call, how to tell whether a user is connected, when to refresh, what to commit, how to wire each model provider, and what never to do.
  • A build. A fresh agent gets only the skill and a real app, and what it builds must run against the sandbox.

If you write a skill for your own platform, run the same two tests. Two details decide whether it passes. Name the host, api.configure.dev, in full, or the agent guesses one. Show mcp_servers being passed to the model, not only the session mint, or the tools never reach the model and nothing reports it.

Infrastructure to connect agents, apps, and chats