Wire your agent

What you need

• Node.js 24 or newer. Not optional. Current releases refuse installation on Node versions below 24: the preinstall check prints the detected version and fails the install, so npm install -g rcf-lite will not leave you with a silently-broken CLI. Run node -v first anyway.
• A coding-agent harness. The default init-and-restart path is verified against Claude Code; other harnesses work when they read .mcp.json and either CLAUDE.md or AGENTS.md at session start. For anything else, see Wiring alternatives.

Nothing else.

Install and initialise

In your project directory:

node -v                # must print v24 or higher
npm install -g rcf-lite
rcf --version          # expect 0.34.2 or later
rcf init

If rcf --version comes back command not found, something in the install went wrong: on Node < 24 the preinstall check fails with a Node-version error message, and other causes (a broken PATH, a global-install target the shell does not read, an npm permission error) can produce the same missing-command symptom. Read the last lines of the failing npm install -g rcf-lite output for the real reason and address that. If it was the Node version, install Node 24 (brew install node@24, or your platform's equivalent), then re-run the install.

rcf init asks you for the project name and nothing else. Then restart your coding-agent session in that directory. The order matters: harnesses read .mcp.json and their instructions file at session start, so init has to have run first.

What rcf init just did

• Scaffolded the document chain under rcf/: placeholder documents for the product, its requirements, its architecture and its build queue, there for your agent to fill in.
• Registered the rcf MCP server in .mcp.json, so your agent gets the tools.
• Wrote a managed instructions block into your agent's instructions file: CLAUDE.md if it already exists; otherwise AGENTS.md if that already exists; both files are created only when neither is present.
• Seeded a knowledge space at rcf/knowledge/, the project's memory between sessions.

That is the whole survey. Init is safe to run in a repository that already has code: it touches only the paths above plus a managed block in .gitignore, and it never reads or writes your source. Adding RCF Lite to an existing repository sets out that contract in full and shows you how to prove it.

Ask it to build

Paste this into the session, with your own idea in the brackets:

AII want to build [describe your product idea in a sentence or two]. Let's get started.

What the agent will do next

First it checks the state of the project's documents and the work queue; that check is its habit at every session start, not something you ask for:

AIShow me the state of the document chain.

Terminalrcf define validate
rcf build queue

Then it walks its elicitation playbook with you: plain-language questions about the problem, who it is for, what done means, and where the thing will run, working through the chain one document level at a time. It authors and validates each level from your answers as the conversation progresses rather than drafting the whole tree in one pass, so you see the shape land document by document. When the chain is drafted, the agent offers you a review before the first build starts; whether you take that review or wave it through is your call.

So this is what success looks like: your agent asking questions before it authors, and writing each new document from what you just told it. Incremental drafting through the elicitation is expected; jumping straight into a full-tree draft without asking is the failure mode. If it is interviewing you about your product before writing anything, the wiring took.

If something is off

• The harness did not pick up the wiring. It read its config before rcf init ran. Restart the session so it re-reads .mcp.json and the instructions file.
• The agent starts drafting the tree without asking you anything. The instructions block did not load. Run rcf doctor to diagnose the drift, then rcf doctor --fix to apply the supported safe repairs, and restart the session.

Where next

Driving is the supervision craft: what to look at, what to ask, and when to step in. And the rules your agent is now following are no secret: they are the managed block init wrote into your agent's instructions file, in your own repository, readable any time. If you want to read them here first, the harness block publishes the same text.