Using the team, rung by rung.

Capture freely with /idea. Pressure-test one with /canvas, filled a few cells at a time rather than all at once. You never pick a framework: you answer questions, and the frame is a view you switch. The same answers render as the Humane Product Canvas (the default), a Lean Canvas, or a Business Model Canvas; /canvas --frame lean re-renders what you've already said rather than interviewing you again, and a cell you haven't answered shows as _(not yet)_ in every frame instead of quietly disappearing to make a view look complete. A fourth frame, /canvas --frame onepager, folds the same answers into the smallest thing you can hand to somebody outside, and it refuses to render at all until at least one piece of evidence is on file.

Commercial prompts are folded into every cell (who exactly has the problem, what they use instead, who pays and why). And two questions ride along in all three frames, not just the humane one: who this could harm or exclude, and the principles you'll hold when holding them costs you something. Un-defaulting the framework was never meant to make those optional.

Then find out if it's real, which is the half that doesn't happen in the editor. /interview preps one 15-minute conversation under Mom-Test discipline (past behaviour, their life, no pitching) and debriefs your notes into graded records afterwards. /pretotype builds the fake door: a real page you can put in front of real people, published in one turn, so demand gets tested while it still costs an afternoon. Both live here, at the first rung, because testing whether anyone wants the thing is not an advanced move, and holding it back until MVP had it arriving after the build it was meant to prevent.

Work out who it's for with /persona: your target user as a voice you can actually consult, both to decide what to build and to react to what you built. It carries a visible ledger of how much of that user is real evidence and how much is still a guess, and it starts at all guess. It's a way to sharpen the questions you take to a real person, never a way to skip them. Record what you learn with /evidence, and what you chose with /decide. A project that lives here forever is a legitimate project.

Adds the spec discipline (/spec, with validated-learning and evals fields) and the smoke gate, the first rung where "is it alive?" becomes a gate rather than a habit. Design tokens get scaffolded here too, the moment there's real UI, so style never gets locked into code. The designer arrives with MVP — one designer for both halves, what it looks like and what it does: /design-review before the code, and again once there's a screen.

It's also where the questions start pointing outward. /comp-eval goes and finds out who else is solving this (features, pricing, and the honest “why they might win”), then keeps it as a living set you add names to, rather than a slide you drew once. /roadmap weighs what to build next into a short bet-list with a mandatory no-list, because a roadmap that only says yes isn't a decision.

Some verbs wait until they're earned. Retention, pricing, health and the first dollar arrive once a feature has shipped; the AI-cost and failure-state set when your code first calls a model; /design-tokens-init when there's a screen. Until then they aren't in your slash menu at all, so a founder with one idea isn't read a menu of verbs about pricing. And a project can end at any rung. /sunset exists because quitting well is a skill, and a tool that only knows how to grow things is lying to you about how this usually goes.

V1 hires nobody. It's the one rung that adds no agents at all, and that's deliberate. By now you have the team; what you don't have is a way to see what you've already made. So it adds two views. /design-library generates a gallery of your components, every variant, all five states, from your code, plus a reuse index the agent reads before writing a new one. /board sequences work across features instead of within one.

Adds /incident. Deliberately thin: most projects should never need this rung.

mentor-cofounder coaches dividing work across different skill sets, decision rights, and the hard conversations about roles, pace and equity. It serves the partnership as a unit and never takes a side.

If real work has happened and you have never recorded a single decision together, the conscience says so once: "you've been building a while and haven't decided anything jointly; are you two actually deciding this together, or in parallel?" It notices that through the artifacts, an empty decision log, and never by asking "how's your teamwork?", because self-report is precisely what is blind to this drift. It is deliberately conservative, because a quiet decision log can just mean you decide on a call; if that is you, boss conscience mute coordination and it stops. It surfaces the seam. It never says whose fault it is, and it never scores your equity.

The full teams guide