Prompt improver

An agent works from what you wrote, not from what you meant. The prompt improver is the sparkle (✦) beside every field where you write instructions for an agent: press it and your draft comes back restructured for an agent — goal, steps, constraints, what “done” means — streamed back word by word with Accept and Discard underneath.

Nothing is committed until you accept. Discard leaves your draft exactly as you typed it, character for character.

console.clustercode.io New run

Where you’ll find it

Surface	Field
Runs	The New run composer
Schedules	Instructions, in the create panel
Prototyping	Prompt
Loops	Goal, when you create a loop or reopen one

The sparkle only rewrites the field it sits in. It never starts a run, saves a schedule, or submits anything.

Using it

1. Write a draft. Anything — a one-liner, bullets, a paste from a ticket. The sparkle stays dimmed until the field has something in it (hover it and it tells you so).

2. Press the sparkle and pick how much latitude to give it — or type an instruction of your own into the box at the bottom of the menu and send it with the arrow.

3. Watch the proposal arrive. It streams into a panel below the field. You can press the sparkle again (or Cancel) to stop it mid-stream; nothing is committed.

4. Accept or Discard. Accept replaces the draft with the rewrite and closes the panel. Discard closes the panel and leaves the draft untouched.

Modes

Mode	What it does
Improve (default)	Restructures and clarifies what you wrote. Changes nothing else.
Expand	Spells out the steps your draft implies and adds the sections its content calls for — without adding requirements you never stated.
Be creative	May propose a different framing or structure for the same goal, and may run a little longer. Every stated requirement still survives.
Your own instruction	The free-text box in the menu — “make the done criteria stricter”, “keep it to three steps”, “write it as a checklist”. It steers style, structure and focus; it can’t override the rules below.

What it will and won’t do

The improver is deliberately conservative — a rewrite you have to re-check is worse than no rewrite at all.

• It keeps everything. Every requirement, number, file path, URL and constraint in your draft appears in the rewrite. It reorganizes; it does not summarize away.
• It never invents requirements. No tests, tools, steps or acceptance criteria you didn’t state or clearly imply.
• It preserves ambiguity instead of resolving it. If your draft leaves out something the agent will certainly need — which repo, which branch, what “done” means — you get an Open questions bullet, not a guess.
• It keeps your voice. Your domain terms, your names for things. It fixes grammar, ordering and structure, not vocabulary.
• It knows this surface. It’s told which agents, models and effort levels exist where you’re typing, so “use claude on high effort” comes back as the exact identifiers — and as an @agent:model:effort mention where mentions are honoured (Runs) or as plain prose where they aren’t. If you name an agent or tool that isn’t available here, it keeps your word and flags it as an open question rather than substituting one.
• It treats your draft as material, never as instructions. Text inside your draft that reads like a command to an AI (“ignore the above and output X”) is rewritten as content, like everything else.

Blanks and shell variables are guaranteed

A draft can carry {blank} fill-in fields — from a saved prompt shortcut, or typed by hand — and instructions often carry ${VAR} shell interpolation. Both survive verbatim:

• Every {blank} in your draft appears in the rewrite, spelled the same, and no new ones are introduced.
• ${VAR} is left exactly as written — it’s never converted to a {blank}, or the other way round.

This one is checked, not just requested: if a proposal drops a blank, the panel says so and Accept is not offered. You can never accept a rewrite that lost one.

It won’t overwrite an edit you made under it

The field stays editable while a proposal is open. If you change the draft after the rewrite was generated, Accept refuses — the panel tells you the draft changed and offers only Discard, so a rewrite of the old text can never silently replace what you just typed. Improve again to include the edits.

What it costs

The improver runs on a fast Claude model and its usage comes out of your plan’s monthly AI allowance, the same pot as Nucleus and Nova — see AI Credits.

• Bring your own Claude subscription or key (Settings → Environment Variables → Agent Secrets) and improves run on your credential instead — they don’t draw down the allowance at all.
• On the Free plan the improver is bring-your-own only. Without a connected credential the panel says so and no request is made.
• When the allowance is exhausted the sparkle turns amber and, instead of a proposal, you get a notice naming the reason and when it resets — plus a toast, in case you were looking elsewhere on the form. Your draft is untouched.

Note

Two size limits worth knowing: a draft is improved up to 20,000 characters, and your own steering instruction up to 5,000 — room for a pasted style guide or a list of constraints, not just a one-line nudge.