Commands and the Council Fan-Out
A command turns a repeatable multi-step job into one slash trigger.
Use the right surface
After this you can pick Commands for the right job and define done.
Done means you can create a command and run a Council fan-out from the slash menu.
Use Commands when you keep retyping the same multi-step prompt, such as run tests, fix CI or open a PR. Keep the boundary narrow.
Start small. Name the job, attach the context that proves the point and decide what evidence would make the output trustworthy.
Read the loop before touching the controls. The first beat frames the work, the second uses Cursor, the third checks the result and the fourth leaves a handoff someone else can inspect.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
Run this loop in a real repo.
- Entry point
- A
.cursor/commands/directory in your repo and the slash menu - Source
- Cursor field-engineering sessions on commands and the Council command pattern
Use the source as the product reference.
Ask Cursor for an output you can inspect.
If the output cannot be checked, narrow the task before you continue.
A good run leaves a file, setting, screenshot, command result or written claim you can verify.
Takeaway. Done means you can create a command and run a Council fan-out from the slash menu.
Self-check
QWhen should you reach for Commands?
Run it
After this you can do the task with clear scope and one proof point.
Treat this as a short practice loop, not a product tour. The task should be small enough that you can inspect the result without trusting the summary.
- 1Spot a multi-step prompt you repeat and save it as a Markdown file under
.cursor/commands/. - 2End the command with how to report back, for example
reply with only the PR link, so output stays tight. - 3Commit it so the whole team gets the same command in their slash menu.
- 4For research, write a Council command that spawns several sub-agents on one question and has a final agent merge their findings.
The exercise is complete only when the proof matches the requested outcome. If the proof is weak, reduce the scope or fix the context instead of adding more instructions.
Keep the task small enough to review.
The command file is committed and a teammate can run it.
Takeaway. Stop when you have proof: Your command runs end to end from the slash menu and reports back the way you asked..
Self-check
QWhich habit makes this workflow safe to use on a real project?
Check it
After this you can find the first failed check before changing tools.
Verification decides the next move.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
Pick a row to see what to look for.
Use the first failure signal as the next prompt. Broad retries usually make the run noisier; a narrow retry gives Cursor a concrete repair target.
No proof means more checking.
Use a real repo or admin setting. Save the prompt, context and proof.
Takeaway. If it fails, find the first failed check.
Self-check
QThe workflow failed. What is the best first move?