Interactive Agent, Plan and Ask Modes
The CLI has modes too; use them with the same routing discipline.
Use the right surface
After this you can pick Cursor CLI interactive mode for the right job and define done.
Done means you can run interactive CLI sessions without losing mode choice or context hygiene.
The same agent loop can run in a terminal, script, CI job or SDK-backed internal tool.
Use Cursor CLICursor's command line: the full agent, all modes and models, in the terminal and pipeable into scripts and CI. interactive mode when you need a terminal-first session with readable context and review control. 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
- agent, agent prompt, Ask, Plan, review UI, @ context and session commands
- Source
- CLI usage docs
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 run interactive CLI sessions without losing mode choice or context hygiene.
Self-check
QWhen should you reach for Cursor CLICursor's command line: the full agent, all modes and models, in the terminal and pipeable into scripts and CI. interactive mode?
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.
- 1Choose Ask, Plan or Agent before starting.
- 2Attach files, folders or docs with @ context where needed.
- 3Use review UI and summaries to keep the session inspectable.
- 4Resume or continue only when the task context still matches.
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 CLI session has the same verification standard as editor work.
Takeaway. Stop when you have proof: Mode choice matches the task..
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?