Cursor CLI (subagent / task delegation)

What is it

This skill teaches your agent to use an agent from another vendor as a subagent.

Almost every coding agent has a headless mode. Headless mode runs the agent from the terminal with one command and returns the answer to stdout. This skill gives the command pattern for one such agent, and the protocol to transfer enough context with the task.

You stay the main agent. You keep the plan, the decisions and the conversation with the user. The subagent does one bounded task and reports back.

When to delegate

• The user asks for it. The user names another agent, or asks for a second opinion.
• Large or multi-step work. The task covers several files, phases or checkpoints.
• Code review with a fresh mind. Another agent reviews the work with a different lens and no memory of the decisions that produced it.
• Planning that needs different ideas. A second agent proposes options that you did not consider.
• An internal council. Several subagents answer the same question, and you compare the answers.
• Deep research. The other CLI has web search, web extraction or browser automation.
• Background investigation. A long task runs in the background while you continue in the foreground.

When not to delegate

• Small or single-step tasks. One or two edits, or a short explanation, are faster in this thread.
• Tight feedback loops. The user wants quick back-and-forth in one conversation.
• Secrets or policy-sensitive work. Do not pipe credentials into a subagent. Redact first.
• Context you already hold. Repeating the whole plan in a prompt adds no value.
• Low return on investment. If writing the handoff costs more than doing the edit, do the edit.
• Work that needs high precision and full judgement. A subagent without your context will break a task that depends on a detail only this session knows.

Delegation and context transfer protocol

An isolated subagent saves tokens, but it splits the story. The subagent does not see this conversation. It has no memory of the goal you agreed with the user, the decisions you already made, or the paths you agreed not to touch. A poor handoff causes misread tasks, wrong assumptions about the stack or the style, and wasted edits.

Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state. A good handoff happens when you keep these practices in mind:

• Shared state handoff. The prompt carries the original goal, the decisions already made, and the explicit scope, to bridge the subagent's missing session history.
• Contextual preservation. The high-volume work stays in the isolated process, so the bulk never enters this conversation and no "split story" forms from missing history.
• Result reconciliation. What comes back is folded into this thread afterwards, so there is a single source of truth.

Write the prompt as a transfer of shared state, not as a title. Include all six fields:

Prefer sequential delegations with explicit carry-over. Parallel runs diverge unless every run gets the same briefing.

Run the subagent in the mode that does the work without asking for approval. Headless mode has nobody to answer a permission prompt. Any mode that stops to ask will stall, or return an empty answer with a success exit code. Each CLI names this mode differently — take the flag from the vendor card below.

Never call a subagent in plan mode. Many CLIs have a plan or read-only mode. That mode makes the other agent write a plan for itself, which is not what you asked for: you want its work or its answer, and you keep the planning. Plan mode also waits for someone to approve that plan, so the run comes back with nothing. If you want no file changes, keep the auto-approving mode and write "report only, no edits" in the Output field. Do not use plan mode to make a run read-only.

After the subagent returns:

• Report to the user. Give a short summary. Do not paste long logs unless the user asks.
• Reconcile the context. Record the decisions it made, the files it changed, and the open risks, so this session stays the single source of truth.

CLI failure modes

Every vendor has its own terminal rules. A headless run fails quietly more often than it fails loudly.

• Wrap the call in an external timeout. A headless CLI can stall before its own timeout starts.
• Exit code 0 is not success. If stdout is empty, treat the run as failed and read stderr. A permission the CLI could not ask for, and a prompt that never arrived, both look like success.
• Never carry a flag habit from one CLI to another. The same short flag means different things in different tools. In OpenCode, -p is --password: passing a prompt to it empties the message and the run waits on stdin forever. Confirm every flag against the CLI's own --help.
• An unrecognized-flag error means this skill is stale, not that the task is impossible. Read --help, continue with the flags that exist, and tell the user which line in this file is wrong.

Vendor card

Binary and prompt form

• Binary: agent
• Install: curl https://cursor.com/install -fsS | bash (macOS and Linux; from the vendor CLI installation page).
• Prompt form: positional. -p / --print is a mode flag ("print responses to console for scripts or non-interactive use") — it does not carry the prompt text itself. The prompt is the plain string given alongside it, e.g. agent -p --force "prompt text". A bare agent "prompt" with no -p opens the interactive interface and never returns.

Headless and output flags

Approvals and permissions

• -f, --force (alias --yolo) — "force allow commands unless explicitly denied."
• --approve-mcps — automatically approve all MCP servers.
• --sandbox <enabled\|disabled> — sandbox the run.
• What happens with nobody to answer: agent --help says -p "has access to all tools, including write and shell". It does not say what a run without --force does when a command needs approval. The vendor headless docs say changes are only proposed without --force; the help does not confirm that. Do not rely on -p alone for a no-edit run.
• --mode plan and --mode ask are read-only per --help. Do not use them for delegation (see the plan-mode rule above). For a no-edit run, write "report only, no edits" in the Output field. For a delegation that must change files, pass --force/--yolo.

Models and how to list them

Run agent models (subcommand) or pass --list-models to list the models this install accepts. Select with --model <model>. New installs default to automatic model routing.

If the user names a model, use it. Otherwise run agent models first, and consult Artificial Analysis for capability and price comparisons.

Command pattern

agent -p --force "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | CONSTRAINTS: [constraints] | VERIFICATION: [test_command] | OUTPUT: [format]" \
  --model <identifier> --trust 2>&1

Prompt examples

• Implement: agent -p --force "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | CONSTRAINTS: [constraints] | VERIFICATION: [test_command] | OUTPUT: [format]"
• Investigate (no edits needed): agent -p "GOAL: Map how [feature] works | SCOPE: [paths] | CONSTRAINTS: report only, no edits | OUTPUT: concise file:line map"
• Review: agent -p "GOAL: Review [scope] for [concerns] | CONSTRAINTS: report only, no edits | OUTPUT: findings with severity"

Docs and reference

• Flags, delegation checklist: reference.md
• Vendor documentation: https://cursor.com/docs/cli/headless and https://cursor.com/docs/cli/reference/parameters
• Checked against cursor-agent 2026.06.04 --help on 2026-11-05. Note: the previous version of this card documented --mode agent|plan|ask; the official reference only lists --mode <plan|ask> (no explicit agent value — that's simply the unnamed default) plus a --plan shorthand for --mode=plan.