Skip to content

amElnagdy/delegate-skills / skills/cursor-delegate

cursor-delegate

Unverified

Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use Cursor to implement/fix/refactor" — or wants to run a queue of coding tasks through Cursor while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.

Cursor Delegate

You are the orchestrator. Hand a bounded coding task to a separate implementer — the Cursor Agent CLI — then review what it produced and land it yourself. You write the brief and own the judgment; Cursor does the typing in its own session; you verify and commit.

The loop needs only a shell command and file access, so any comparable orchestrator can drive it.

When NOT to use this

  • The task is small enough to do inline; delegation overhead is not worth it.
  • The cursor-agent CLI is not installed or authenticated (run cursor-agent login).
  • You want to write the code yourself, or you only need Cursor's opinion on code you wrote (a --read-only dispatch covers that — see below — but a plain review may not need delegation at all).

Prerequisites (check once)

  1. cursor-agent --version succeeds. If not, follow the installer for your platform at cursor.com/cli, inspect what it will run, and authenticate with cursor-agent login.
  2. cursor-agent status shows you logged in.
  3. You are in (or will point --cd at) the target git repository. The relay passes --trust, so point it only at repositories you trust.

Choose the model

Omitting --model uses your Cursor default (usually auto — Cursor picks). To pin one, pass --model <name> with a name from the account's live cursor-agent models output — select from that list rather than inventing a name. Parameterized forms like <name>[context=1m,effort=high] are forwarded as-is. The model that actually served the run is recorded as resolvedModel in result.json.

The loop

Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.

1. Write the brief

Cursor sees only the text you send plus what it can inspect in the workspace — no chat history or shared context. Include the goal, current state, what to change, what to leave untouched, the project's actual gates, and a report contract. Tell Cursor not to commit. Keep one task per brief. See references/writing-the-brief.md.

2. Dispatch

Use the bundled helper. It wraps cursor-agent -p, feeds the brief on stdin, captures the structured event stream, and writes result.json. (<skill-dir> is the installed folder containing this SKILL.md.)

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo
# read-only (plan mode — review/diagnosis, no edits):  add --read-only
# write-capable without automatic command approval:   add --no-force
# explicitly override Cursor's sandbox for this run:  add --sandbox enabled|disabled
# pin a model from `cursor-agent models`:              add --model <name>
# resume the most recent session:                      add --resume-last  (delta brief only)
# resume a specific session:                           add --session <id> (delta brief only)
# hard time limit (watchdog):                          add --timeout 2h  (the 30m default suits short runs; implementation briefs routinely need 1-2h)
# kill a live-but-silent run early (opt-in):           add --stall-timeout 10m  (status "stalled"; clock pauses during tool calls)
# see all options:                                     node .../relay.mjs --help

The child process's cwd pins the workspace. On Cursor 2026.07.23 or newer, use repeatable --add-dir flags only for extra workspace directories. The relay writes artifacts under the system temp dir by default and never commits. See references/dispatch-and-poll.md.

3. Wait for completion

The helper blocks until Cursor finishes. Run it with the orchestrator's background-command facility, or background it in the shell and poll for result.json. A pre-run usage error exits 2 and writes no result; a missing cursor-agent exits 127 and writes status: "cursor_agent_unavailable".

Trust process state and the working tree over a progress display. Completion means the process exited and result.json exists. Cursor's full report is the finalMessage field in result.json (also printed in full on stdout between the report markers).

Windows + hooks caveat: if the user has Cursor hooks configured (~/.cursor/hooks.json, or Claude Code PreToolUse hooks, which cursor-agent imports), dispatching from a Git Bash (MSYS) console makes cursor-agent feed PowerShell-syntax hook wrappers to bash, so every command Cursor tries to run is blocked — edits still land, gates do not run. Dispatch from a PowerShell or cmd console instead. Details: references/dispatch-and-poll.md.

4. Review — do not trust the self-report

Treat Cursor's final message and gate claims as claims:

  • Re-run the project's gates yourself.
  • Read the diff against the brief, starting with touchedFiles.
  • Run relevant guard skills if installed.
  • Round-trip migrations and grep for dangling references after removals or renames.

See references/review-and-land.md.

5. Land it

The implementer edits the working tree; the orchestrator commits. Commit only after the gates pass and the diff holds. If rework is needed, send a delta brief with --resume-last or --session <id>, then review again.

Autonomy and permissions

A fresh run defaults to write-capable with --force: Cursor runs commands without approval unless your Cursor config explicitly denies them, so ordinary gates (tests, linters, builds) run headlessly. --no-force keeps the run write-capable but withholds automatic command approval; commands that require approval are refused because a headless run cannot prompt. --read-only switches to Cursor's plan mode (read-only analysis, no edits, no --force). The relay always passes --trust to keep headless runs from stalling on the workspace-trust prompt, which is why --cd must only ever point at repositories you trust. Pass --sandbox enabled or --sandbox disabled only when you need to override Cursor's sandbox for that dispatch. The requested value is recorded as sandbox in result.json; it does not claim what Cursor actually applied. The permission mode Cursor reports is recorded as permissionMode; inspect touchedFiles and the diff after every run.

Read-only second opinions

--read-only doubles as a clean way to get an adversarial second opinion with no write risk: dispatch a brief that lists the agreed points, then each contested point with both positions, and ask Cursor to defend or concede each — deliverable in its final message, touching no files.

Authorization model

Delegation is something the human opts into. Once they have ("run this queue", "proceed"), committing verified, gate-passing work is the agreed contract. Two limits remain: surface, don't absorb (report Cursor's design decisions, defensible-but-unasked turns, and non-blocking nitpicks) and stop for scope changes (if correct completion needs going beyond the brief, ask instead of expanding the mandate). See references/review-and-land.md.

References

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall