`mode: plan` 'explores and drafts a plan before coding' (v1 docs).
Estimated cost per run
~$0.01 runner + Cursor plan usage (UNVERIFIED)
Estimated, not measured.
Basis. 1 runner min x $0.006/min GitHub-hosted Linux 2-core (docs.github.com/en/billing/reference/actions-runner-pricing); agent compute billed against Cursor plan/usage pool — not quantified, UNVERIFIED.
Verification
Last checked Oct 16, 2026.
inputs checked against source docs; workflow not executed.
How the plan gets back onto the issue (comment) is not handled by the API — you'd poll GET /v1/agents/{id}/runs/{runId} for `result`. Not implemented here.
Labels
planning
Workflow YAML
Copy the file as-is. Highlighting is only for reading.
workflow.yml
1name:Cursorplanonlabel2on:3issues:4types:[labeled]5jobs:6plan:7if:github.event.label.name=='planning'8runs-on:ubuntu-latest9steps:10- env:11CURSOR_API_KEY:${{ secrets.CURSOR_API_KEY }}12ISSUE_URL:${{ github.event.issue.html_url }}13REPO_URL:https://github.com/${{ github.repository }}14run:|15 jq -n --arg t "Read $ISSUE_URL and draft an implementation plan. Do not write code." --arg r "$REPO_URL" \16 '{prompt:{text:$t}, repos:[{url:$r}], mode:"plan", name:"plan"}' > body.json17 curl -sS --fail -u "$CURSOR_API_KEY:" -H 'Content-Type: application/json' -d @body.json https://api.cursor.com/v1/agents