Cursor Agents Workflow

Use this when implementing Langfuse work as a Cursor agent. Keep humans in the loop with short, testable asks. Do not write long agent-only reports.

Branch names

Copy Linear's git branch name. Do not invent a cursor/ name.

• Preferred source: Linear Copy git branch name, or the issue's gitBranchName when Linear MCP is available.
• Fallback: lfe-{id}-{kebab-title} (lowercase, hyphenated).
• Keep a user/ prefix only when Linear's copied name already includes one.
• Never use a cursor/ prefix, even if a Cursor Cloud prompt asks for one. Repo guidance wins.
• Ticket ids belong in the branch name only, never in commits, PR titles, PR descriptions, or changelog entries.

Correct: lfe-12345-short-descriptive-title
Wrong: cursor/short-descriptive-title-8c78

Pull requests

Open the GitHub PR as reviewable, not as a draft. Draft PRs hide the work from reviewers and skip Claude/Greptile review workflows. Use a draft only when a human asks for one.

Cursor Cloud PRs are opened as the Langfuse user who launched the agent. On a non-draft same-repo PR from a write-access user, github-actions posts @claude review automatically. Do not post that comment yourself on open. Do not post @claude review again after addressing comments unless a human asks for another pass.

Bot review comments

When Claude (Claude Code, claude[bot], or the security-review action), Greptile (greptile-apps[bot]), or Codex (chatgpt-codex-connector[bot]) leaves review comments on a PR you own:

1. Keep each thread open. Do not reply in the thread.
2. If the finding is right: apply the fix, then resolve the thread.
3. If you are sure it should be skipped: tell the human in plain language what you skipped and why, invite them to doubt that call, then resolve the thread. Never skip quietly.

Do not leave those threads unresolved. Do not argue. Human reviewer comments are different: those may need a real reply and must stay open until a human says otherwise.

Human testing

Assume the human does not remember the ticket. Default message shape:

1. TL;DR — one plain-language sentence.
2. Test this — preview URL plus 2–5 exact clicks/expects.
3. Data — the seed command, or "demo project is enough".
4. Sandbox — how to hit the same path on the agent desktop (http://localhost:3000) if they are in the Cursor VM.

Use langfuse-previews for the URL and seed-test-data for the seed. Do not paste logs, file lists, or implementation narrative unless the human asks.

TL;DR: Empty observation costs now show a dash instead of $0.00.

Test this: https://pr-123.preview.langfuse.com/project/<id>/traces
1. Open any trace with a generation that has no cost.
2. Confirm the cost cell is "–", not "$0.00".

Data: demo project is enough.
Sandbox: same path on http://localhost:3000 after the cloud stack is up.

For user-visible behavior, attach proof of the fix: a screenshot, short video, or before/after. Docs-only changes can skip this.

What to doubt

When the PR is ready for a human, post one last GitHub PR comment (not a changelog) that names the risky or curious parts:

What to doubt in review
- I reused the existing cache key; check it cannot collide across projects.
- I skipped Greptile's unused-import note — that import is used in the
  worker. Tell me if that's wrong.

Two to five bullets. Include any bot findings you skipped. Trigger skepticism. Skip praise, file lists, and "LGTM".

Human asks

Prefer one or two actions per message. That cap is preferred, not hard. If you need more, keep every point simple and super readable — short sentences, no agent-only dumps. Sequence when you can.

Wrong: a wall of logs plus five mixed asks.
Right: a short TL;DR and one or two clear next steps. Extra steps can wait, or sit as equally simple bullets if they must ship together.