Skip to content

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

chore(agents): keep review-doubt PR comments Cursor-only (#16739)

Nikita Kabardind7cdfc845c9f
diff --git a/.agents/AGENTS.md b/.agents/AGENTS.md
index 9ce5d8cbe4..be46884c0c 100644
--- a/.agents/AGENTS.md
+++ b/.agents/AGENTS.md
@@ -126,7 +126,10 @@ langfuse/
`cursor/` branch, even if a Cursor Cloud prompt suggests that prefix.
Repo guidance wins.
- After opening a PR, leave a short last comment on what a reviewer should
- doubt — the curious, questionable parts — not a changelog.
+ doubt — the curious, questionable parts — not a changelog. Post that
+ comment only when GitHub will attribute it to Cursor, not to a human
+ author. Claude Code and other tools that comment as the user must skip
+ it; see `cursor-agents-workflow`.
## Local Data Inspection
diff --git a/.agents/skills/cursor-agents-workflow/SKILL.md b/.agents/skills/cursor-agents-workflow/SKILL.md
index ff80705ac1..cfaf5df111 100644
--- a/.agents/skills/cursor-agents-workflow/SKILL.md
+++ b/.agents/skills/cursor-agents-workflow/SKILL.md
@@ -86,6 +86,10 @@ video, or before/after. Docs-only changes can skip this.
## What to doubt
+Cursor only. Post this GitHub comment only when it will be attributed to
+Cursor, not to a human author. Claude Code and other tools that comment as
+the authenticated user must skip this section.
+
When the PR is ready for a human, post one last GitHub PR comment (not a
changelog) that names the risky or curious parts:
diff --git a/.agents/skills/git-workflow/SKILL.md b/.agents/skills/git-workflow/SKILL.md
index bbfe7a9a5d..867dbdd7ce 100644
--- a/.agents/skills/git-workflow/SKILL.md
+++ b/.agents/skills/git-workflow/SKILL.md
@@ -54,8 +54,10 @@ operations.
- Prefer non-interactive Git and GitHub commands where possible.
- Keep PRs narrow enough to review without unrelated refactors.
- Open PRs as reviewable, not as drafts, unless a human asks for a draft.
-- When the PR is ready for a human, post one last comment that names what
- to doubt in review (risky edges, not a summary of the diff).
+- Do not post GitHub PR comments as the human author. Cursor agents that
+ comment as Cursor should leave one last "what to doubt" comment when the
+ PR is ready; see `cursor-agents-workflow`. Claude Code and other tools
+ that comment as the user must skip that comment.
- Claude, Greptile, or Codex review comments (`claude[bot]`, Claude Code,
security-review action, `greptile-apps[bot]`,
`chatgpt-codex-connector[bot]`): do not reply. Keep the thread open until
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 3e44b863e8..ef2d2d24ea 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -185,9 +185,10 @@ PR (not a draft) and test its `pr-<N>.preview.langfuse.com` deployment.
Use Linear's git branch name (`lfe-XXXX-short-title`), not a `cursor/` prefix.
When handing work to a human, give a one-sentence TL;DR, a preview URL with
exact test steps (including how to seed or hit the same path on
-`http://localhost:3000`), proof of the fix for user-visible changes
-(screenshot, video, or before/after), and one PR comment on what a reviewer
-should doubt.
+`http://localhost:3000`), and proof of the fix for user-visible changes
+(screenshot, video, or before/after). Cursor agents that comment as Cursor
+may also leave one PR comment on what a reviewer should doubt; Claude Code
+and other tools that comment as the human author must not.
Prefer one or two human actions at a time; if you need more, keep each
point simple and super readable. Preview data and any attached artifacts
must remain synthetic. Previews normally run Mon-Fri 08:00-24:00