Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/emaraschio/cursor-commandsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/emaraschio/cursor-commands/merge-open-prs)<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/merge-open-prs"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/merge-open-prs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/merge-open-prs"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/merge-open-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.00629 |
| Opus 5 | $0.00010 | $0.00315 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
merge-open-prs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Review, verify, approve, and merge open pull requests in the current repo. Docker verification and batch cap of 10 are on by default.
Defaults
| Setting | Default | Override |
|---|---|---|
| Verification | Docker-first | --no-docker |
| Batch size | 10 PRs | --limit N |
| Merge | auto_if_green | --dry-run |
Steps
- Read
.cursor/skill-contracts/merge-open-prs/SKILL.mdfor the full contract (preflight, inventory, babysit, review, verify, gate, merge, post-smoke); if that file is missing, read~/.cursor/skill-contracts/merge-open-prs/SKILL.md. - Parse flags:
--dry-run,--no-docker,--limit N, optional PR number. - Execute phases 0 to 5 in order. Per PR, follow babysit at
~/.cursor/skills-cursor/babysit/SKILL.md. - Emit plan table before processing and summary table after post-batch smoke.
Anti-patterns
- Merge only when the gate passes. Trigger: a PR looks ready. Wrong: merging without local verification or a passing auto_if_green gate. Correct: run local verify, confirm CI, reviews, and threads, then merge only if every gate check passes. Reason: merging unverified code can break the default branch for everyone.
- Do not silently skip Docker. Trigger:
docker infofails and the user did not pass--no-docker. Wrong: falling back to host test heuristics without telling the user. Correct: stop with a blocker and suggest--no-dockeronly if they accept non-Docker verification. Reason: a silent fallback verifies the PR differently than intended and can mask failures. - Keep the batch bounded. Trigger: more open PRs than the limit. Wrong: processing an unbounded queue of PRs. Correct: process up to
--limit(default 10) FIFO and report the deferred count. Reason: runaway merges are hard to review and hard to undo.
Examples
/merge-open-prs/merge-open-prs --dry-run/merge-open-prs --limit 3/merge-open-prs 42
Maintainers
Behavioral eval: .cursor/skill-contracts/merge-open-prs/eval/cases.md. Ship gate: A, D, E before changing SKILL.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 47 lines · 20 tokens per session scan A 24042f223a37
merge-open-prs is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 629 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
open-pr
Create a pull request for the current branch following the the team's standard PR template.
handle-pr-comments
Fetch all PR comments, classify by severity, and present for user approval before acting.
self-review
Review only changed files in this branch Your primary goal is to provide valuable, trustworthy feedback while avoiding false positives and low-impact commentary.
create-pr
Commit changes and create a PR with proper formatting.
back-to-master-delete-branch
Cleanup current branch and switch to default branch with latest changes.