Borrowing it
Nothing to install: this file belongs to agigante80/actual-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agigante80/actual-mcp-server/main/.claude/skills/merge-pr/SKILL.mdgit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote 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/skills/agigante80/actual-mcp-server/merge-pr)<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/merge-pr"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/merge-pr/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/skills/agigante80/actual-mcp-server/merge-pr"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/merge-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00191 | $0.01628 |
| Opus 5 | $0.00096 | $0.00814 |
| Sonnet 5 | $0.00038 | $0.00326 |
| Haiku 4.5 | $0.00019 | $0.00163 |
Grade A, and why
merge-pr 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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge PR (develop-first, never direct)
A request to "merge a PR" is treated as a request to INTEGRATE the PR's change
through the normal process, not to click merge. Direct PR merges are forbidden
here: most PRs (Dependabot especially) target main, and merging them straight
in would bypass the develop-first workflow, skip the version bump and the live
/local-env full gate, and re-diverge main from develop. Every change earns
its way to main the same way: develop -> ticket -> gate -> implement -> bump ->
/local-env full -> CI green -> (later) an explicit release.
The hard rule
- NEVER run
gh pr merge(or merge the PR in the UI) as part of this skill. - A version bump and a passing
/local-env fullare NON-NEGOTIABLE prerequisites for anything that will eventually reachmain. A PR provides neither on its own, so it must go through the ticketed pipeline first. - The original PR is CLOSED as superseded once its change lands on
develop. It never merges tomain.
Inputs
The PR number (extract it from the request; if absent, ask). Everything happens
on develop; main is untouched.
Pipeline
Phase 1: Inspect the PR
Read it so the integration ticket is accurate and the change is reproducible:
gh pr view <n> --json title,baseRefName,headRefName,labels,author,url,mergeable,statusCheckRollup
gh pr diff <n> # the actual change
gh pr diff <n> --name-only # files touched
Classify it: dependency bump (Dependabot) vs code change; security/CVE driver
(check npm audit for the package and the PR's referenced advisories); which
files; whether the dep is direct or transitive (npm ls <pkg>). Note the
resolved target versions from the lock diff so they can be reproduced exactly.
Phase 2: Refuse the direct merge, explicitly
State plainly that the PR will not be merged directly, and that its change is
being routed through the develop-first pipeline (ticket + gate + bump +
/local-env full). This is the policy, not a limitation.
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.
- 11d ago First seen · 138 lines · 191 tokens per session scan A 8c95280296aa
merge-pr is a skill published in the GitHub repository agigante80/actual-mcp-server (54 stars, last pushed yesterday), licensed MIT. It adds 191 tokens to every session and 1,628 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
developer_pr_prep
Prepare branches, diffs, tests, and GitHub PR text from Developer Studio.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
openclaw-pr-batch-sweep
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.