electrobun: Skill for Claude Code

.skills/review-pr/SKILL.md

review-pr is a skill for Claude Code, Codex from blackboardsh/electrobun. It costs 87 tokens per session (2,674 once invoked), scanned A, original, MIT.

A guide for reviewing a GitHub pull request, which is a proposed code change shared for review. It focuses on understanding the change and checking whether it is safe to run or merge from a security and runtime perspective.

In plain words
What is it for?
Use it after someone provides a pull-request link and asks for a security, runtime-safety, or merge-readiness assessment.
Why use it?
It provides a consistent way to decide whether a proposed change is safe and whether it should be merged, closed, or replaced with a narrower fix.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is blackboardsh/electrobun's own configuration. It tells Claude Code and Codex how to work on electrobun itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything electrobun configures →

About the project

Electrobun is a toolkit for building, updating, and shipping small cross-platform desktop applications written in TypeScript. Developers use its Hutch command-line tool, JavaScript runtime, and native platform layer to create and build these apps.

blackboardsh/electrobun · 12,766 stars · on GitHub · blackboard.sh

Reuse

Borrowing it

Nothing to install: this file belongs to blackboardsh/electrobun. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/blackboardsh/electrobun/main/.skills/review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/blackboardsh/electrobun

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackboardsh/electrobun/review-pr/github.svg)](https://agentmods.dev/skills/blackboardsh/electrobun/review-pr)
Your own site
<a href="https://agentmods.dev/skills/blackboardsh/electrobun/review-pr"><img src="https://agentmods.dev/badge/skills/blackboardsh/electrobun/review-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.

agentmods 80×15 button for review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackboardsh/electrobun/review-pr"><img src="https://agentmods.dev/badge/skills/blackboardsh/electrobun/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.02674
Opus 5 $0.00044 $0.01337
Sonnet 5 $0.00017 $0.00535
Haiku 4.5 $0.00009 $0.00267

Measured 9d ago against content hash a00ef21f6c0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-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 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.

.skills/review-pr/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR

Overview

Use this skill when the user pastes a PR link and wants a security-first assessment before running, testing, or merging it. The goal is to understand the PR intent, inspect the diff, decide whether it is safe to run, and then help with feedback, fixes, merge readiness, or a close recommendation.

This skill is discussion-first, but it should still support fast maintainer throughput. Loading the skill does not authorize guessing which PR to inspect from local branches, refs, or open worktrees. Wait for the user to paste a PR URL, review that one PR, give a concise rundown, and discuss it with the user before taking any local git actions beyond basic repository state checks.

If the maintainer is clearly trying to fly through PRs, keep the discussion short and move quickly to a decisive recommendation:

  • Merge
  • Close
  • Supersede with direct fix

Use Supersede with direct fix when the underlying issue is legitimate but the PR implementation is too broad, changes the wrong behavior, or is close but not quite right. In that case, offer to implement the narrower fix locally and draft the close comment for the maintainer.

Workflow

0. Wait for the PR URL

  • Do not infer the target PR from local branches such as pr-*, from recent git history, or from the current worktree.
  • Review one PR at a time, in the order the user pastes them.
  • If no PR URL has been pasted in the current discussion, ask for it and stop there.
  • After the user pastes a PR URL, read it first and respond with a rundown before fetching refs, checking out branches, or diffing local PR branches.

1. Read the PR first

  • Read the PR description and discussion before touching the branch.
  • Capture the claimed intent, test plan, linked issue, and any mention of permissions, downloads, shell execution, networking, updater behavior, or native code.
  • If the description is missing or inaccessible, say so explicitly and continue with the code review.
  • The first substantive reply after reading should be a rundown for discussion with the user:
    • what the PR claims to do
    • what parts of the codebase it likely touches
    • which runtime host or VM should be used for build/run/test work
    • obvious security or runtime-risk areas to focus on
    • any missing context or questions
  • Do not assume the user wants immediate local branch inspection. Discuss first, then inspect locally if it will materially help the review.
  • If the user is clearly in rapid triage mode, keep this rundown to a few lines and then continue with local diff inspection.

Read the full file on GitHub · 212 lines

Changes

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.

  1. 9d ago First seen · 212 lines · 87 tokens per session scan A a00ef21f6c0a

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository blackboardsh/electrobun (12,766 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 2,674 once invoked, about $0.0004 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.