VoxMesh: Skill for Claude Code

.github/skills/pr-review-autopilot/SKILL.md

pr-review-autopilot is a skill for Claude Code, Codex from AntaresQAQ/VoxMesh. It costs 79 tokens per session (2,292 once invoked), scanned A, original, MIT.

An automated workflow for taking one GitHub pull request from review through merge. A pull request is a proposed code change that teammates and automated checks review before it enters the main codebase.

In plain words
What is it for?
Use it to run tests and checks, update the pull request branch, create focused commits, push changes, handle review threads, wait for repeated Copilot reviews, and merge once the pull request is clean.
Why use it?
It removes the need to repeatedly check CI results, wait for Copilot reviews, respond to review comments, and merge the same pull request manually. It only operates when the user explicitly authorizes editing, committing, pushing, resolving comments, and merging.

Skill for Claude CodeCodex

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

This is AntaresQAQ/VoxMesh's own configuration. It tells Claude Code and Codex how to work on VoxMesh 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 VoxMesh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AntaresQAQ/VoxMesh. 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/AntaresQAQ/VoxMesh/main/.github/skills/pr-review-autopilot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AntaresQAQ/VoxMesh

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 pr-review-autopilot

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/antaresqaq/voxmesh/pr-review-autopilot"><img src="https://agentmods.dev/badge/skills/antaresqaq/voxmesh/pr-review-autopilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,292 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.
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 $0.00079 $0.02292
Opus 5 $0.00039 $0.01146
Sonnet 5 $0.00016 $0.00458
Haiku 4.5 $0.00008 $0.00229

Measured 10d ago against content hash 277986fd305e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-review-autopilot 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 10d 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.

.github/skills/pr-review-autopilot/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Autopilot

Own one pull request from review through merge for this repository. Continue looping until the current PR head has completed CI and GitHub Copilot review, no unresolved or new actionable comments remain, and the PR is merged.

Authorization

Use this skill only when the user has explicitly authorized each of these operations for the specified PR:

  • edit the PR branch
  • run tests, builds, lint, type checks, and E2E checks
  • create focused commits
  • push the branch
  • reply to and resolve review threads
  • wait for repeated GitHub Copilot reviews
  • merge the PR after the stable-clean gate passes

Naming this skill alone does not override repository rules that require operation-specific confirmation. The invocation must explicitly authorize commit, push, and merge for this PR. Otherwise, do not use this skill and do not infer authorization.

Do not amend, rebase, force-push, or merge a different PR. Follow repository instructions and any stricter current-session rules. Include repository- or session-required commit trailers.

Inputs

Determine from the user request or current branch:

  • repository owner/name
  • pull request number
  • PR head branch and SHA
  • base branch
  • repository validation command
  • repository merge method

If the PR is not explicit, resolve it from the current branch with gh pr view. Stop only if multiple PRs are genuinely ambiguous.

Core Invariants

  1. Never claim completion while a review or required check for the current head is pending.
  2. Never merge with an unresolved review thread, failing required check, conflict, draft state, or blocking review decision.
  3. Never treat an old clean review as valid after pushing a new commit. The clean review must cover the current head SHA.
  4. Inspect review summaries as well as published threads. GitHub Copilot may place useful findings under Suppressed comments without creating a thread.
  5. Fix valid findings at the root cause. For incorrect, stale, or conflicting findings, reply with concrete evidence before resolving.
  6. Preserve user changes and keep fixes scoped to the PR.
  7. Use targeted validation while iterating and the repository's full required validation before each final push intended for merge.
  8. A successful workflow/check run is not proof that no comments were added. Always fetch reviews and threads after the Copilot review job completes.

Read the full file on GitHub · 324 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. 10d ago First seen · 324 lines · 79 tokens per session scan A 277986fd305e

Subscribe to this mod's changes

pr-review-autopilot is a skill published in the GitHub repository AntaresQAQ/VoxMesh (1 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 2,292 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 2026-08-31.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

oss-maintainer

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

debpalash/VoiceStudio · 55 tokens