review-requests

review-requests is a skill for Claude Code from in-the-loop-labs/pair-review. It costs 83 tokens per session (567 once invoked), scanned A, original, Apache-2.0.

A workflow for finding GitHub pull requests where you are directly asked to review the code and opening them in a pair-review tool for AI-assisted analysis. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to find recently updated open pull requests needing your review, then start pair-review analysis for up to ten of them.
Why use it?
It saves time spent searching GitHub for pending review requests and opening each review manually. It also excludes requests made only to a team.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pair-review plugin — 5 skills shipped together

Good fit Use it to find recently updated open pull requests needing your review, then start pair-review analysis for up to ten of them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/in-the-loop-labs/pair-review/review-requests
Install

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.

Any agent
npx skills add in-the-loop-labs/pair-review --skill review-requests
Clone the repo
git clone --depth 1 https://github.com/in-the-loop-labs/pair-review

Made for: Claude Code.

Or install pair-review, the plugin that ships this one along with the rest of its 5 skills.

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-requests

README.md
[![agentmods](https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-requests/github.svg)](https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-requests)
Your own site
<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-requests"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-requests/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-requests

Your own site · 80×15
<a href="https://agentmods.dev/skills/in-the-loop-labs/pair-review/review-requests"><img src="https://agentmods.dev/badge/skills/in-the-loop-labs/pair-review/review-requests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 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 $0.00083 $0.00567
Opus 5 $0.00042 $0.00283
Sonnet 5 $0.00017 $0.00113
Haiku 4.5 $0.00008 $0.00057

Measured 12d ago against content hash 550c4a65e568, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-requests 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 12d 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.

plugin/skills/review-requests/SKILL.md · 58 lines

What it actually says

Review Requests

Batch-open outstanding GitHub review requests in pair-review with AI analysis.

Workflow

Phase 1: Discover pair-review server

Call mcp__pair-review__get_server_info to get the pair-review web UI URL. If the server is not running, inform the user and stop.

Phase 2: Find pending review requests

Use user-review-requested:@me (not review-requested) to find only PRs where the user was directly requested as a reviewer, excluding team-based review requests. The gh search prs CLI does not support this qualifier, so use the search API directly:

SINCE=$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d)
gh api "search/issues?q=is:pr+is:open+user-review-requested:@me+updated:>=${SINCE}&per_page=30" \
  --jq '.items[] | {number, title, html_url, repo: (.repository_url | split("/")[-2:] | join("/"))}'

Each result provides number, title, html_url, and repo (as owner/repo).

Phase 3: Open each PR in pair-review with auto-analysis

Limit: Open at most 10 PRs. If more than 10 are found, open only the first 10 (most recently updated) and report how many were skipped.

For each PR found (up to the limit), open it in the browser with the ?analyze=true query parameter, which automatically starts AI analysis when the page loads:

open "{server_url}/pr/{owner}/{repo}/{number}?analyze=true"

where {owner}/{repo} comes from the repo field split on /.

No MCP calls per PR are needed — the ?analyze=true parameter handles triggering analysis.

Phase 4: Report

Summarize what was done:

  • How many PRs were found with pending review
  • List each PR opened in pair-review with title and URL
  • If no pending review requests exist, say so
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. 12d ago First seen · 58 lines · 83 tokens per session scan A 550c4a65e568

Subscribe to this mod's changes

review-requests is a skill published in the GitHub repository in-the-loop-labs/pair-review (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 567 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.