agentmods.dev

github:pr-comments

github:pr-comments is a skill for Claude Code from bendrucker/claude. It costs 51 tokens per session (817 once invoked), scanned A, original, MIT.

A skill for reading, replying to, and resolving review conversations on a GitHub pull request. It can distinguish unresolved, outdated, human, and review-bot comments.

In plain words
What is it for?
Use it to find outstanding comments, check whether your review threads were resolved, reply to feedback, and clear review-bot threads after addressing them.
Why use it?
It gives you a focused view of feedback that still needs action instead of making you search the pull request manually. Filters can limit results by author or recent review activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the github plugin — 5 skills, 2 agents shipped together

not rated 18repo changed yesterday A scan 51 tokens original MIT

Good fit Use it to find outstanding comments, check whether your review threads were resolved, reply to feedback, and clear review-bot threads after addressing them.

Compare 6 skills from other repositories ↓
View source ↗ bendrucker/claude
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bendrucker/claude
Claude Code
/plugin install github

Made for: Claude Code.

Or install github, the plugin that ships this one along with the rest of its 5 skills, 2 agents.

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 github:pr-comments

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/bendrucker/claude/pr-comments"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 817 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 $0.00051 $0.00817
Opus 5.5 $0.00020 $0.00327
Sonnet 5.5 $0.00010 $0.00163
Haiku 4.5 $0.00005 $0.00082

Measured yesterday against content hash e484f4ded4f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github:pr-comments 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 yesterday.

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.

plugins/github/skills/pr-comments/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Comments

Fetch review threads from a GitHub pull request. Resolved threads are excluded by default. Outdated threads are included but marked.

Usage

bun ${CLAUDE_PLUGIN_ROOT}/scripts/pr-comments.ts <pr-url> [--role author|reviewer] [--since last-review|<date>] [--bots] [--include-resolved]
  • --role: author fetches all unresolved threads, the feedback that needs addressing. reviewer fetches only unresolved threads started by the authenticated user, to check whether comments have been resolved. Defaults by whether the authenticated user is the PR author.
  • --since last-review: threads with activity since the last relevant review. As author: the most recent review by a human other than you (bot reviews excluded). As reviewer: your most recent submitted review. An ISO date (e.g. 2025-01-15) sets an explicit cutoff.
  • --bots: only review-bot threads: accounts the API types as Bot (Copilot, CodeRabbit, Greptile) plus the plugin's configured reviewers. Always pass --reviewers=${user_config.reviewers} with it. Use this filter to detect bots rather than hardcoding logins.
  • --include-resolved: include resolved threads, tagged (resolved), for follow-up-style flows that must surface silently resolved threads.

Output is compact markdown grouped by file with line numbers and full comment bodies. Each thread prints its node id, used to reply and resolve.

Replying and Resolving

bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts reply <thread-id> --resolve --body "..."
bun ${CLAUDE_PLUGIN_ROOT}/scripts/review-threads.ts resolve <thread-id>

Pass the reply text with --body, --bodyFile <path>, or stdin. Don't resolve without a reply: a silent resolve hides why the thread closed. Prefer reply --resolve so the resolve carries context. A reply that shows a screenshot uploads it first through the endpoint in github:attach. Review threads sit outside the reach of gh's --attach flag.

Read the full file on GitHub · 50 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. yesterday Changed e484f4ded4f7
  2. 1mo ago Changed f2b5adb0416e
  3. 1mo ago First seen · 50 lines · 51 tokens per session scan A 132e67f81d07

Subscribe to this mod's changes

github:pr-comments is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 817 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude CodeCode reviewclaude-code-plugin
Related

Other skills, from other repositories

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

pr-review

Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…

nitinjain999/platform-skills · 81 tokens

genshijin-review

A compact pull-request review format that writes one actionable finding per line in Japanese or English.

InterfaceX-co-jp/genshijin · 78 tokens

pr-review

Use when the user wants to deeply review a pull/merge request or a local diff — "review this PR", "grill the MR", "stress-test this diff", "deep-dive code review", "code review before merge", or when they name a PR/MR URL, number, branch, commit range (A..B/A...B), tag or SHA. Works on GitHub (gh), GitLab (glab), or a…

procoders/superpowers-v · 112 tokens