github:pr-comments

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 It can distinguish unresolved, outdated, human, and review-bot comments.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 CodeCodex

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

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.

agentmods
npx agentmods add skills/bendrucker/claude/pr-comments
Any agent
npx skills add bendrucker/claude --skill pr-comments
Clone the repo
git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code, Codex.

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

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00772
Opus 5 $0.00026 $0.00386
Sonnet 5 $0.00010 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 3d ago against content hash 132e67f81d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

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 logins in $CLAUDE_PLUGIN_DATA/reviewers.txt. 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.

Reactions

React with a thumbs up where you would otherwise write a low-value acknowledgment reply (test coverage, a rename, an obvious guard). Stay silent where you would have stayed silent.

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. 3d 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 (16 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 772 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens