review-pr-comments

review-pr-comments is a skill for Claude Code, Codex from nikeyes/stepwise-dev. It costs 20 tokens per session (751 once invoked), scanned A, original, Apache-2.0.

A workflow for examining open pull-request comments, deciding which points are technically justified, and replying after agreement.

In plain words
What is it for?
Use it to review active inline or general comments on the current or specified pull request and prepare individual responses.
Why use it?
It organizes review feedback and avoids accepting changes based only on preference, while keeping the user involved before replies are posted.

Skill for Claude CodeCodex

Part of the stepwise-git plugin — 2 skills 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/nikeyes/stepwise-dev/review-pr-comments
Any agent
npx skills add nikeyes/stepwise-dev --skill review-pr-comments
Clone the repo
git clone --depth 1 https://github.com/nikeyes/stepwise-dev

Made for: Claude Code, Codex.

Or install stepwise-git, the plugin that ships this one along with the rest of its 2 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-pr-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/review-pr-comments.svg)](https://agentmods.dev/skills/nikeyes/stepwise-dev/review-pr-comments)
Your own site
<a href="https://agentmods.dev/skills/nikeyes/stepwise-dev/review-pr-comments"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/review-pr-comments.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 751 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 $0.00020 $0.00751
Opus 5 $0.00010 $0.00376
Sonnet 5 $0.00004 $0.00150
Haiku 4.5 $0.00002 $0.00075

Measured 3d ago against content hash f985e6144990, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-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.

git/skills/review-pr-comments/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR Comments

Review all open PR comments, present a summary with your position on each, iterate with the user until agreed, then post responses individually to each comment.

Rules

  • PR target: if no PR number is given, auto-detect from the current branch. If none exists, ask.

  • Scope: only active comments (both inline and general). Ignore resolved and outdated ones.

  • Bias: defend the existing code. Only accept a change with a concrete technical reason (bug, violated principle, demonstrable readability gain). Reject style preferences without objective justification.

  • Context: before evaluating, read the full files affected plus related files (tests, types, direct dependencies).

  • Summary format: after reviewing every comment, present all decisions grouped by severity, one compact block per comment. Do NOT quote the full body verbatim — the user has GitHub open and can click through. Rephrase the claim in one sentence in your own words.

    Extract severity from the comment's prefix when present ([SECURITY — CRITICAL], [CODE QUALITY — HIGH], [TESTS — LOW], [SUGGESTION], etc.). If no prefix, infer: correctness/security bugs → HIGH; performance, tests, or missing error paths → MEDIUM; style, docstrings, naming, "for symmetry", "for consistency" nits → LOW.

    Block format per comment:

    N. [ACCEPT|REJECT] {path}:{line or "general"} @{user} — {your one-sentence rephrase of the claim}
       Reason: {1-2 lines, technical}
       Fix: {concrete action you will take}          # only if ACCEPT
       Alternative: {what you propose instead}       # only if REJECT
       Link: {comment.html_url}
    

    Present them in this order:

    HIGH — decision required:
      <blocks>
    
    MEDIUM — decision required:
      <blocks>
    
    LOW / nits — proposed REJECT in batch (unless you rescue any):
      <blocks, but with just the one-line rephrase + link; no Reason/Alternative>
    

    Then ask ONE question: "Confirm my ACCEPT/REJECT on HIGH+MEDIUM and I discard the LOW batch — or do you want to rescue any LOW?"

Read the full file on GitHub · 56 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 · 56 lines · 20 tokens per session scan A f985e6144990

Subscribe to this mod's changes

review-pr-comments is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 15d ago), licensed Apache-2.0. It adds 20 tokens to every session and 751 once invoked, about $0.0001 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