review-comments

review-comments is a skill for Claude Code from flurdy/agent-skills. It costs 45 tokens per session (2,017 once invoked), scanned A, original, MIT.

A workflow for handling comments left on a GitHub pull request, a proposed code change for review. It selects and checks feedback, makes local fixes, runs verification, and creates a local commit.

In plain words
What is it for?
Use it to work through selected pull-request comments, validate each one, make focused edits, run tests or checks, and prepare a local commit.
Why use it?
It separates confirmed, useful review feedback from comments that may not apply and prevents accidental online actions such as posting replies or publishing changes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Good fit Use it to work through selected pull-request comments, validate each one, make…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flurdy/agent-skills/review-comments
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 flurdy/agent-skills --skill review-comments
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

Made for: Claude Code.

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-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/review-comments.svg)](https://agentmods.dev/skills/flurdy/agent-skills/review-comments)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/review-comments"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/review-comments.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,017 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 $0.00045 $0.02017
Opus 5 $0.00023 $0.01009
Sonnet 5 $0.00009 $0.00403
Haiku 4.5 $0.00005 $0.00202

Measured 6d ago against content hash 3c901293dc7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/gh-pr-comments.sh, scripts/gh-pr-current-info.sh, scripts/gh-pr-view-reviews.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/review-comments/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Address Review Comments

Select and independently validate PR feedback before making focused local changes. This skill owns only the attended local phase: selection, validation, edits, tests, and a local commit. It never publishes a branch, GitHub reply, or thread resolution. /reply-comments owns those separately confirmed remote actions.

Usage

/review-comments                         # PR for the current branch
/review-comments 123                     # backward-compatible current-repository selector
/review-comments owner/repo#123          # repository-qualified selector from the watcher
/review-comments owner/repo#123 inline:C1 conversation:I2

Trailing stable identities preselect candidates but never authorize an edit or reply.

Instructions

1. Resolve the PR and Checkout

Accept owner/repo#number or a numeric PR. With no selector, resolve the current branch through:

~/.agents/skills/review-comments/scripts/gh-pr-current-info.sh

For a numeric selector, derive owner/repository from the current checkout. For a repository-qualified selector, use its owner/repository for every GitHub call. Fetch PR metadata, head SHA, branch, body, and changed files read-only.

Before offering a local fix, prove that the current directory is a matching checkout:

  1. origin resolves to the selected owner/repository;
  2. the current branch/HEAD represents the selected PR head;
  3. the working tree's pre-existing changes are understood and will not be overwritten.

Never switch branches, create a checkout, fetch, reset, clean, or overwrite unrelated work. If no matching checkout exists, validation and reply preparation may continue from the PR diff, but local fix actions are unavailable. Tell the user which checkout is required.

2. Fetch the Normalized Inventory

Use one bounded read-only call:

~/.agents/skills/pr-status/scripts/gh-pr-feedback.py {owner} {repo} {pr_number}

Read records, partial, and errors. Preserve each candidate's stable identity, updatedAt, updateKey, stateKey, source, lifecycle, author kind, and targets throughout the run. Never use body text or counts as identity. Pending draft review comments are not observable and must not be invented.

Read the full file on GitHub · 184 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 184 lines · 45 tokens per session scan A 3c901293dc7b

Subscribe to this mod's changes

review-comments is a skill published in the GitHub repository flurdy/agent-skills (8 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 2,017 once invoked, about $0.0002 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

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens