review-comments

review-comments is a skill for Claude Code from LaStrada/claude. It costs 91 tokens per session (2,893 once invoked), scanned A, original, MIT.

A review command for comments, docstrings, and nearby documentation that were added or changed in the current code change. A docstring is explanatory text attached to a function, class, or module.

In plain words
What is it for?
Auditing changed comments, deciding whether each should stay, be shortened, rewritten, or removed, and suggesting replacements before any edits are made.
Why use it?
It helps remove explanations that merely repeat the code while preserving comments that explain hidden constraints, surprising behavior, or workarounds.

Skill for Claude Code

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

Part of the review-comments plugin — 1 skill 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/lastrada/claude/review-comments
Any agent
npx skills add LaStrada/claude --skill review-comments
Clone the repo
git clone --depth 1 https://github.com/LaStrada/claude

Made for: Claude Code.

Or install review-comments, the plugin that ships this one along with the rest of its 1 skill.

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/lastrada/claude/review-comments.svg)](https://agentmods.dev/skills/lastrada/claude/review-comments)
Your own site
<a href="https://agentmods.dev/skills/lastrada/claude/review-comments"><img src="https://agentmods.dev/badge/skills/lastrada/claude/review-comments.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,893 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 5.1 $0.00091 $0.02893
Opus 5 $0.00046 $0.01447
Sonnet 5 $0.00018 $0.00579
Haiku 4.5 $0.00009 $0.00289

Measured 5d ago against content hash 8b99707bf7d8, 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 5d 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/review-comments/skills/review-comments/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-comments

Audit every comment, docstring, and adjacent documentation block that is new or changed in the current change set. For each one, decide: keep, tighten, rephrase, or drop. Then surface the verdicts as a table with concrete suggested rewrites, and wait for approval before editing.

Two rules drive the audit:

  1. The default is no comment. A comment exists only when the WHY is non-obvious — a hidden constraint, a subtle invariant, a workaround, an intentional non-action, behaviour that would surprise the reader. If the code already tells the same story through naming, the comment is noise.
  2. Comments belong to the code, not the conversation. They must read sensibly to someone who arrives 6 months later, never saw the PR or change set, doesn't have access to internal memory, and can't tell what "previously" or "now" refers to.

When this applies

Trigger phrases (not exhaustive):

  • "review the comments" / "review the new comments" / "review the changed comments"
  • "audit the comments" / "comment audit" / "audit the docs"
  • "are the comments overkill" / "too many comments" / "too verbose"
  • "check the comments before commit" / "comments before PR" / "comment hygiene"
  • "shorten / trim / tighten the comments" / "are the docstrings too long"
  • "review the docs" — when scoped to docs that move with this change set
  • The user invokes /review-comments directly.

Do NOT trigger for:

  • Full PR / code review (use review, code-review, or pr-review-toolkit:review-pr).
  • Writing new comments from scratch — this skill audits, doesn't draft.
  • "What does this comment mean" — that's explanation, not audit.
  • Reviewing arbitrary unchanged markdown not touched by the change set.

Scope — what counts as "new or changed"

Always include:

  • Lines added in the diff (+ lines).
  • Comment blocks where any line changed (- immediately followed by + with comment syntax on either side counts as a modified block — review the new version).
  • Every comment in newly-added files. (Whole-file additions are entirely "new" by definition.)
  • Doc comments adjacent to changed code, even if the doc itself didn't textually change — if the underlying function's signature or behaviour changed, the doc may now be stale. Flag those as "stale-check" rather than re-evaluating their wording.

Read the full file on GitHub · 198 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. 5d ago First seen · 198 lines · 91 tokens per session scan A 8b99707bf7d8

Subscribe to this mod's changes

review-comments is a skill published in the GitHub repository LaStrada/claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 2,893 once invoked, about $0.0005 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

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens