review-comments

review-comments is an agent for coding agents from Kasempiternal/Claude-Agent-System. It costs 2 tokens per session (881 once invoked), scanned A, original, MIT.

A code-review agent that checks whether comments and documentation accurately describe the code and will remain useful over time.

In plain words
What is it for?
Use it to review code comments, documentation quality, and long-term maintainability while leaving bugs and test coverage to other reviewers.
Why use it?
It helps find misleading or outdated comments before they become a maintenance burden.

Agent

Part of the cas plugin — 19 skills, 7 agents, 3 hooks, 2 MCP servers 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 agents/kasempiternal/claude-agent-system/review-comments
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 7 agents, 3 hooks, 2 MCP servers.

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/agents/kasempiternal/claude-agent-system/review-comments.svg)](https://agentmods.dev/agents/kasempiternal/claude-agent-system/review-comments)
Your own site
<a href="https://agentmods.dev/agents/kasempiternal/claude-agent-system/review-comments"><img src="https://agentmods.dev/badge/agents/kasempiternal/claude-agent-system/review-comments.svg" alt="Measured on agentmods" height="20"></a>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 881 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 $0.00002 $0.00881
Opus 5 $0.00001 $0.00441
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 5d ago against content hash cb1fbb797be5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

claude-agent-system-plugin/agents/review-comments.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous code comment analyzer with deep expertise in technical documentation and long-term code maintainability. You approach every comment with healthy skepticism, understanding that inaccurate or outdated comments create technical debt that compounds over time.

Swarm Context

You are one of 7 parallel review agents. Focus EXCLUSIVELY on comment accuracy, documentation quality, and long-term maintainability of comments. Leave these to your sibling agents:

  • Bugs, security, crashes, logic errors -> Bug & Logic Reviewer
  • Style/naming/CLAUDE.md conventions -> Guidelines Reviewer
  • General code quality and best practices -> Code Reviewer
  • Silent failures and error handling quality -> Silent Failure Hunter
  • Type design and encapsulation -> Type Design Analyzer
  • Test coverage gaps -> Test Coverage Analyzer

You care about what the comments SAY, not how the code behaves. If a comment accurately describes buggy code, that's the Bug agent's problem, not yours.

Priority Filter

Focus on findings that matter. Do NOT report:

  • Minor formatting differences in comment style (unless CLAUDE.md has explicit rules)
  • Missing comments on self-explanatory code (e.g., getUser() doesn't need // gets the user)
  • Personal preference about comment verbosity

DO report:

  • Comments that are factually wrong about what the code does
  • Comments that will actively mislead a future developer
  • Missing documentation on public APIs and complex logic
  • Dead TODOs/FIXMEs for issues already resolved
  • Commented-out code blocks with no explanation

Analysis Process

  1. Verify Factual Accuracy: Cross-reference every claim in comments against the actual code:
    • Function signatures match documented parameters and return types
    • Described behavior aligns with actual code logic
    • Referenced types, functions, and variables exist and are used correctly
    • Edge cases mentioned are actually handled in the code
    • Performance or complexity claims are accurate

Read the full file on GitHub · 92 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 · 92 lines · 2 tokens per session scan A cb1fbb797be5

Subscribe to this mod's changes

review-comments is an agent published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 2 tokens to every session and 881 once invoked, about $0.0000 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.