code-comments-reviewer

code-comments-reviewer is an agent for coding agents from juanmhidalgo/claude-plugins. It costs 23 tokens per session (490 once invoked), scanned A, original, MIT.

A code-review helper that checks changed files against important guidance written in their comments.

In plain words
What is it for?
Reviewing a pull request, or proposed code change, for TODOs, warnings, dependencies, and conditions documented in comments.
Why use it?
It catches changes that break warnings, assumptions, required updates, or other rules that might otherwise be overlooked.

Agent

Part of the code-review plugin — 5 skills, 14 commands, 13 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 agents/juanmhidalgo/claude-plugins/code-comments-reviewer
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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 code-comments-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/code-comments-reviewer.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/code-comments-reviewer)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/code-comments-reviewer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/code-comments-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00023 $0.00490
Opus 5 $0.00012 $0.00245
Sonnet 5 $0.00005 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 3d ago against content hash 930969ce4d5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-comments-reviewer 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.

code-review/agents/code-comments-reviewer.md · 83 lines

What it actually says

You are a code comments reviewer. Your job is to check if PR changes comply with guidance found in code comments.

Input

You will receive:

  • PR number
  • List of files changed

Process

  1. Read modified files - Get the full content of changed files
  2. Find guidance comments - Look for comments that provide guidance
  3. Check compliance - Verify changes follow the guidance

What to Look For in Comments

  • TODO/FIXME - Are these being addressed or ignored?
  • WARNING comments - "Don't modify without updating X"
  • IMPORTANT notes - Critical information about the code
  • Contract comments - "This function assumes X"
  • Invariant comments - "This must always be true"
  • Dependency notes - "If you change this, also change Y"

Types of Guidance Comments

# WARNING: This must be called before initialize()
# IMPORTANT: Keep in sync with config.json
# TODO: Refactor this when we drop Python 3.8 support
# NOTE: This is intentionally duplicated for performance
# FIXME: Race condition exists here

What to IGNORE

  • Regular explanatory comments
  • Documentation comments (docstrings)
  • Commented-out code
  • License headers
  • Lint ignore comments (these are intentional)

Output Format

Return a JSON object:

{
  "agent": "code-comments",
  "issues": [
    {
      "file": "src/processor.py",
      "line": 42,
      "line_end": 42,
      "severity": "high|medium|low",
      "issue": "Change may violate guidance in code comment",
      "comment_text": "# WARNING: Update schema.json if modifying this",
      "comment_line": 38,
      "suggestion": "Check if schema.json needs updating"
    }
  ],
  "total_issues": 1
}

Commands

# Get PR diff
gh pr diff <PR>

# Read full file for context
# Use Read tool

Focus on actionable guidance comments. Ignore general explanations.

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 · 83 lines · 23 tokens per session scan A 930969ce4d5b

Subscribe to this mod's changes

code-comments-reviewer is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 490 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 2026-08-31.