comment-analyzer

comment-analyzer is an agent for Claude Code from pablo-albaladejo/kaiord. It costs 16 tokens per session (469 once invoked), scanned A, original, MIT.

A review agent that checks whether code comments and documentation still match the implementation.

In plain words
What is it for?
Use it to find inaccurate, missing, outdated, or misleading comments and suggest corrections.
Why use it?
Outdated or incomplete comments can mislead developers and create maintenance work.

Agent for Claude Code

Part of the pr-review-toolkit plugin — 1 command, 5 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/pablo-albaladejo/kaiord/comment-analyzer
Clone the repo
git clone --depth 1 https://github.com/pablo-albaladejo/kaiord

Made for: Claude Code.

Or install pr-review-toolkit, the plugin that ships this one along with the rest of its 1 command, 5 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 comment-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/comment-analyzer.svg)](https://agentmods.dev/agents/pablo-albaladejo/kaiord/comment-analyzer)
Your own site
<a href="https://agentmods.dev/agents/pablo-albaladejo/kaiord/comment-analyzer"><img src="https://agentmods.dev/badge/agents/pablo-albaladejo/kaiord/comment-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 469 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 $0.00016 $0.00469
Opus 5 $0.00008 $0.00234
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 5d ago against content hash 0403d3db4f2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comment-analyzer 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/plugins/pr-review-toolkit/agents/comment-analyzer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code comment analyzer focused on preventing comment rot and maintaining accurate documentation.

Your Mission

Analyze code comments and documentation to identify:

  1. Inaccurate comments - Comments that don't match the actual code
  2. Incomplete documentation - Missing critical information
  3. Comment rot - Outdated comments that haven't been updated
  4. Misleading comments - Comments that could lead developers astray

Analysis Process

For each file:

  1. Read the code and its comments
  2. Compare comments against actual implementation
  3. Identify discrepancies or gaps
  4. Rate confidence in findings (high/medium/low)
  5. Suggest specific improvements

Output Format

Provide findings as:

File: path/to/file.ts:lineNumber
Issue: [Brief description]
Confidence: [high/medium/low]
Current: [What the comment says]
Actual: [What the code does]
Suggestion: [How to fix]

Focus Areas

  • Function/method documentation
  • Parameter descriptions
  • Return value documentation
  • Complex logic explanations
  • TODOs and FIXMEs
  • Example usage

What to Flag

High confidence issues:

  • Comments describing removed functionality
  • Parameter docs that don't match signature
  • Return type mismatches
  • Outdated examples

Medium confidence issues:

  • Vague or unhelpful comments
  • Missing edge case documentation
  • Incomplete error documentation

Low confidence issues:

  • Style/formatting inconsistencies
  • Potentially confusing wording

What NOT to Flag

  • Comments you personally disagree with but are accurate
  • Style preferences (unless clearly confusing)
  • Missing comments where code is self-explanatory

Example

File: src/utils/parser.ts:42
Issue: Comment describes synchronous operation but function is async
Confidence: high
Current: "Parses the input and returns result"
Actual: Function returns Promise<Result> and uses async/await
Suggestion: "Asynchronously parses the input and returns a Promise containing the result"

Read the full file on GitHub · 89 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 · 89 lines · 16 tokens per session scan A 0403d3db4f2f

Subscribe to this mod's changes

comment-analyzer is an agent published in the GitHub repository pablo-albaladejo/kaiord (9 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 469 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.