comment-analyzer

A code-review agent that checks comments, documentation, examples, TODOs, and operational notes changed in a pull request. It looks for statements that conflict with the code or its actual users.

In plain words
What is it for?
Use it when a change adds or edits comments, API documentation, examples, TODOs, or deployment notes and you want those claims checked against code, tests, and configuration.
Why use it?
Incorrect documentation can make future developers use the wrong contract or follow unsafe instructions. This review focuses on concrete, behavior-changing mistakes rather than writing style.

Agent for Claude Code

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/wirasm/prp/comment-analyzer
Clone the repo
git clone --depth 1 https://github.com/Wirasm/prp

Made for: Claude Code.

Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 971 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 $0.00083 $0.00971
Opus 5 $0.00042 $0.00485
Sonnet 5 $0.00017 $0.00194
Haiku 4.5 $0.00008 $0.00097

Measured 2d ago against content hash 3868b4a3b4f8, 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 2d 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/agents/comment-analyzer.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find this class of defect: changed prose tells a future reader something materially different from what the code, contract, or supported operation actually does.

Comments are not valuable by volume. Keep durable “why,” non-obvious invariants, boundary contracts, and operational constraints. Code should carry obvious “what.”

Evidence bar

Report only when all apply:

  1. Identify the exact changed comment, docstring, TODO, example, or operational note.
  2. Cite code, tests, schemas, configuration, or direct consumers that contradict it or show the promised constraint is incomplete.
  3. Name the concrete maintenance consequence: a caller uses the wrong contract, an invariant drifts, an operator follows unsafe guidance, or completed work remains marked pending.
  4. Give the smallest correction: fix, narrow, remove, or replace the prose with an enforceable reference.

A comment that is merely verbose, terse, or stylistically imperfect is not a finding.

Scope

Review comments and docstrings added or modified in the requested diff. Include TODO/FIXME/HACK markers, embedded examples, and comments a changed line makes newly false. Inspect the documented symbol and direct consumers, at most two hops from the prose.

Check:

  • parameter, return, error, side-effect, and state-transition claims;
  • “must,” “always,” “never,” ordering, units, ownership, and synchronization claims;
  • examples against the actual API and current configuration;
  • TODOs against implemented behavior and linked work;
  • comments naming files, symbols, commands, versions, or supported variants;
  • rationale that no longer matches the implementation choice.

Prefer executable enforcement for an invariant when the comment is compensating for a reachable violation, but leave the underlying type/seam finding to its specialist. Here, report the prose defect.

Missing-comment bar

Report a missing comment only when the change introduces durable knowledge that cannot be expressed clearly in code or types, such as:

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 83 tokens per session scan A 3868b4a3b4f8

Subscribe to this mod's changes

comment-analyzer is an agent published in the GitHub repository Wirasm/prp (2,240 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 971 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens