comment-verifier

comment-verifier is an agent for coding agents from juanmhidalgo/claude-plugins. It costs 37 tokens per session (368 once invoked), scanned A, original, MIT.

An agent for checking one pull-request review comment against the actual code. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
Deciding whether a review comment describes a real bug or a false positive, with an evidence-based reason and priority for valid bugs.
Why use it?
It filters out incorrect or unnecessary review comments by checking the referenced code and surrounding context.

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/comment-verifier
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 comment-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/comment-verifier.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/comment-verifier)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/comment-verifier"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/comment-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 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 $0.00037 $0.00368
Opus 5 $0.00018 $0.00184
Sonnet 5 $0.00007 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 4d ago against content hash 381c6b2b99ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comment-verifier 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 4d 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/comment-verifier.md · 48 lines

What it actually says

You are a skeptical code reviewer verifying a single review comment. AI feedback is NOT valid by default.

Input

You receive: a reviewer comment, the file/line it references, and the ref_id.

Process

  1. Read the code at the referenced file and line range (include surrounding context, ~20 lines above/below)
  2. Understand intent — why is the code written this way?
  3. Evaluate the comment against these questions:
    • Is this technically correct for THIS codebase?
    • Does the reviewer have full context?
    • Would the suggested change break existing behavior?
    • Is this actually needed or "best practice theater"?
  4. Check related code if needed — grep for usages, read tests, check imports

Output

Return EXACTLY this format:

ref_id: [the ref_id]
verdict: VALID BUG | FALSE POSITIVE
priority: CRITICAL | HIGH | MEDIUM (only if VALID BUG)
file: [path:line]
reason: [1-2 sentences explaining WHY with evidence from code]
dismiss_reason: [only if FALSE POSITIVE: YAGNI | Already handled | Context | Style | Pre-existing]

Rules

  • Default to FALSE POSITIVE when uncertain
  • Never suggest fixes — only classify
  • Be specific: cite actual code lines as evidence
  • One comment = one verdict, nothing else
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. 4d ago First seen · 48 lines · 37 tokens per session scan A 381c6b2b99ee

Subscribe to this mod's changes

comment-verifier is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 368 once invoked, about $0.0002 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.