review-verifier

review-verifier is an agent for Claude Code from lxb12123/agent-plugin-kit. It costs 44 tokens per session (170 once invoked), scanned A, original, MIT.

An adversarial second review of code-review findings that tests whether each reported issue is real, incorrectly identified, or correctly classified.

In plain words
What is it for?
Use it after a review to challenge each finding, confirm genuine problems, reclassify severity, and record which concerns should be dropped.
Why use it?
It reduces false positives and makes the final review verdict more trustworthy.

Agent for Claude Code

Part of the review-plugin plugin — 1 skill, 1 agent 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/lxb12123/agent-plugin-kit/review-verifier
Clone the repo
git clone --depth 1 https://github.com/lxb12123/agent-plugin-kit

Made for: Claude Code.

Or install review-plugin, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

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-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/lxb12123/agent-plugin-kit/review-verifier.svg)](https://agentmods.dev/agents/lxb12123/agent-plugin-kit/review-verifier)
Your own site
<a href="https://agentmods.dev/agents/lxb12123/agent-plugin-kit/review-verifier"><img src="https://agentmods.dev/badge/agents/lxb12123/agent-plugin-kit/review-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 170 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 $0.00044 $0.00170
Opus 5 $0.00022 $0.00085
Sonnet 5 $0.00009 $0.00034
Haiku 4.5 $0.00004 $0.00017

Measured 3d ago against content hash 6e3bdce985db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-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 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.

examples/review-plugin/.claude/agents/review-verifier.md · 14 lines

What it actually says

You are an adversarial reviewer of review verdicts. For each finding listed by /review:

  1. First try to refute it — is it really an issue? Is there context that makes it moot (a false positive)?
  2. Distinguish severity: blocker / warning / nit / false positive.
  3. Keep only the issues you confirm as real, giving a reason for each; explicitly drop the ones judged to be false positives.

Output a concise review verdict: the list of confirmed issues + the dropped false positives + a one-line overall judgment.

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 · 14 lines · 44 tokens per session scan A 6e3bdce985db

Subscribe to this mod's changes

review-verifier is an agent published in the GitHub repository lxb12123/agent-plugin-kit (1 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 170 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.