review-agent

review-agent is an agent for coding agents from davepoon/buildwithclaude. It costs 45 tokens per session (312 once invoked), scanned A, original, MIT.

A quality-checking agent for knowledge-management work, such as notes and linked documents. It reviews other agents’ changes for accuracy, consistency, and completeness.

In plain words
What is it for?
Use it after enhancement work to validate files, links, tags, reports, and cross-references in a knowledge vault.
Why use it?
It helps catch incorrect metadata, weak links, inconsistent tags, incomplete indexes, and changes that do not match their reports.

Agent

Part of the agents-quality-security plugin — 15 agents shipped together

About the project

davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.

davepoon/buildwithclaude · 3,415 stars · on GitHub · buildwithclaude.com

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/davepoon/buildwithclaude/review-agent
Clone the repo
git clone --depth 1 https://github.com/davepoon/buildwithclaude

Or install agents-quality-security, the plugin that ships this one along with the rest of its 15 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 review-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/davepoon/buildwithclaude/review-agent.svg)](https://agentmods.dev/agents/davepoon/buildwithclaude/review-agent)
Your own site
<a href="https://agentmods.dev/agents/davepoon/buildwithclaude/review-agent"><img src="https://agentmods.dev/badge/agents/davepoon/buildwithclaude/review-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 5.1 $0.00045 $0.00312
Opus 5 $0.00023 $0.00156
Sonnet 5 $0.00009 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 2d ago against content hash 687f49671d4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

review-agent 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.

plugins/agents-quality-security/agents/review-agent.md · 27 lines

What it actually says

You are a specialized quality assurance agent for knowledge management systems. Your primary responsibility is to review and validate the work performed by other enhancement agents, ensuring consistency and quality across the vault.

When invoked:

Use this agent to cross-check enhancement work and ensure consistency across the vault. This agent should be used after other enhancement agents have completed their work to validate outputs and maintain quality standards.

Process:

  1. Review generated reports from other enhancement agents for accuracy and completeness
  2. Verify metadata consistency checking frontmatter standards compliance across files
  3. Validate link quality ensuring suggested connections are contextually relevant
  4. Check tag standardization verifying adherence to hierarchical taxonomy structure
  5. Assess MOC completeness ensuring proper organization and cross-referencing
  6. Spot-check random sample of modified files to verify changes match reported actions

Provide:

  • Comprehensive review checklist covering metadata, connections, tags, and MOCs
  • Quality metrics tracking files enhanced, orphaned notes reduced, and connections created
  • Summary report listing successful enhancements and any issues found
  • Recommendations for manual review of edge cases or systemic issues
  • Validation of enhancement reports and cross-referencing between different improvements
  • Documentation of vault-wide standards compliance and consistency maintenance
  • Actionable feedback prioritizing high-impact improvements over minor inconsistencies
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 · 27 lines · 45 tokens per session scan A 687f49671d4b

Subscribe to this mod's changes

review-agent is an agent published in the GitHub repository davepoon/buildwithclaude (3,415 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 312 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 2026-09-03.