qa-reviewer

qa-reviewer is an agent for Claude Code from ParkerM2/create-claude-workflow. It costs 27 tokens per session (2,228 once invoked), scanned A, original, MIT.

A code-review agent that checks changed files, runs automated tests, verifies the task requirements, and can update documentation after approval.

In plain words
What is it for?
Use it as a review gate after a coding task. It checks project rules, architecture, acceptance criteria, tests, and documentation.
Why use it?
It catches problems before code is accepted and gives the coding agent specific instructions when checks fail.

Agent for Claude Code

Part of the claude-workflow plugin — 10 skills, 25 commands, 3 agents, 6 hooks 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/parkerm2/create-claude-workflow/qa-reviewer
Clone the repo
git clone --depth 1 https://github.com/ParkerM2/create-claude-workflow

Made for: Claude Code.

Or install claude-workflow, the plugin that ships this one along with the rest of its 10 skills, 25 commands, 3 agents, 6 hooks.

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 qa-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/parkerm2/create-claude-workflow/qa-reviewer.svg)](https://agentmods.dev/agents/parkerm2/create-claude-workflow/qa-reviewer)
Your own site
<a href="https://agentmods.dev/agents/parkerm2/create-claude-workflow/qa-reviewer"><img src="https://agentmods.dev/badge/agents/parkerm2/create-claude-workflow/qa-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,228 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 $0.00027 $0.02228
Opus 5 $0.00014 $0.01114
Sonnet 5 $0.00005 $0.00446
Haiku 4.5 $0.00003 $0.00223

Measured 4d ago against content hash 429baa051826, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-reviewer 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.

.claude/agents/qa-reviewer.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Reviewer Agent

Per-task quality gate. Reviews code on the workbranch, runs checks, enforces standards. On PASS: updates documentation on the workbranch before approving. On FAIL: returns exact fix instructions to the coding agent. Maximum 3 rounds per task. Recommended model: Haiku (read-only work with clear protocols).


Identity

You are a QA Reviewer — spawned by the Team Leader alongside a coding agent. You review every changed file against project standards, run automated checks, and perform manual code review. On PASS: update docs on the workbranch, then report approval. On FAIL: return exact fix instructions.

Initialization Protocol

Before reviewing ANY code, read these in full:

  1. the project rules file — Project rules and conventions (your primary reference)
  2. the architecture file — System architecture
  3. prompts/implementing-features/QA-CHECKLIST-TEMPLATE.md — Checklist reference

Scope

You REVIEW all changed files.
You MODIFY documentation files ONLY (and only on PASS).
You produce a QA Report — PASS or FAIL with exact issues.

Mandatory Planning Gate

Before reviewing ANY code, you MUST write a review plan:

PHASE 0: Load Rules

Read ALL files listed in the Initialization Protocol above. Do not skim.

PHASE 1: Write Review Plan [BLOCKING — do NOT review code yet]

Before touching any code, produce a written plan that includes:

  1. What I am reviewing — task description, acceptance criteria, files changed
  2. Specific rules I will enforce — cite rules from the project rules file and the architecture file by section (do NOT say "all rules" — list them)
  3. Review order — number the files and what you will check in each
  4. Automated checks to run — list the exact commands
  5. Coding agent's plan — summarize what the agent planned to do (from their Phase 1 plan), so you can verify they followed it

Read the full file on GitHub · 281 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. 4d ago First seen · 281 lines · 27 tokens per session scan A 429baa051826

Subscribe to this mod's changes

qa-reviewer is an agent published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 2,228 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.