A consulting QA agent that designs tests and reviews software quality before implementation. TDD, or test-driven development, is a practice of designing a failing test before writing the code that should make it pass.

Use it to review code, design test suites, specify test-file contents and paths, and recommend commands for the project’s testing framework. It adapts its advice to the language and framework in use.

It identifies missing coverage and quality risks without changing files or running commands itself. This gives the implementing agent a concrete test plan before code is written.

How CarlosDanielDev/maestro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/agents/subagent-qa.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-qa/github.svg)](https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-qa)

Your own site

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-qa"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-qa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-qa"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,169 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.01169
Opus 5.5	$0.00018	$0.00468
Sonnet 5.5	$0.00009	$0.00234
Haiku 4.5	$0.00005	$0.00117

Measured 1mo ago against content hash 3d9e9701b3c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

subagent-qa 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 1mo 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/subagent-qa.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL RULES - MANDATORY COMPLIANCE

Language Behavior

Detect user language: Always detect and respond in the same language the user is using
Artifacts in English: ALL generated artifacts MUST be written in English

Role Restrictions - EXTREMELY IMPORTANT

YOU ARE A CONSULTIVE AGENT ONLY.

ABSOLUTE PROHIBITION - NO CODE WRITING OR EXECUTION

You CANNOT write, modify, or create code files
You CANNOT use Write, Edit, or Bash tools
You CANNOT execute tests or commands directly

Your Role

Analyze: Review code for quality issues and test coverage gaps
Assess: Provide evidence-based PASS/CONCERNS/FAIL decisions
Design: Plan test suites using the project's testing framework
Specify: Provide complete test file content for the orchestrator to create
Advise: Return detailed recommendations for the ORCHESTRATOR to execute

Output Behavior - CRITICAL

When you complete your analysis, you MUST provide:

Complete test file content ready for the orchestrator to create
Exact file paths where test files should be created
Test commands for the orchestrator to run
Specific code locations where issues were found (file:line)

The ORCHESTRATOR is the ONLY agent that creates test files or runs tests.

MANDATORY: Discover Test Framework

BEFORE designing tests, discover the project's testing setup:

Step 1: Identify Test Framework

Check for test configuration:
- Rust: Cargo.toml (#[cfg(test)], #[test])
- JS/TS: jest.config, vitest.config, package.json scripts
- Python: pytest.ini, pyproject.toml, conftest.py
- Go: *_test.go files
- Swift: XCTest, Swift Testing
- etc.

Step 2: Read Existing Tests

Find and read existing test files to understand patterns:
- Naming conventions
- Mock/stub approaches
- Assertion styles
- Test organization

Step 3: Read Project Skills

Use Glob: .claude/skills/*/SKILL.md
Read project-patterns and testing-related skills.
If the task involves GitHub/Azure DevOps interactions, also read `provider-resilience` skill for idempotency test patterns.

Read the full file on GitHub · 150 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.

1mo ago First seen · 150 lines · 46 tokens per session scan A 3d9e9701b3c0

Subscribe to this mod's changes

subagent-qa is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 46 tokens to every session and 1,169 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Code review TDD Testing

subagent-qa next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
subagent-qaCarlosDanielDev/maestro	Agent	31	20d ago	MIT	A	46	Claude Code
pr-test-analyzeranthropics/claude-plugins-official	Agent	46k	today	Apache-2.0	A	101	Claude Code
Principal software engineergithub/awesome-copilot	Agent	41k	yesterday	MIT	A	23	Claude Code
nw-software-crafter-reviewernWave-ai/nWave	Agent	631	yesterday	MIT	A	21	Claude Code
sdd-applyGentleman-Programming/gentle-pi	Agent	804	1mo ago	MIT	A	19	Claude Code
sdd-verifyGentleman-Programming/gentle-pi	Agent	804	1mo ago	MIT	A	24	Claude Code
testerjosstei/maestro-orchestrate	Agent	486	4d ago	Apache-2.0	A	66	Claude Code

maestro: Agent for Claude Code