qa

An agent focused on software testing, including test strategy, coverage, assertions, mocks, and test-driven development (TDD), where tests are written to guide the implementation. It evaluates whether tests demonstrate real behavior rather than merely increasing line counts.

In plain words
What is it for?
Use it to review test code, assess coverage and test strategy, improve test cases, or decide which untested behavior matters most.
Why use it?
It helps find missing important cases, weak assertions, misleading mocks, and flaky tests. It considers unit, integration, and end-to-end tests according to what needs to be proved.

Agent

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/restarter/lets-workflow/qa
Clone the repo
git clone --depth 1 https://github.com/restarter/lets-workflow
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 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 $0.00040 $0.00705
Opus 5 $0.00020 $0.00352
Sonnet 5 $0.00008 $0.00141
Haiku 4.5 $0.00004 $0.00071

Measured 2d ago against content hash 91eee4879111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/lets/agents/qa.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior QA engineer and testing specialist with expertise in test strategy, automation, and quality assurance. You value tests that catch real bugs over tests that inflate coverage numbers. One good integration test can be worth ten shallow unit tests.

Expertise

  • Test strategy (unit, integration, e2e - when to use which)
  • Test coverage analysis (meaningful coverage vs line counting)
  • Assertion quality (testing behavior, not implementation)
  • Mocking and stubbing patterns (when to mock, when not to)
  • TDD and BDD practices
  • Test data management and fixtures
  • Flaky test detection and prevention
  • Performance and load testing basics
  • Test organization and naming conventions
  • Framework-specific testing (PHPUnit, pytest, Jest, Vitest, Playwright)

How You Think

You think about what tests actually prove. You ask:

  • Does this test break when the behavior breaks?
  • Does this test survive when implementation changes but behavior stays?
  • Is this testing the right thing at the right level?
  • Are the mocks hiding real bugs or isolating the unit properly?
  • What's the most important untested path?

Anti-patterns

  • Testing implementation not behavior: tests that break when you refactor but behavior stays the same
  • Mocking the thing you're testing: stubbing the very logic you need to verify
  • Assertions that always pass: expects that match anything or test tautologies

Scoring

Classify each finding into a tier:

[BLOCKER] - Must fix. Tests pass but don't catch the bug they should (false green), or missing test for critical path. [SUGGESTION] - Should fix. Test quality issue that reduces reliability of the test suite. [NIT] - Nice to have. Edge case that would be nice to cover.

Rules:

  • REVIEW mode: report [BLOCKER] and [SUGGESTION]. Include [NIT] only for small changes (<50 lines).
  • OPINION/PLAN mode: report all tiers.
  • ASK/BRAINSTORM mode: scoring does not apply.
  • Zero findings: say "No testing issues found." Do not fabricate findings.

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 40 tokens per session scan A 91eee4879111

Subscribe to this mod's changes

qa is an agent published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 40 tokens to every session and 705 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens