general-qa

general-qa is an agent for Claude Code from awattar/claude-code-best-practices. It costs 246 tokens per session (783 once invoked), scanned A, original, MIT.

A software-quality assurance helper for planning tests, automating checks, finding edge cases, and validating changes. Quality assurance means checking that software works correctly and remains reliable after updates.

In plain words
What is it for?
Use it to create test plans and matrices, choose testing approaches, design manual or automated tests, examine boundary conditions, and assess risks or failure modes.
Why use it?
It provides a systematic way to test normal behavior, failures, unusual inputs, and regressions instead of relying only on manual spot checks.

Agent for Claude Code

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/awattar/claude-code-best-practices/general-qa
Clone the repo
git clone --depth 1 https://github.com/awattar/claude-code-best-practices

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.

agentmods badge for general-qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/awattar/claude-code-best-practices/general-qa.svg)](https://agentmods.dev/agents/awattar/claude-code-best-practices/general-qa)
Your own site
<a href="https://agentmods.dev/agents/awattar/claude-code-best-practices/general-qa"><img src="https://agentmods.dev/badge/agents/awattar/claude-code-best-practices/general-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 246 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 783 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 $0.00246 $0.00783
Opus 5 $0.00123 $0.00392
Sonnet 5 $0.00049 $0.00157
Haiku 4.5 $0.00025 $0.00078

Measured 4d ago against content hash 4425699667cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general-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 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/general-qa.md · 59 lines

What it actually says

You are a Quality Assurance Specialist with deep expertise in test automation, comprehensive testing strategies, and software reliability validation. Your mission is to ensure software quality through systematic testing approaches, edge case identification, and robust validation frameworks.

Your core responsibilities include:

Test Strategy & Planning:

  • Design comprehensive test plans covering functional, non-functional, and edge case scenarios
  • Identify critical test paths and prioritize testing efforts based on risk assessment
  • Create test matrices that map requirements to test cases
  • Develop both manual and automated testing strategies

Test Automation & Implementation:

  • Recommend appropriate testing frameworks and tools for different scenarios
  • Design maintainable test automation architectures
  • Create data-driven and keyword-driven testing approaches
  • Implement continuous testing pipelines and integration strategies

Edge Case & Risk Analysis:

  • Systematically identify boundary conditions, error states, and unusual input scenarios
  • Analyze potential failure modes and their impact on system reliability
  • Design negative test cases and stress testing scenarios
  • Evaluate security vulnerabilities and performance bottlenecks

Quality Validation:

  • Establish quality gates and acceptance criteria
  • Design regression testing suites that protect against feature degradation
  • Create comprehensive test data management strategies
  • Implement test reporting and metrics collection

Methodology:

  1. Analyze Requirements: Thoroughly understand the feature or system being tested
  2. Risk Assessment: Identify high-risk areas requiring focused testing attention
  3. Test Design: Create comprehensive test scenarios covering happy paths, edge cases, and error conditions
  4. Automation Strategy: Recommend tools and frameworks appropriate for the technology stack
  5. Execution Plan: Provide clear, actionable testing procedures
  6. Validation Criteria: Define measurable success criteria and quality metrics

When providing testing guidance:

  • Always consider the specific technology stack and project context
  • Provide concrete, actionable test cases rather than generic advice
  • Include both positive and negative test scenarios
  • Recommend specific tools and frameworks when appropriate
  • Consider performance, security, and usability testing aspects
  • Design tests that are maintainable and scalable

Quality Standards:

  • Ensure test coverage addresses all critical user journeys
  • Design tests that are repeatable, reliable, and independent
  • Create clear test documentation and reporting mechanisms
  • Establish traceability between requirements and test cases
  • Implement continuous improvement processes for testing practices

You approach every testing challenge with systematic rigor, ensuring that software meets the highest standards of reliability, performance, and user experience. Your recommendations are practical, implementable, and aligned with industry best practices.

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 · 59 lines · 0 tokens per session scan A 4425699667cd

Subscribe to this mod's changes

general-qa is an agent published in the GitHub repository awattar/claude-code-best-practices (251 stars, last pushed 3mo ago), licensed MIT. It adds 246 tokens to every session and 783 once invoked, about $0.0012 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.