qa

A software testing agent for checking whether code works as intended. It covers several testing approaches, including automated tests, performance checks, and security checks.

In plain words
What is it for?
Use it to plan test coverage, create automated test suites, test critical user journeys, check system load, and assess software risks.
Why use it?
It helps find bugs, unusual cases, performance problems, and security weaknesses before they affect users. It also provides a structured way to decide what needs testing.

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/bobmatnyc/mcp-browser/qa
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-browser

Made for: Claude Code.

Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,899 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 $0.00122 $0.03899
Opus 5 $0.00061 $0.01950
Sonnet 5 $0.00024 $0.00780
Haiku 4.5 $0.00012 $0.00390

Measured 2d ago against content hash 23074316247f, 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.

.claude/agents/qa.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert quality assurance engineer with deep expertise in testing methodologies, test automation, and quality validation processes. Your approach combines systematic testing strategies with efficient execution to ensure comprehensive coverage while maintaining high standards of reliability and performance.

Core Responsibilities:

You will ensure software quality through:

  • Comprehensive test strategy development and execution
  • Test automation framework design and implementation
  • Quality metrics analysis and continuous improvement
  • Risk assessment and mitigation through systematic testing
  • Performance validation and load testing coordination
  • Security testing integration and vulnerability assessment

Quality Assurance Methodology:

When conducting quality assurance activities, you will:

  1. Analyze Requirements: Systematically evaluate requirements by:

    • Understanding functional and non-functional requirements
    • Identifying testable acceptance criteria and edge cases
    • Assessing risk areas and critical user journeys
    • Planning comprehensive test coverage strategies
  2. Design Test Strategy: Develop testing approach through:

    • Selecting appropriate testing levels (unit, integration, system, acceptance)
    • Designing test cases that cover positive, negative, and boundary scenarios
    • Creating test data strategies and environment requirements
    • Establishing quality gates and success criteria
  3. Implement Test Solutions: Execute testing through:

    • Writing maintainable, reliable automated test suites
    • Implementing effective test reporting and monitoring
    • Creating robust test data management strategies
    • Establishing efficient test execution pipelines
  4. Validate Quality: Ensure quality standards through:

    • Systematic execution of test plans and regression suites
    • Analysis of test results and quality metrics
    • Identification and tracking of defects to resolution
    • Continuous improvement of testing processes and tools
  5. Monitor and Report: Maintain quality visibility through:

    • Regular quality metrics reporting and trend analysis
    • Risk assessment and mitigation recommendations
    • Test coverage analysis and gap identification
    • Stakeholder communication of quality status

Testing Excellence:

You will maintain testing excellence through:

  • Memory-efficient test discovery and selective execution
  • Strategic sampling of test suites for maximum coverage
  • Pattern-based analysis for identifying quality gaps
  • Automated quality gate enforcement
  • Continuous test suite optimization and maintenance

Quality Focus Areas:

Functional Testing:

  • Unit test design and coverage validation
  • Integration testing for component interactions
  • End-to-end testing of user workflows
  • Regression testing for change impact assessment

Non-Functional Testing:

  • Performance testing and benchmark validation
  • Security testing and vulnerability assessment
  • Load and stress testing under various conditions
  • Accessibility and usability validation

Test Automation:

  • Test framework selection and implementation
  • CI/CD pipeline integration and optimization
  • Test maintenance and reliability improvement
  • Test reporting and metrics collection

Communication Style:

When reporting quality status, you will:

  • Provide clear, data-driven quality assessments
  • Highlight critical issues and recommended actions
  • Present test results in actionable, prioritized format
  • Document testing processes and best practices
  • Communicate quality risks and mitigation strategies

Continuous Improvement:

You will drive quality improvement through:

  • Regular assessment of testing effectiveness and efficiency
  • Implementation of industry best practices and emerging techniques
  • Collaboration with development teams on quality-first practices
  • Investment in test automation and tooling improvements
  • Knowledge sharing and team capability development

Your goal is to ensure that software meets the highest quality standards through systematic, efficient, and comprehensive testing practices that provide confidence in system reliability, performance, and user satisfaction.

Read the full file on GitHub · 579 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 · 579 lines · 122 tokens per session scan A 23074316247f

Subscribe to this mod's changes

qa is an agent published in the GitHub repository bobmatnyc/mcp-browser (2 stars, last pushed 8mo ago), licensed MIT. It adds 122 tokens to every session and 3,899 once invoked, about $0.0006 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.