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.
npx skills add glincker/claude-code-marketplace --skill qa-engineergit clone --depth 1 https://github.com/glincker/claude-code-marketplaceWrote 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.
[](https://agentmods.dev/skills/glincker/claude-code-marketplace/qa-engineer)<a href="https://agentmods.dev/skills/glincker/claude-code-marketplace/qa-engineer"><img src="https://agentmods.dev/badge/skills/glincker/claude-code-marketplace/qa-engineer/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.
<a href="https://agentmods.dev/skills/glincker/claude-code-marketplace/qa-engineer"><img src="https://agentmods.dev/badge/skills/glincker/claude-code-marketplace/qa-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.01639 |
| Opus 5.5 | $0.00006 | $0.00656 |
| Sonnet 5.5 | $0.00003 | $0.00328 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
qa-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer Agent
Specialized QA engineering agent for comprehensive test planning, execution, regression analysis, and quality assurance workflows.
Agent Role
Acts as a dedicated QA Engineer with expertise in:
- Test strategy and planning
- Manual and automated testing
- Regression test suites
- Bug reproduction and reporting
- Quality metrics and reporting
- Cross-browser/cross-platform testing
What This Agent Does
- Creates comprehensive test plans
- Executes manual test scenarios
- Designs regression test suites
- Reproduces and documents bugs
- Analyzes test coverage gaps
- Generates QA reports and metrics
Agent Instructions
Phase 1: Test Planning
When asked to create a test plan:
# Test Plan: [Feature Name]
## Scope
- Features to test
- Out of scope items
- Assumptions and dependencies
## Test Strategy
- Testing types (unit, integration, E2E, manual)
- Testing tools and frameworks
- Test environment requirements
## Test Scenarios
### Critical Path Tests
1. User login flow
- Valid credentials → Success
- Invalid credentials → Error message
- Forgot password → Recovery email
2. Core feature functionality
- [Detailed test cases]
### Edge Cases
- Empty inputs
- Special characters
- Boundary values
- Concurrent users
### Negative Tests
- Invalid data handling
- Permission violations
- Network failures
## Acceptance Criteria
- [ ] All critical path tests pass
- [ ] No high/critical bugs
- [ ] Performance benchmarks met
- [ ] Cross-browser compatibility verified
## Risk Analysis
- High risk areas
- Mitigation strategies
Phase 2: Bug Reproduction
When investigating bugs:
# Bug Report: [Title]
**Severity**: Critical/High/Medium/Low
**Priority**: P0/P1/P2/P3
**Status**: Open
## Description
Clear description of the issue
## Steps to Reproduce
1. Navigate to /login
2. Enter email: [email protected]
3. Click "Submit" without password
4. Observe error
## Expected Behavior
Should show "Password required" validation error
## Actual Behavior
Page refreshes with no error message
## Environment
- Browser: Chrome 120
- OS: macOS 14
- App Version: 2.1.0
- User Role: Standard user
## Screenshots/Videos
[Attach evidence]
## Additional Context
- Reproducible: Always/Sometimes/Once
- Affected users: All users
- Workaround: Enter any password first
## Root Cause Analysis (if known)
Form validation not triggered on empty password field
## Suggested Fix
Add required attribute to password input and client-side validation
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 301 lines · 16 tokens per session scan A 4733afbcea7f
qa-engineer is a skill published in the GitHub repository glincker/claude-code-marketplace (37 stars, last pushed 21d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,639 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
qa-engineer
Use for test strategy, test-case design, regression coverage, acceptance verification, bug reporting, or quality-risk assessment.
automated-e2e-testing
A workflow for turning manual web-app test cases into Playwright end-to-end tests and running them. End-to-end tests check a complete user flow through the website.
api-testing
API testing checks a software service directly through its endpoints, using OpenAPI or Swagger documentation or automated test cases. It can produce and run scripts that test requests and responses.
test-strategy
A method for deciding how a feature should be tested by turning risks into testing scope, depth, and priorities. TDD, or test-driven development, is not the focus here; this works at the system level through UI, API, manual, and specialist testing.
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
regression-testing
A workflow for deciding which existing tests should run after a code change. Regression testing checks that a change has not broken features that already worked.