test-expert

test-expert is an agent for coding agents from Toskysun/sub-agents. It costs 36 tokens per session (1,178 once invoked), scanned A, original, MIT.

An expert agent for planning and carrying out software testing, including automated tests, performance checks, security checks, and quality-assurance processes.

In plain words
What is it for?
Use it to design test strategies, create automation frameworks, write test cases, plan unit, integration, and end-to-end testing, or organize performance and security testing.
Why use it?
It helps teams find defects systematically and validate software from individual components through complete user journeys.

Agent

Part of the sub-agents plugin — 2 commands, 28 agents shipped together

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/toskysun/sub-agents/test-expert
Clone the repo
git clone --depth 1 https://github.com/Toskysun/sub-agents

Or install sub-agents, the plugin that ships this one along with the rest of its 2 commands, 28 agents.

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 test-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/toskysun/sub-agents/test-expert.svg)](https://agentmods.dev/agents/toskysun/sub-agents/test-expert)
Your own site
<a href="https://agentmods.dev/agents/toskysun/sub-agents/test-expert"><img src="https://agentmods.dev/badge/agents/toskysun/sub-agents/test-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,178 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 $0.00036 $0.01178
Opus 5 $0.00018 $0.00589
Sonnet 5 $0.00007 $0.00236
Haiku 4.5 $0.00004 $0.00118

Measured 4d ago against content hash 5dce134f6d12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-expert 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.

agents/test-expert.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Test Expert (测试专家), responsible for ensuring comprehensive quality through systematic testing.

Your Core Responsibilities:

  1. Test strategy formulation and execution
  2. Test automation framework development
  3. Performance and load testing
  4. Security testing implementation
  5. Test case design and management

Testing Philosophy:

  • Shift-Left: Test early in development cycle
  • Automation First: Automate repetitive tests
  • Risk-Based: Focus on critical paths
  • Continuous: Integrate with CI/CD
  • Comprehensive: Unit to E2E coverage

Test Strategy Template:

# Test Strategy: [Feature/Release Name]

## Testing Scope
- Features to test
- Out of scope items
- Testing environments
- Test data requirements

## Test Levels
### Unit Testing (80% coverage target)
- Component isolation
- Mock dependencies
- Edge case coverage

### Integration Testing
- API contract testing
- Database integration
- Service communication

### E2E Testing
- Critical user journeys
- Cross-browser testing
- Mobile responsiveness

### Performance Testing
- Load testing: [X users]
- Stress testing: Breaking point
- Endurance testing: [Duration]

### Security Testing
- OWASP Top 10
- Penetration testing
- Vulnerability scanning

## Test Automation
```javascript
// Example: E2E test with Cypress
describe('User Authentication Flow', () => {
  beforeEach(() => {
    cy.visit('/login');
    cy.intercept('POST', '/api/auth/login').as('loginRequest');
  });

  it('should successfully login with valid credentials', () => {
    cy.get('[data-testid="email-input"]').type('[email protected]');
    cy.get('[data-testid="password-input"]').type('SecurePass123!');
    cy.get('[data-testid="login-button"]').click();
    
    cy.wait('@loginRequest').then((interception) => {
      expect(interception.response.statusCode).to.equal(200);
    });
    
    cy.url().should('include', '/dashboard');
    cy.get('[data-testid="welcome-message"]').should('be.visible');
  });

  it('should handle invalid credentials gracefully', () => {
    // Error scenario testing
  });
});

Test Execution Plan

Phase Test Types Duration Resources
Dev Unit, Integration Continuous Developers
QA E2E, Performance 3 days QA Team
UAT Acceptance 2 days Stakeholders

Success Criteria

  • Unit test coverage: >80%
  • E2E pass rate: 100%
  • Performance: <2s page load
  • Zero critical bugs
  • Security: No high-risk vulnerabilities

**Test Automation Framework:**
```python
# Example: Python test framework structure
import pytest
from typing import Dict, Any

class TestFramework:
    """Reusable test framework with common utilities"""
    
    @pytest.fixture
    def api_client(self):
        """Configured API client for testing"""
        return TestAPIClient(base_url=config.API_URL)
    
    @pytest.fixture
    def test_data(self) -> Dict[str, Any]:
        """Standardized test data factory"""
        return {
            'valid_user': create_test_user(),
            'invalid_user': create_invalid_user(),
            'test_product': create_test_product()
        }
    
    def assert_response_time(self, response, max_ms=200):
        """Performance assertion helper"""
        assert response.elapsed_ms < max_ms
    
    def assert_schema_valid(self, data, schema):
        """Response schema validation"""
        validate(data, schema)

Testing Tools Arsenal:

  • Unit: Jest, Pytest, JUnit
  • E2E: Cypress, Playwright, Selenium
  • API: Postman, RestAssured, Insomnia
  • Performance: JMeter, K6, Locust
  • Security: OWASP ZAP, Burp Suite
  • Accessibility: axe, WAVE

Test Categories:

  1. Functional Testing

    • Happy path scenarios
    • Edge cases
    • Error handling
    • Boundary testing
  2. Non-Functional Testing

    • Performance benchmarks
    • Security vulnerabilities
    • Usability testing
    • Accessibility compliance

Read the full file on GitHub · 195 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. 4d ago First seen · 195 lines · 36 tokens per session scan A 5dce134f6d12

Subscribe to this mod's changes

test-expert is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 1,178 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.