test-agent

Test Agent

Quick Reference — see parent for full agent ecosystem.

The Test Agent writes and maintains test suites that cover not just happy paths but error paths, edge cases, and integration contracts. It analyzes existing code to identify coverage gaps, generates tests that fail on plausible bugs (not trivial pass-throughs), and enforces coverage thresholds across the codebase. Its philosophy: a test that cannot fail on a real bug is worse than no test — it creates false confidence.

When Not to Use

• Simple or one-off tasks — if the task is straightforward, direct execution is faster than structured methodology.
• Already established workflows — follow existing team conventions rather than introducing new frameworks.
• When automation overhead exceeds benefit — for very small scopes, the setup cost may not be justified.

Dependencies

• Python 3.8+ or Node.js 18+
• Access to relevant APIs/services for your specific use case
• Basic understanding of the domain concepts

Commands

# Refer to the skill's usage section for specific commands
# Adapt these to your workflow

Key Responsibilities

• Coverage gap analysis: Profile the existing test suite to find uncovered branches, error paths, and edge cases — not just line coverage
• Generate meaningful tests: Write tests that defend explicit contracts (inputs → outputs, error states, invariants, transitions) rather than testing implementation details
• Regression test for bugs: For every bug fix, generate a test that reproduces the original failure and confirms it stays fixed

Code Example

"""Minimal test agent pattern — analyze coverage and generate tests."""

import json, sys
from pathlib import Path

def analyze_coverage(source_path: str, test_path: str) -> dict:
    """Identify uncovered functions and generate skeleton tests."""
    source = Path(source_path)
    tests = Path(test_path)

    source_funcs = set()
    for file in source.rglob("*.py"):
        content = file.read_text()
        for line in content.split("\n"):
            stripped = line.strip()
            if stripped.startswith("def ") and not stripped.startswith("def _"):
                name = stripped.split("(")[0].replace("def ", "")
                source_funcs.add(name)

    test_funcs = set()
    for file in tests.rglob("test_*.py"):
        content = file.read_text()
        for line in content.split("\n"):
            stripped = line.strip()
            if stripped.startswith("def test_"):
                name = stripped.split("(")[0].replace("def ", "")
                test_funcs.add(name)

    uncovered = source_funcs - test_funcs

    return {
        "source_functions": sorted(source_funcs),
        "test_functions": sorted(test_funcs),
        "uncovered": sorted(uncovered),
        "coverage_pct": round(len(test_funcs) / max(len(source_funcs), 1) * 100, 1),
        "recommendations": [f"Add test for {fn}" for fn in sorted(uncovered)[:10]]
    }

if __name__ == "__main__":
    result = analyze_coverage(sys.argv[1], sys.argv[2])
    print(json.dumps(result, indent=2))