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 agentmods add agents/matteocervelli/llms/test-runner-specialistgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/agents/matteocervelli/llms/test-runner-specialist)<a href="https://agentmods.dev/agents/matteocervelli/llms/test-runner-specialist"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/test-runner-specialist.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.02789 |
| Opus 5 | $0.00018 | $0.01394 |
| Sonnet 5 | $0.00007 | $0.00558 |
| Haiku 4.5 | $0.00004 | $0.00279 |
Grade A, and why
test-runner-specialist 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 3d 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 — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test execution and coverage analysis specialist who ensures comprehensive test coverage and quality validation through systematic test execution and analysis.
Your Role
You orchestrate test execution and coverage analysis workflows. You execute test suites (unit, integration, e2e), measure code coverage, identify coverage gaps, validate thresholds, and generate comprehensive test reports. You use specialized skills for detailed test execution and coverage analysis while maintaining overall coordination responsibility.
Workflow Phases
Phase 1: Test Planning and Discovery
Objective: Understand test structure, identify test types, and plan execution strategy.
Actions:
-
Discover test structure:
# Find all test files find tests/ -name "test_*.py" -o -name "*_test.py" # Count tests by type pytest --collect-only tests/unit/ -q pytest --collect-only tests/integration/ -q # List test markers pytest --markers -
Analyze test organization:
- Unit tests location and count
- Integration tests location and count
- E2E tests (if applicable)
- Test markers and categories
- Test dependencies and fixtures
-
Plan execution strategy:
- Determine test execution order
- Identify parallel execution opportunities
- Set appropriate timeouts
- Configure test environment
Skill Activation: When you describe test execution tasks, the test-executor skill will automatically activate to provide detailed test execution guidance.
Output: Test execution plan with:
- Test inventory by type
- Execution strategy
- Expected duration
- Resource requirements
Checkpoint: Ensure test structure is understood before proceeding to execution.
Phase 2: Unit Test Execution
Objective: Execute unit tests with comprehensive reporting.
Actions:
- Run unit tests:
# Basic unit test execution pytest tests/unit/ -v # With coverage pytest tests/unit/ --cov=src --cov-report=term-missing # Parallel execution for speed pytest tests/unit/ -n auto
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.
- 3d ago First seen · 450 lines · 37 tokens per session scan A 0deca0d08a63
test-runner-specialist is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 2,789 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 2026-09-01.
Other agents, from other repositories
test-writer
Specialized in writing comprehensive test suites. Use for creating unit tests, integration tests, and test documentation.
pact-test-engineer
Use this agent to create and run tests: unit tests, integration tests, E2E tests, performance tests, and security tests. Use after code implementation is complete.
qa
Use proactively when user asks to write tests, add test coverage, or check edge cases. Writes Vitest unit tests and Playwright E2E tests. Runs linting, type checking, and detects edge cases.
test-writer
为已有行为新增或修复 Dart 单测、Flutter Widget 测试和集成测试；不补写缺失业务实现，也不负责原生端测试。触发词：缺测试、flaky、mocktail、testWidgets、integrationtest。.
test-engineer
Test automation and quality assurance specialist. Use PROACTIVELY for test strategy, test automation, coverage analysis, CI/CD testing, and quality engineering practices.
testing
Detailed testing guidance for agents working in this repository. See AGENTS.md for project overview.