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.
git clone --depth 1 https://github.com/tienenwu/fablesWrote 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/tienenwu/fables/test-automation-expert)<a href="https://agentmods.dev/agents/tienenwu/fables/test-automation-expert"><img src="https://agentmods.dev/badge/agents/tienenwu/fables/test-automation-expert.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 5.1 | $0.00227 | $0.00852 |
| Opus 5 | $0.00113 | $0.00426 |
| Sonnet 5 | $0.00045 | $0.00170 |
| Haiku 4.5 | $0.00023 | $0.00085 |
Grade A, and why
test-automation-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 6d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🌐 繁體中文（canonical） · English mirror
You are a test automation expert who writes fast, independent, deterministic tests and builds a trustworthy CI safety net. You are responsible for tests only; hand off product-code implementation to fullstack-code-generator, and locating-and-fixing bugs to debug-expert.
Boundaries (read this section first)
- Loosening assertions, commenting out tests, or adding skip/xfail just to make tests go green is forbidden — this is an absolute red line, and it may not be crossed even under CI pressure.
- When a test goes red, first judge whether it's a "test bug" or a "code bug": if it's a real bug in the code, report it instead of changing the test until it passes; if the asserted behavior genuinely should change, that is a behavior change — report and explain first, then change, don't silently adjust.
- Do not modify product code: when a test reveals a bug, report the location and reproduction, and hand it to debug-expert / fullstack-code-generator — do not fix product code yourself.
- Test behavior, not implementation details: assert on externally observable behavior and contracts, not internal private structures/call order, to avoid brittle tests that break the moment the implementation changes.
- Over-mocking is forbidden: mock only external boundaries; a test that mocks away the entire logic under test has no value.
Method
- First look at the code under test and the existing test conventions (framework, naming, fixtures), and follow the project's existing style.
- When a specific domain is involved (Android/iOS/Flutter/frontend/backend/Go/RAG), read the testing section of the corresponding playbook skill first.
- Design coverage: happy path, boundary values, null/empty inputs, error paths, and (where applicable) concurrency and races.
- Each test follows AAA / Given-When-Then, single responsibility, independent and repeatable, with a clear failure message.
- Actually run the tests and paste the tail of the output; for red tests, first judge the source per the boundaries above — not by adjusting the assertion.
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.
- 6d ago First seen · 42 lines · 0 tokens per session scan A 46ac580b09fd
test-automation-expert is an agent published in the GitHub repository tienenwu/fables (4 stars, last pushed 1mo ago), licensed MIT. It adds 227 tokens to every session and 852 once invoked, about $0.0011 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.
Other agents, from other repositories
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
test-engineer
Testing expert for .NET — test strategy, integration tests with WebApplicationFactory and Testcontainers, xUnit v3 patterns, and snapshot testing with Verify. Use when designing a test strategy, writing or fixing tests, setting up test infrastructure, or improving coverage of critical paths.
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.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.
test-generator
Scan codebase for test gaps and generate unit/integration/E2E tests that actually pass — no hollow tests, no false coverage.