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 Miaoge-Ge/coding-agent-skills --skill testing-expertgit clone --depth 1 https://github.com/Miaoge-Ge/coding-agent-skillsWrote 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/miaoge-ge/coding-agent-skills/testing-expert)<a href="https://agentmods.dev/skills/miaoge-ge/coding-agent-skills/testing-expert"><img src="https://agentmods.dev/badge/skills/miaoge-ge/coding-agent-skills/testing-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 | $0.00087 | $0.01031 |
| Opus 5 | $0.00044 | $0.00515 |
| Sonnet 5 | $0.00017 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
testing-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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Testing Expert
Test behavior, not implementation — that's what survives refactors. Fast and deterministic beats exhaustive. A bug fixed without a failing test first will come back.
When to Use
- Writing unit/integration/e2e tests for new or existing code.
- Designing a test strategy or adopting TDD.
- Flaky, slow, or brittle tests that break on harmless changes.
- Mocking/stubbing, fixtures, fakes, and coverage decisions.
When NOT to Use
- LLM/model evaluation specifically →
llm-testing-expert. - Diagnosing a specific known failure →
debugging-expert. - Performance benchmarking →
performance-expert.
Core Principles
1. Test the contract, not the internals
- Assert on observable behavior and public outputs/effects, not private methods or call counts. Tests coupled to implementation block refactoring and create false failures.
- Follow the test pyramid: many fast unit tests, fewer integration tests, a thin layer of e2e for critical user journeys. Push detail down to the cheapest level that can catch the bug.
- Cover edge cases and error paths, not just the happy path. Boundary values, empties, nulls, concurrency, and failures are where bugs live.
2. Good test shape
- Arrange–Act–Assert, one behavior per test, names that state the expectation (
returns 401 when token expired). - Tests must be deterministic and independent: no shared mutable state, no order dependence, no real clock/network/randomness leaking in.
3. Test doubles, sparingly
- Mock/stub/fake only at boundaries you don't own (network, DB, clock, filesystem, randomness). Never mock the unit under test.
- Inject those dependencies (time, IDs, I/O) so tests control them. Prefer fakes (in-memory impl) over brittle mock-verification chains. Over-mocking tests the mocks, not the code.
4. Reliability & coverage
- Eliminate flakiness at the source: fake time,
awaitreal conditions instead ofsleep, control async ordering, isolate test data. Quarantine and fix flaky tests — don't retry-until-green. - Coverage finds untested branches; it's a flashlight, not a goal. 100% coverage of trivial code ≠ quality; a critical untested branch at 90% is the real risk.
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.
- 7d ago First seen · 78 lines · 87 tokens per session scan A cca49c7c7bf8
testing-expert is a skill published in the GitHub repository Miaoge-Ge/coding-agent-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,031 once invoked, about $0.0004 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 skills, from other repositories
Cursor Skill (.mdc) Authoring
Author effective Cursor rules in .cursor/rules/.mdc - YAML frontmatter (description, globs, alwaysApply), the four rule types, scoped QA rules, subagents, and structure that actually steers the model.
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
vibeflow-hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Use when a defect was observed and the evidence is in hand — an error message, a failing log, real data misbehaving — wherever…
vibeflow-audit
Audits implementation against its DoD and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. With --consolidate-hotfixes, reclassifies hotfix trace docs against the…
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…