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 niels-emmer/myace --skill test-strategygit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/test-strategy)<a href="https://agentmods.dev/skills/niels-emmer/myace/test-strategy"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/test-strategy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/niels-emmer/myace/test-strategy"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/test-strategy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00461 |
| Opus 5 | $0.00015 | $0.00230 |
| Sonnet 5 | $0.00006 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
Test Strategy 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.
What it actually says
Purpose
A test suite that's the right shape is cheap to run and catches real regressions. This skill is a checklist for deciding what to test at what level, so effort goes where the risk is rather than into a slow, brittle suite that mostly re-tests the same paths.
When to use it
When starting a new feature, adding tests to an existing one, or reviewing whether a suite is well-shaped. Also when a suite has grown unwieldy and needs rebalancing.
Checklist
- Shape it like a pyramid. Most tests at the unit level (fast, isolated), fewer at integration (boundaries between components), fewest at e2e (critical user journeys). A cone — lots of slow e2e tests — is a maintenance trap.
- Test at the level that exercises the behavior. Logic belongs in unit tests; a frontend-backend contract belongs in an integration test; a multi-service user journey belongs in e2e. Don't write a slow e2e test for something a unit test covers.
- Risk-based depth. The deeper the test investment, the higher the change risk: auth, payments, data migration, and concurrency deserve more coverage than a pure UI copy change.
- Cover failure modes deliberately. Boundaries, empty/null input, partial failures, concurrency, and authorization denials — the happy path is the least likely case to break in production.
- Coverage is a signal, not a target. Use coverage to find untested paths, not as a pass/fail gate. A covered module with no behavioral assertions isn't tested.
Expected output
A suite that's fast enough to run often, shaped like a pyramid, and concentrated on the behaviors most likely to break — with failure modes covered deliberately rather than by accident.
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 · 27 lines · 29 tokens per session scan A b91548997a1f
Test Strategy is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 461 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
loom-test-strategy
Test strategy guidance covering pyramid design, coverage, test categorization, flaky tests, infrastructure, and risk-based prioritization.
loom-testing
Test implementation across unit, integration, e2e, security, infrastructure, data pipeline, and ML domains.
testing-setup
Analyze and create a testing strategy for native Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
testing-strategies
Comprehensive testing strategy covering unit, integration, e2e, property-based, and mutation testing with practical patterns.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
frontend-testing
Comprehensive frontend testing strategy covering unit, integration, E2E, visual regression, and accessibility testing.