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 AdamBien/airails --skill ears-testsgit clone --depth 1 https://github.com/AdamBien/airailsWrote 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/adambien/airails/ears-tests)<a href="https://agentmods.dev/skills/adambien/airails/ears-tests"><img src="https://agentmods.dev/badge/skills/adambien/airails/ears-tests/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/adambien/airails/ears-tests"><img src="https://agentmods.dev/badge/skills/adambien/airails/ears-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 47 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00206 | $0.01327 |
| Opus 5.5 | $0.00082 | $0.00531 |
| Sonnet 5.5 | $0.00041 | $0.00265 |
| Haiku 4.5 | $0.00021 | $0.00133 |
Grade A, and why
ears-tests 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn EARS requirement statements into parameterized tests. The leverage is structural: every
EARS pattern is a (condition → response) tuple, and an SBCE requirement group already
collects statements that share one boundary operation — same arrange/act skeleton, only the
data differs. That is the textbook precondition for parameterization, so the mapping is mechanical.
Own only the transform and the trace. The concrete test syntax is the composed stack skill's call — never name a runner or framework verb here. When the generated tests exercise the running system, the system-tests skill owns the contract (black box, coordinates as configuration, total verdict reporting).
The mapping
- One requirement group
Rn→ one parameterized test method (the shared boundary op is the body). - One statement
Rn.m→ one row in the parameter source. - The statement id
Rn.mis the row's display name — so the spec↔test binding stays per-statement and grep-visible, exactly as SBCE requires (a removed id retires its row; a row with no statement is drift). - The id MUST surface in the runner-visible case label — as a string literal or as a symbol whose display form is the literal id. An id that appears only in a comment is not a trace.
- The EARS pattern fixes the row's role and shape — you do not invent the columns, you read them off the pattern.
EARS pattern → row shape
The system is always the BC. Each pattern decomposes into the arrange/act/assert columns of a row:
| Pattern | Statement shape | Arrange (state) | Act (trigger) | Assert (response) | Role |
|---|---|---|---|---|---|
| Event-driven | When <trigger>, the BC shall <response> |
— | trigger | response | happy |
| Unwanted-behaviour | If <trigger>, then the BC shall <response> |
— | bad/invalid trigger | rejection / error | unhappy |
| State-driven | While <precondition>, the BC shall <response> |
precondition | (implicit) | response | stateful |
| Complex | While <precondition>, when <trigger>, the BC shall <response> |
precondition | trigger | response | full tuple |
| Optional-feature | Where <feature>, the BC shall <response> |
feature enabled | trigger | response | gated |
| Ubiquitous | The BC shall <response> |
— | — | invariant | single case (least parameterizable — a plain test is fine) |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 74 lines · 206 tokens per session scan A b1b2bc4afa1f
ears-tests is a skill published in the GitHub repository AdamBien/airails (60 stars, last pushed today), licensed MIT. It adds 206 tokens to every session and 1,327 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
simulation-validator
Validate simulations across three stages — run pre-flight checks on configuration files (parameter ranges, required fields, disk space), monitor runtime logs for residual growth, NaN/Inf, and adaptive dt collapse, and perform post-flight validation of results (physical bounds, mass/energy conservation, convergence).…
skill-evaluator
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta…
unit-test-parameterized
Provides parameterized testing patterns with JUnit 5, generates data-driven unit tests using @ParameterizedTest, @ValueSource, @CsvSource, @MethodSource. Creates tests that run the same logic with multiple input values. Use when writing data-driven Java tests, multiple test cases from single method, or boundary value…
unit-test-scheduled-async
Provides patterns for unit testing Spring @Scheduled and @Async methods using JUnit 5, CompletableFuture, Awaitility, and Mockito. Covers mocking task execution and timing, verifying execution counts, testing cron expressions, validating retry behavior, and simulating thread pool behavior. Use when testing background…
unit-test-mapper-converter
Provides patterns for unit testing mappers, converters, and bean mappings. Validates entity-to-DTO and model transformation logic in isolation. Generates executable mapping tests with MapStruct and custom converter test coverage. Use when writing mapping tests, converter tests, entity mapping tests, or ensuring…
unit-test-service-layer
Provides patterns for unit testing service layer with Mockito. Creates isolated tests that mock repository calls, verify method invocations, test exception scenarios, and stub external API responses. Use when testing service behaviors and business logic without database or external services.