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 infews/pxp_skill --skill ears-specificationsgit clone --depth 1 https://github.com/infews/pxp_skillWrote 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/infews/pxp_skill/ears-specifications)<a href="https://agentmods.dev/skills/infews/pxp_skill/ears-specifications"><img src="https://agentmods.dev/badge/skills/infews/pxp_skill/ears-specifications.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 | $0.00046 | $0.00563 |
| Opus 5 | $0.00023 | $0.00282 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
ears-specifications 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.
What it actually says
EARS Specifications
EARS (Easy Approach to Requirements Syntax) is a lightweight requirements format: every spec follows one of five patterns. Each spec should be small enough for a single red-green-refactor cycle.
The Five Patterns
- Ubiquitous (always true): "The system shall [behavior]."
- Event-driven (triggered by action): "When [trigger], the system shall [response]."
- State-driven (while condition holds): "While [state], the system shall [behavior]."
- Optional (feature-dependent): "Where [feature is enabled], the system shall [behavior]."
- Unwanted (error handling): "If [unwanted condition], then the system shall [response]."
Semantic IDs
Use the format {FEATURE}-{TYPE}-{NNN}:
- FEATURE: 2–4 letter prefix derived from the feature area (e.g.,
AUTH,CART,DASH) - TYPE: Component type —
UI,API,DATA,NAV,BE,PROC - NNN: Sequential number, zero-padded (
001,002, ...)
Keep IDs stable. Don't renumber when inserting — use gaps or sub-numbers like AUTH-API-001a.
Converting from Gherkin
One Gherkin scenario often yields multiple EARS specs. Decompose each Given/When/Then into atomic, testable assertions.
Gherkin:
Scenario: Successful login
Given a registered user
When they submit valid credentials
Then a session is created
And they are redirected to the dashboard
EARS:
AUTH-API-001: When valid credentials are submitted, the system shall create a session.AUTH-NAV-001: When a session is created, the system shall navigate to the dashboard.
Common Mistakes
- Spec too big. If you can't write a single test that proves it, split it.
- Two specs in one sentence. "When X, the system shall A and B." Split.
- Renumbering on insertion. Once issued, an ID is permanent. Use gaps or
001a. - Compound TYPE.
AUTH-UI-API-001is two specs masquerading as one. Pick the dominant type, or split.
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 · 52 lines · 46 tokens per session scan A df5658252829
ears-specifications is a skill published in the GitHub repository infews/pxp_skill (20 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 563 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.