Borrowing it
Nothing to install: this file belongs to ekbatan-io/ekbatan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ekbatan-io/ekbatan/main/.agents/skills/ekbatan-verification/SKILL.mdgit clone --depth 1 https://github.com/ekbatan-io/ekbatanWrote 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/ekbatan-io/ekbatan/ekbatan-verification)<a href="https://agentmods.dev/skills/ekbatan-io/ekbatan/ekbatan-verification"><img src="https://agentmods.dev/badge/skills/ekbatan-io/ekbatan/ekbatan-verification/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/ekbatan-io/ekbatan/ekbatan-verification"><img src="https://agentmods.dev/badge/skills/ekbatan-io/ekbatan/ekbatan-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00417 |
| Opus 5.5 | $0.00024 | $0.00167 |
| Sonnet 5.5 | $0.00012 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
ekbatan-verification 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 2mo 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
Ekbatan Verification
Use this skill for test planning and execution in the Ekbatan repository.
First Reads
references/test-matrix.md..github/workflows/ci.ymlfor normal CI..github/workflows/heavy-verification.ymlfor native/heavy coverage.AGENTS.mdfor project conventions.
Default Strategy
-
Run focused tests that target the changed behavior.
-
Run root JVM tests when shared framework code changed:
TESTCONTAINERS_RYUK_DISABLED=true ./gradlew test --max-workers=1 --continue -
Run standalone example JVM tests when examples changed:
agent-skills/ekbatan-verification/scripts/run-jvm-example-tests.sh -
Run native/heavy tests only when explicitly requested or when the change affects native-image behavior. They are expensive.
Reporting
Report exactly what ran and what did not run. Distinguish:
- Root JVM tests.
- Standalone Gradle example JVM tests.
- Standalone Maven example JVM tests.
- Native image tests.
- GitHub Actions heavy verification.
If a command fails due to sandboxing, Docker, dependency cache, or network access, rerun with appropriate approval if available. Do not claim full coverage when only representative tests ran.
GitHub Actions
Heavy verification is manual/scheduled and can be controlled from the GitHub Actions UI through run_mode:
respect-recent-activity: keep the recent-commit gate.force: run the full heavy workflow regardless of recent commits.
Use the workflow rather than local native tests when the user wants CI-equivalent heavy validation.
What ships with it
3 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.
- 2mo ago First seen · 54 lines · 60 tokens per session scan A eb9572e75efc
ekbatan-verification is a skill published in the GitHub repository ekbatan-io/ekbatan (22 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 417 once invoked, about $0.0002 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
java-affected-tests
Use before opening or updating an OpenMetadata PR that changes Java, a JSON schema, an index mapping, a SQL migration, seed data or a pom — PR CI no longer runs the Java integration tests (they run only in the merge queue) and the JavaUIIT/search-it suites run only nightly, so this selects the unit tests and…
oss-fuzz
Run Tika's OSS-Fuzz Jazzer targets locally against a working-tree checkout — build the image, build fuzzers from local source, fuzz a target, run a corpus as a regression pass, reproduce a crash, and add seeds. Use for "fuzz the OneNote parser", "run OneNoteParserFuzzer against these files", "reproduce an OSS-Fuzz…
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".
run-tests
Run project tests using Maven (mvn). Use when the user asks to run tests.
test-proxy
Push test-proxy recordings/assets using the test-proxy CLI (e.g., test-proxy push -a assets.json). Use when publishing recordings.
llm-judge
AI quality judge that scores agent responses 0-10 across helpfulness, accuracy, completeness, and clarity. Use when evaluating multi-agent output or implementing LLM-as-judge quality gates.