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 Jarroslav/agentic-os --skill eval-harnessgit clone --depth 1 https://github.com/Jarroslav/agentic-osWrote 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/jarroslav/agentic-os/eval-harness)<a href="https://agentmods.dev/skills/jarroslav/agentic-os/eval-harness"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/eval-harness/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/jarroslav/agentic-os/eval-harness"><img src="https://agentmods.dev/badge/skills/jarroslav/agentic-os/eval-harness.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 | $0.00000 | $0.02096 |
| Opus 5.5 | $0.00000 | $0.00838 |
| Sonnet 5.5 | $0.00000 | $0.00419 |
| Haiku 4.5 | $0.00000 | $0.00210 |
Grade A, and why
eval-harness 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Harness
Bootstrap repo-wide evaluation for skill and agent instruction files. Two layers, one spec file per target.
| Layer | Mechanism | Failure class caught | Cost profile |
|---|---|---|---|
| Contract | Code-only checks, zero LLM calls | Structural rot: missing files, edited-away instructions, oversized bodies, broken helper scripts | Cheap — safe to run on every commit |
| Judge | Candidate model executes the skill against a case prompt; judge model grades output vs assertions | Behavioral drift: skill still loads but no longer behaves as designed | Model calls — on demand or scheduled |
Both layers exist because they detect different failure classes. Route structure to code checks and behavior to the judge: never regex-grade prose, never burn a model call to confirm a file exists.
Both layers read the same spec, eval/evals.json, colocated inside each target's directory. A spec with contracts and no behavioral cases is valid. Each judge case runs N repetitions, so flakiness surfaces as a pass rate instead of a binary verdict.
eval/here is notevals/in the agentic-os marketplace repo, and the near-collision is deliberate to name rather than rename. This skill writes<target>/eval/evals.jsoninto your repo. The marketplace repo's own CI (tests/lib/check-skill-contract.py) separately requires<skill>/evals/evals.jsonfor the skills it ships. Different scope, different owner, no conflict — except when you point this skill at the marketplace repo itself, where you will end up with both. In that one case keep the plugin'sevals/as the shipped contract and treat the generatedeval/as local scaffolding.
Blast radius: R2 — this skill writes harness code, spec files, and config into the repo. Judge runs place outbound model calls; automation wiring is opt-in and confirmed first. It never creates real credential files and never gates merges on paid model runs.
Inputs
Collect during the interview phase. Ask only what the repo has not already answered; confirm inferences rather than re-asking.
What ships with it
18 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.
- assets/ci/hooks/pre-commit 1.2 KB
- assets/python/evals.example.json 1.8 KB
- assets/python/llm_eval_runner.py 31 KB runs code
- assets/python/runner.py 17 KB runs code
- assets/python/test_runner.py 14 KB runs code
- assets/typescript/evals.example.json 2.2 KB
- assets/typescript/llm_eval_runner.mts 33 KB
- assets/typescript/runner.test.ts 18 KB runs code
- assets/typescript/runner.ts 23 KB runs code
- assets/typescript/skill-contracts.test.ts 2.0 KB runs code
- assets/typescript/tsconfig.json 997 B
- evals/evals.json 7.5 KB
- README.md 3.0 KB
- references/ci.md 7.3 KB
- references/eval-spec.md 9.9 KB
- references/judge-providers.md 7.2 KB
- references/python.md 7.4 KB
- references/typescript.md 6.2 KB
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 · 128 lines · 0 tokens per session scan A 0d58f1a89cec
eval-harness is a skill published in the GitHub repository Jarroslav/agentic-os (0 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,096 tokens. 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
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.
tdd
Guided test-driven development workflow for .NET 10 using xUnit v3, WebApplicationFactory, Testcontainers, and Verify snapshots. Follows the strict red-green-refactor cycle. Use when: "TDD", "test-driven", "let's TDD this", "red green refactor", "write the test first", or when building a feature with clear acceptance…