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 opendatahub-io/agent-eval-harness --skill eval-setupgit clone --depth 1 https://github.com/opendatahub-io/agent-eval-harnessWrote 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/opendatahub-io/agent-eval-harness/eval-setup)<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-setup"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-setup.svg" alt="Measured on agentmods" 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 | $0.00148 | $0.02568 |
| Opus 5 | $0.00074 | $0.01284 |
| Sonnet 5 | $0.00030 | $0.00514 |
| Haiku 4.5 | $0.00015 | $0.00257 |
Grade A, and why
eval-setup 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 8d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an environment configurator. You verify the evaluation harness environment, configure optional integrations like MLflow, and suggest evaluation modes based on what's available in the repository. Non-destructive: skip steps that are already done, report status.
Most users can skip this skill entirely — dependencies auto-install via the plugin's SessionStart hook, and agent_eval is available to scripts via symlinks. This skill is useful for configuring MLflow tracking, troubleshooting dependency issues, verifying the environment, and discovering what evaluation modes are available.
The eval pipeline is: /eval-analyze → /eval-dataset → /eval-run → /eval-review or /eval-optimize. /eval-mlflow can be invoked at any point after /eval-run. MLflow tracing is handled by /eval-mlflow after a run completes. No tracing setup is needed here.
Step 0: Parse Arguments
Parse $ARGUMENTS for:
| Argument | Required | Default | Description |
|---|---|---|---|
--tracking-uri <uri> |
no | auto-detect | MLflow tracking URI (skips interactive setup) |
--skip-mlflow |
no | false | Skip MLflow setup entirely |
--runs-dir <path> |
no | eval/runs |
Directory where eval runs are stored |
--harbor |
no | false | Install Harbor + Kubernetes for containerized execution (~650 MB) |
Step 1: Install Dependencies (if needed)
Dependencies are managed in an isolated venv at <plugin_root>/.eval-venv/. The SessionStart hook creates this venv automatically. Scripts auto-activate it via agent_eval._bootstrap on import.
This step is a fallback for mid-session installs or troubleshooting. Re-run the hook's install script:
python3 "${CLAUDE_SKILL_DIR}/../../scripts/ensure_deps.py" "${CLAUDE_PLUGIN_DATA:-${XDG_STATE_HOME:-$HOME/.local/state}/agent-eval-data}"
To check the venv status:
VENV_PYTHON="${CLAUDE_SKILL_DIR}/../../.eval-venv/bin/python3"
test -x "$VENV_PYTHON" && echo "venv: OK" || echo "venv: MISSING"
"$VENV_PYTHON" -c "import yaml; print('pyyaml: OK')" 2>&1 || echo "pyyaml: MISSING"
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.
- 8d ago First seen · 246 lines · 148 tokens per session scan A 3a5ca1800a5a
eval-setup is a skill published in the GitHub repository opendatahub-io/agent-eval-harness (40 stars, last pushed 5d ago), licensed Apache-2.0. It adds 148 tokens to every session and 2,568 once invoked, about $0.0007 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.