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-mlflowgit 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-mlflow)<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-mlflow"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-mlflow/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/opendatahub-io/agent-eval-harness/eval-mlflow"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-mlflow.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 | $0.00103 | $0.01976 |
| Opus 5 | $0.00051 | $0.00988 |
| Sonnet 5 | $0.00021 | $0.00395 |
| Haiku 4.5 | $0.00010 | $0.00198 |
Grade A, and why
eval-mlflow 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 12d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MLflow integration agent. You bridge the evaluation harness with MLflow — syncing datasets, logging results, and managing feedback bidirectionally between the harness's file-based pipeline and MLflow's experiment tracking.
Step 0: Parse Arguments
Parse $ARGUMENTS for:
| Argument | Required | Default | Description |
|---|---|---|---|
--action <action> |
no | all |
One of: sync-dataset, log-results, push-feedback, pull-feedback, all |
--config <path> |
no | auto-discover | Path to eval config |
--run-id <id> |
for log/push/pull | — | Which eval run to log or attach feedback to |
Config Discovery
If --config was explicitly provided, use that path directly. Otherwise, auto-discover:
python3 ${CLAUDE_SKILL_DIR}/../../scripts/discover.py
- 1 config found: auto-select it as
<config> - Multiple configs found: present the list and ask the user which eval to operate on
- No configs found: error, suggest running
/eval-analyzefirst
Step 1: Verify MLflow
Check MLflow is configured:
PYTHONPATH=${CLAUDE_SKILL_DIR}/scripts python3 -c "
from agent_eval.mlflow.experiment import ensure_server
if ensure_server():
print('MLflow server: OK')
else:
print('MLflow server: not reachable')
import os
print(f'MLFLOW_TRACKING_URI={os.environ.get(\"MLFLOW_TRACKING_URI\", \"not set\")}')
"
If not configured, suggest running /eval-setup first. The scripts resolve the tracking URI from mlflow.tracking_uri in eval.yaml first, then MLFLOW_TRACKING_URI env var, then default to http://127.0.0.1:5000. If the server is unreachable but a remote URI is set, proceed — the scripts handle connectivity errors by logging warnings and exiting cleanly.
Step 2: Read Configuration
Read eval.yaml to understand:
mlflow.experiment— the experiment namedataset.pathanddataset.schema— where cases are and what they look likejudges— what was scored (for feedback context)
What ships with it
6 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.
- 12d ago First seen · 185 lines · 103 tokens per session scan A 0be9a3e64c14
eval-mlflow is a skill published in the GitHub repository opendatahub-io/agent-eval-harness (41 stars, last pushed 9d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,976 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…