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 0x-Professor/Agent-Skills-Hub --skill ml-model-eval-benchmarkgit clone --depth 1 https://github.com/0x-Professor/Agent-Skills-HubWrote 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/0x-professor/agent-skills-hub/ml-model-eval-benchmark)<a href="https://agentmods.dev/skills/0x-professor/agent-skills-hub/ml-model-eval-benchmark"><img src="https://agentmods.dev/badge/skills/0x-professor/agent-skills-hub/ml-model-eval-benchmark/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/0x-professor/agent-skills-hub/ml-model-eval-benchmark"><img src="https://agentmods.dev/badge/skills/0x-professor/agent-skills-hub/ml-model-eval-benchmark.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 | $0.00028 | $0.00153 |
| Opus 5 | $0.00014 | $0.00077 |
| Sonnet 5 | $0.00006 | $0.00031 |
| Haiku 4.5 | $0.00003 | $0.00015 |
Grade A, and why
ml-model-eval-benchmark 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 11d 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
ML Model Eval Benchmark
Overview
Produce consistent model ranking outputs from metric-weighted evaluation inputs.
Workflow
- Define metric weights and accepted metric ranges.
- Ingest model metrics for each candidate.
- Compute weighted score and ranking.
- Export leaderboard and promotion recommendation.
Use Bundled Resources
- Run
scripts/benchmark_models.pyto generate benchmark outputs. - Read
references/benchmarking-guide.mdfor weighting and tie-break guidance.
Guardrails
- Keep metric names and scales consistent across candidates.
- Record weighting assumptions in the output.
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.
- 11d ago First seen · 28 lines · 28 tokens per session scan A 9b652ff17efa
ml-model-eval-benchmark is a skill published in the GitHub repository 0x-Professor/Agent-Skills-Hub (10 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 153 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
llm-inference-benchmark
Benchmark OpenAI-compatible LLM inference servers (vLLM, SGLang, or anything serving /v1/completions; local, cross-host via TARGETHOST= , or behind a TLS+Bearer proxy via --base-url + OPENAIAPIKEY) with sglang.benchserving run as a standalone dockerized client — one engine-agnostic script (scripts/benchsweep.sh)…
deploy-kimi-k26-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, MLA, 256K context, vision) in a user-chosen quantization — official INT4 QAT (moonshotai/Kimi-K2.6, compressed-tensors→Marlin; vLLM or SGLang) or NVFP4 (nvidia/Kimi-K2.6-NVFP4, ModelOpt FP4; vLLM only — SGLang NVFP4 is NaN-broken on sm120) — on a Linux server (verified…
deploy-kimi-k3-on-rtx-pro-6000
Deploy and serve Moonshot Kimi-K3 (2.8T MoE, hybrid KDA+MLA attention, native vision via MoonViT-3d) from Unsloth's GGUF quantizations (unsloth/Kimi-K3-GGUF) via llama.cpp on a Linux server with 8x NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB, sm120) GPUs. Unlike vLLM/SGLang's tensor-parallel all-in-VRAM…
prompt-engineering
Prompt engineering workflow for designing, rewriting, debugging, evaluating, and optimizing LLM prompts, system prompts, developer prompts, few-shot examples, structured-output instructions, tool-use prompts, and prompt eval cases. Use when prompt behavior, reliability, safety, cost, latency, or model fit is the main…
ubuntu-nvidia-gpu-enablement
Enable NVIDIA GPUs on a Ubuntu server for compute/inference serving — install the open-kernel-module driver (required for Blackwell/Hopper), CUDA toolkit, turn on IOMMU (inteliommu=on iommu=pt), set up nvidia-persistenced, and install/wire a container runtime (Docker + nvidia-container-toolkit, or the minimal CLI)…