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 agentscope-ai/OpenJudge --skill 00-arena-routergit clone --depth 1 https://github.com/agentscope-ai/OpenJudgeWrote 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/agentscope-ai/openjudge/00-arena-router)<a href="https://agentmods.dev/skills/agentscope-ai/openjudge/00-arena-router"><img src="https://agentmods.dev/badge/skills/agentscope-ai/openjudge/00-arena-router/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/agentscope-ai/openjudge/00-arena-router"><img src="https://agentmods.dev/badge/skills/agentscope-ai/openjudge/00-arena-router.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 | $0.00126 | $0.00918 |
| Opus 5 | $0.00063 | $0.00459 |
| Sonnet 5 | $0.00025 | $0.00184 |
| Haiku 4.5 | $0.00013 | $0.00092 |
Grade A, and why
00-arena-router 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arena Eval Router
Entry router for the arena-eval suite. You diagnose what the user wants to
compare models on and route them to the appropriate sub-skill or both when
the request spans both evaluation goals. You don't run comparisons yourself
— you're the triage desk.
Each sub-skill is self-contained: it carries inline everything it needs, so it can be installed and used on its own.
Diagnostic Question
Ask (unless the user's request already makes the answer obvious):
To route you correctly: what are you comparing the models on?
a) A custom task of your own choosing (chatbot quality, summarization,
coding, anything) — you'll get win-rate rankings from a judge model
b) Specifically how often each model fabricates or hallucinates references
when asked to recommend citations
Shortcut rule: if the user already said "run an arena eval on my chatbot task" or "benchmark reference hallucination across these models", skip the question — the routing is already clear from their phrasing. Also skip the question when they explicitly ask for both general quality and citation accuracy; recommend both workflows.
Triage Table
| User says / has | Use workflow | What it does |
|---|---|---|
| "Compare/benchmark/rank these models on [any custom task]" | 01-auto-arena |
Generates queries from a task description, collects responses, auto-generates rubrics, runs pairwise judge comparisons, produces win-rate rankings |
| "Which model hallucinates citations least?" / "benchmark reference recommendation accuracy" | 02-ref-hallucination-arena |
Runs reference-recommendation queries per model, verifies every returned citation against CrossRef/PubMed/arXiv/DBLP, ranks by verified accuracy |
| "Compare general helpfulness AND citation accuracy" | 01-auto-arena, then 02-ref-hallucination-arena |
Runs separate evaluations for judge preference and verified citation accuracy, preserving both goals |
| "I want to review one paper's existing bibliography, not compare models" | — | Not this suite — see the academic-eval suite's 01-paper-review / 02-bib-verify instead |
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.
- today First seen · 84 lines · 126 tokens per session scan A b95c8b33cfe3
00-arena-router is a skill published in the GitHub repository agentscope-ai/OpenJudge (829 stars, last pushed yesterday), licensed Apache-2.0. It adds 126 tokens to every session and 918 once invoked, about $0.0006 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 2026-09-12.
Other skills, from other repositories
tinker-fine-tuning
Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
developer-setup
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. After successful setup this skill is excluded from selection until the marker file is deleted.
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…