eval-compare

eval-compare is a skill for Claude Code from opendatahub-io/agent-eval-harness. It costs 84 tokens per session (1,454 once invoked), scanned A, original, Apache-2.0.

A tool for comparing evaluation results from multiple AI models or runs in one HTML report. An evaluation is a set of tests used to measure how well a model or system performs.

In plain words
What is it for?
Scanning evaluation artifacts and generating a self-contained report with model summaries, quality and cost tables, case-by-case results, and the original reports.
Why use it?
It puts quality, cost, and per-test differences in one view instead of requiring separate reports to be inspected manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the agent-eval-harness plugin — 10 skills shipped together

Good fit Scanning evaluation artifacts and generating a self-contained report with model summaries, quality and cost tables, case-by-case results, and the original reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opendatahub-io/agent-eval-harness/eval-compare
Install

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.

Any agent
npx skills add opendatahub-io/agent-eval-harness --skill eval-compare
Clone the repo
git clone --depth 1 https://github.com/opendatahub-io/agent-eval-harness

Made for: Claude Code.

Or install agent-eval-harness, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for eval-compare

README.md
[![agentmods](https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-compare/github.svg)](https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-compare)
Your own site
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-compare"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-compare/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.

agentmods 80×15 button for eval-compare

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-compare"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01454
Opus 5 $0.00042 $0.00727
Sonnet 5 $0.00017 $0.00291
Haiku 4.5 $0.00008 $0.00145

Measured 9d ago against content hash 913e72d664c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-compare 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/compare.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/eval-compare/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an eval comparison report generator. You take a directory of eval run results and produce a self-contained HTML comparison report with LLM-generated analysis. You do not run evaluations or modify source data.

IMPORTANT: Follow the steps below sequentially. Do not explore the filesystem, run ls, find, or otherwise investigate the input directory. The scripts handle all discovery. Just run the commands as written.

Step 0: Parse Arguments

Argument Required Default Description
<input-dir> yes Directory to scan recursively for eval runs (any subdirectory containing summary.yaml)
--output <path> no <input-dir>/comparison-report Output directory for the HTML report
--title <text> no Model Comparison Report title
--overview <text> no none (section omitted) Context paragraph shown at the top of the report

Step 1: Discover Runs

Run the discovery script to find all valid eval runs:

python3 ${CLAUDE_SKILL_DIR}/scripts/compare.py discover <input-dir>

This recursively scans for directories containing summary.yaml and prints a JSON manifest of discovered runs with model names, costs, and judge scores. Just pass the input directory — do not search for files yourself. If the input dir also contains an anova.json (written by /eval-anova), the manifest reports "has_stats": true and the generated report gains an ANOVA/Pareto Statistical Significance section automatically — no extra step needed. eval-compare works with or without it.

If no valid runs are found, report the error and stop.

Step 2: Generate Report

Run the report generator:

python3 ${CLAUDE_SKILL_DIR}/scripts/compare.py generate <input-dir> --output <output-dir> --title "<title>"

If --overview was provided, also pass --overview "<text>".

This produces:

  • <output-dir>/index.html — the comparison report
  • Copies of any report.html files into per-run subdirectories (named by a unique run slug) for iframe embedding

Read the full file on GitHub · 100 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 100 lines · 84 tokens per session scan A 913e72d664c9

Subscribe to this mod's changes

eval-compare is a skill published in the GitHub repository opendatahub-io/agent-eval-harness (40 stars, last pushed 6d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,454 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens