agentmods.dev

eval-anova

eval-anova is a skill for Claude Code from opendatahub-io/agent-eval-harness. It costs 152 tokens per session (1,200 once invoked), scanned A, original, Apache-2.0.

An experiment runner and statistics workflow for comparing different agent setups across the same test cases. ANOVA is a statistical method for checking whether differences between groups are likely meaningful rather than caused by random variation.

In plain words
What is it for?
Use it to compare models, reasoning-effort settings, prompts, or other agent factors, with repeated runs and a report showing statistical results and cost-quality trade-offs.
Why use it?
It makes comparisons fair by testing configurations on shared cases and accounting for differences in case difficulty. It also helps compare quality against cost.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 40repo 6d ago A scan 152 tokens original Apache-2.0

Good fit Use it to compare models, reasoning-effort settings, prompts, or other agent factors, with repeated runs and a report showing statistical results and cost-quality trade-offs.

Compare 6 skills from other repositories ↓
View source ↗ opendatahub-io/agent-eval-harness opendatahub-io.github.io
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add opendatahub-io/agent-eval-harness
Claude Code
/plugin install 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-anova

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/opendatahub-io/agent-eval-harness/eval-anova"><img src="https://agentmods.dev/badge/skills/opendatahub-io/agent-eval-harness/eval-anova.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 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.
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 $0.00152 $0.01200
Opus 5 $0.00076 $0.00600
Sonnet 5 $0.00030 $0.00240
Haiku 4.5 $0.00015 $0.00120

Measured 9d ago against content hash cb53ec1c4309, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-anova 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 4 executable files (scripts/analyze.py, scripts/design.py, scripts/orchestrate.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-anova/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

eval-anova

Run a full-factorial experiment comparing agent configurations (models, effort levels, prompts) across shared test cases, then analyze results with repeated-measures ANOVA.

Usage

python3 ${CLAUDE_SKILL_DIR}/scripts/orchestrate.py --config eval.yaml               # run → analyze → report
python3 ${CLAUDE_SKILL_DIR}/scripts/orchestrate.py --config eval.yaml --dry-run     # design + cost estimate, no execution
python3 ${CLAUDE_SKILL_DIR}/scripts/orchestrate.py --config eval.yaml --analyze-only  # re-analyze existing runs + re-render

New to this skill? See QUICKSTART.md for from-scratch setup and run steps, and eval/anova-example/ for a self-contained worked example (with committed sample runs you can analyze offline).

How it works

eval-anova is not its own executor — it wraps /eval-run in a matrix loop:

  • eval-run stays the single-condition primitive (one model/config → one run with a summary.yaml). eval-anova runs it once per matrix cell (condition × replication), so every cell is a standard run under $AGENT_EVAL_RUNS_DIR/<eval-name>/, tagged with a condition.json recording its factor levels.
  • Statistics are computed over those runs' summary.yaml files (analyze.py → anova.json): each case's composite uses the harness's canonical reward composition (the eval.yaml reward: section, else boolean-gate + normalised-numeric average), then repeated-measures / mixed-effects ANOVA + a cost/quality Pareto frontier.
  • The report is /eval-compare, which eval-anova invokes over the runs. eval-compare surfaces the ANOVA/Pareto stats automatically when it finds anova.json, and stays a standalone descriptive comparison when it does not.

Because the stats read standard summary.yaml runs, you can also analyze runs produced elsewhere (e.g. a CI fan-out that runs /eval-run per model) — just point --analyze-only at their directory.

Prerequisites

Read the full file on GitHub · 101 lines

Files

What ships with it

8 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 · 101 lines · 152 tokens per session scan A cb53ec1c4309

Subscribe to this mod's changes

eval-anova 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 152 tokens to every session and 1,200 once invoked, about $0.0008 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.

Analytics and metricsScientific
Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

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.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens