compare-model-sweep

compare-model-sweep is a skill for Claude Code, Codex from understudylabs/understudy-agent-tools. It costs 87 tokens per session (2,865 once invoked), scanned A, original, MIT.

A skill for testing several AI models on the same evaluation, or eval, which is a repeatable set of tasks and scoring rules. It reports quality, response time, cost, and reliability side by side to help choose a model.

In plain words
What is it for?
Use it to run a bounded sweep across local, gateway, or frontier models and produce a report for model or routing decisions.
Why use it?
It replaces scattered model trials with one consistent comparison for a specific workload.

Skill for Claude CodeCodex

Part of the understudy plugin — 43 skills, 1 command shipped together

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.

agentmods
npx agentmods add skills/understudylabs/understudy-agent-tools/compare-model-sweep
Any agent
npx skills add understudylabs/understudy-agent-tools --skill compare-model-sweep
Clone the repo
git clone --depth 1 https://github.com/understudylabs/understudy-agent-tools

Made for: Claude Code, Codex.

Or install understudy, the plugin that ships this one along with the rest of its 43 skills, 1 command.

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 compare-model-sweep

README.md
[![agentmods](https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/compare-model-sweep.svg)](https://agentmods.dev/skills/understudylabs/understudy-agent-tools/compare-model-sweep)
Your own site
<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/compare-model-sweep"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/compare-model-sweep.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00087 $0.02865
Opus 5 $0.00044 $0.01432
Sonnet 5 $0.00017 $0.00573
Haiku 4.5 $0.00009 $0.00286

Measured 3d ago against content hash cf3ba05b25f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compare-model-sweep 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 3d 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.

skills/compare-model-sweep/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compare Model Sweep

Use this worker when the question is not "can one model pass this eval?" but "which candidate sits on the useful frontier for this workload?" The skill runs one frozen harness across a candidate matrix, records each run, and emits a decision-ready Pareto report an agent can use for route decisions.

Prefer this after ../understand-workload/SKILL.md, ../optimize-agentic-workload/SKILL.md, or ../run-local-model-lab/SKILL.md has already identified a resettable eval and a first local candidate.

Safety Gates

Launching a named bounded sweep authorizes its declared provider calls, uploads, benchmark rows, evaluation, receipts, and cleanup. Ask again only if the sweep expands its displayed data, destination, spend, retention, download, or production-impact envelope. Never place private traces or customer data in a public sweep report.

Recommend a candidate matrix sized to resolve the objective, including a strong anchor when it could change the decision. Present expected spend and wall-clock before the run and follow ../understudy/reference.md → Outcome-first spend posture. Do not omit the informative candidate merely to keep the first sweep cheap; one activated plan covers the whole named matrix.

Do not claim a model is cheaper, faster, or better unless the sweep used the same rows, harness, metric, tool-access mode, prompt, seed, and state reset for every candidate. If those differ, label the result as an ablation or diagnostic, not a Pareto comparison.

Flow

  1. Freeze the comparison contract. Record workload id, harness command, split/row ids, metric, prompt, tool-access mode, seed, timeout, concurrency, and budget. Write it to .understudy/model-sweeps/<timestamp>/sweep-plan.json.

  2. Normalize candidate routes. Include each model id, route type (local, understudy-managed-catalog, understudy-routed, byo-provider, or hosted-other), endpoint/base URL, loader/runtime, local-vs-remote boundary, max tokens, reasoning effort, pricing basis, and whether the model is cached or requires download.

Read the full file on GitHub · 230 lines

Files

What ships with it

1 file 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. 3d ago First seen · 230 lines · 87 tokens per session scan A cf3ba05b25f6

Subscribe to this mod's changes

compare-model-sweep is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 87 tokens to every session and 2,865 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

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

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

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 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

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

aatmf-t10-confidentiality-breach

AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.

PurpleAILAB/Decepticon · 39 tokens