model-bakeoff SKILL.md skillA

model-bakeoff from narendawar/narens-claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add narendawar/narens-claude-skills/model-bakeoff@git:20261010.895cd4c

Pins git:20261010.895cd4c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
narendawar/narens-claude-skills
Path
plugins/model-bakeoff/skills/model-bakeoff/SKILL.md
Versions recorded
3
Latest version
git:20261010.895cd4c, committed Oct 10, 2026
First version recorded
Oct 10, 2026
Size
6,272 bytes
Repository stars
4
License
MIT

Use when the user wants to pick the cheapest model that still works for a custom subagent, asks whether Haiku or Sonnet would do, or wants to re-check an agent's model after new models ship (for example 'which model should this agent use?', 'could this run on Haiku?', 'bake-off my reviewer agent').

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Model Bake-off

## Overview

A custom subagent runs on whatever its `model` field says, usually chosen by feel. This skill measures instead: it runs the agent's test cases on Haiku, Sonnet and Opus through `claude -p`, applies a stated pass rule, recommends the cheapest model that passes, and only after the user says yes writes it into the agent's `model` field. It runs only when the user asks. It never invents a number: the script does all the arithmetic, and it states what the runs do and do not show.

## The script

`scripts/bakeoff.py` in this skill's directory (use the base directory shown when the skill loads). Python 3 and the standard library only; use `python3`, or `python` / `py -3` if that is what works.

- `agents [--json]` lists custom agents with their model, tools and whether they are read-only.
- `check-cases --cases FILE` validates a cases file.
- `estimate --agent NAME --cases FILE [--models LIST] [--runs N]` shows the number of runs, the ceiling cost, and whether an opt-in is needed. It calls nothing.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add narendawar/narens-claude-skills/model-bakeoff@sha256:12d5bb10e6506c3e

The line at the top of this page pins the label git:20261010.895cd4c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wro4qwsn4r6k3kfp.svg)](https://markdownregistry.com/a/art_wro4qwsn4r6k3kfp)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, all committed on Oct 10, 2026.

versioncommittedcommitsizeaudit
git:20261010.895cd4c latest2026-10-10 895cd4c 6,272 BA view · diff
git:20261010.2ae1ce62026-10-10 2ae1ce6 5,772 BA view · diff
git:20261010.e9f43602026-10-10 e9f4360 5,407 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6272 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

narendawar/narens-claude-skills · 4 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wro4qwsn4r6k3kfp
GET https://markdownregistry.com/api/v1/resolve?ref=narendawar/narens-claude-skills/model-bakeoff
GET https://markdownregistry.com/api/v1/blob/12d5bb10e6506c3e3d49400b82d345647f83d167024806d265b5184ac44c54d6

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from narendawar/narens-claude-skills

llms.txt llms.txt file
narendawar/narens-claude-skills · llms.txt
git:20261020.8585eaa · audit A · 4 stars
comprehension-check SKILL.md skill
narendawar/narens-claude-skills · plugins/comprehension-check/skills/comprehension-check/SKILL.md · Use when the user asks to be quizzed on, or to check their understanding of, code Claude wrote this session (for…
git:20261001.15ebe60 · audit A · 4 stars
decision-journal SKILL.md skill
narendawar/narens-claude-skills · plugins/decision-journal/skills/decision-journal/SKILL.md · Use when the user wants to log a prediction or estimate about a dev or project decision, grade past predictions, or see…
git:20261001.6851e1f · audit A · 4 stars
human-writing SKILL.md skill
narendawar/narens-claude-skills · plugins/human-writing/skills/human-writing/SKILL.md · Use when the user wants words written or rewritten in a human, personal voice, including short casual messages: a Slack…
git:20261020.8585eaa · audit A · 4 stars
pdf-table-fixer SKILL.md skill
narendawar/narens-claude-skills · plugins/pdf-table-fixer/skills/pdf-table-fixer/SKILL.md · Use when the user has a tagged PDF whose tables fail accessibility checks or read badly in a screen reader (for example…
git:20261011.7b2ffe1 · audit A · 4 stars
podcast-clip-scout SKILL.md skill
narendawar/narens-claude-skills · plugins/podcast-clip-scout/skills/podcast-clip-scout/SKILL.md · Use when the user has a timestamped podcast or video transcript and wants the best short clips picked from it (for…
git:20261014.0506b44 · audit A · 4 stars
rule-promoter SKILL.md skill
narendawar/narens-claude-skills · plugins/rule-promoter/skills/rule-promoter/SKILL.md · Use when the user wants rules in CLAUDE.md enforced with hooks, says Claude keeps ignoring a CLAUDE.md rule, or asks to…
git:20261002.1c575d2 · audit A · 4 stars
schedule-doctor SKILL.md skill
narendawar/narens-claude-skills · plugins/schedule-doctor/skills/schedule-doctor/SKILL.md · Use when the user is about to schedule a Claude task, or asks why a scheduled task, /loop, cron job or routine did not…
git:20261004.a246b3f · audit A · 4 stars
subagent-tax-auditor SKILL.md skill
narendawar/narens-claude-skills · plugins/subagent-tax-auditor/skills/subagent-tax-auditor/SKILL.md · Use when the user asks why their Claude Code quota or usage limit runs out so fast, which subagents cost the most, or…
git:20261003.e9d6b70 · audit A · 4 stars
__SKILL_NAME__ SKILL.md skill
narendawar/narens-claude-skills · template/skills/__SKILL_NAME__/SKILL.md · __DESCRIPTION__
git:20261001.206faba · audit A · 4 stars

Every file in narendawar/narens-claude-skills

Other files named model-bakeoff

model-bakeoff SKILL.md skill
narendawar/narens-claude-toolkit · plugins/model-bakeoff/skills/model-bakeoff/SKILL.md · Use when the user wants to pick the cheapest model that still works for a custom subagent, asks whether Haiku or Sonnet…
git:20261010.895cd4c · audit A · 4 stars

Browse by kind, by grade A, or by owner.