git404hub

what is caliber fr?

jordangrothentic/caliber — explained in plain English

Analysis updated 2026-05-18

3Audience · developerComplexity · 2/5Setup · easy

tl;dr

An advisory tool that recommends the cheapest AI model and effort level whose risk of a wrong answer is still acceptable for your task.

vibe map

mindmap
  root((Caliber))
    What it does
      Recommends model
      Recommends effort
      Advisory only
    Tech stack
      Claude Code
      Claude Skills
    Use cases
      Pick a model
      Compare cost options
      Team standardization
    Audience
      Developers
      Claude Code users
    Setup
      Copy skill files
      Copy command files
      Restart Claude Code

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Get a recommendation for which Claude model and effort level to use before starting a coding task.

VIBE 2

Compare a cheaper model option against a stronger, more expensive one before committing tokens.

VIBE 3

Decide whether a high-stakes task justifies stepping up to a stronger model.

VIBE 4

Standardize model selection guidance across a team using Claude Code.

what's the stack?

Claude CodeClaude SkillsMarkdown

how it stacks up fr

jordangrothentic/caliber000madz000/payload-test-api-route-handler0marildo/imago
Stars333
LanguageTypeScriptPython
Setup difficultyeasyeasyeasy
Complexity2/52/52/5
Audiencedeveloperdevelopergeneral

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · easy time til it works · 5min

Copy the skill and command files into ~/.claude/skills and ~/.claude/commands, or a repo's .claude/ folder.

in plain english

Caliber is a small set of Claude Code slash commands, plus a skill you can upload to the Claude website, that tells you which AI model and effort level to use for the task you are about to give Claude, instead of always reaching for the biggest and most expensive option. It only gives advice: it prints the exact commands to run, but it never switches your model or effort setting for you. The core idea is that picking a model should not be about finding the single best one. The strongest model at the highest effort will usually produce the best answer, but it costs more, runs slower, and can even overthink simple tasks. The real question Caliber tries to answer is what is the cheapest model and effort level whose chance of getting the task wrong is still acceptable. If a cheap setup produces a subtle bug, you end up paying twice: once for the run, and again to notice and fix the mistake, so that is not actually the cheap option. When you type a command like slash caliber followed by a description of your task, it looks at how complex the task is, how costly a mistake would be, how much value getting it exactly right adds, and whether a cheaper model could realistically handle it. From that it prints three suggestions labeled Budget, Optimal, and Splurge, each naming a specific model and effort level, along with a confidence rating and a note on what to fall back to if that choice struggles. It also compares its recommendation to whatever model your current session is already using, telling you whether it is a step up, a step down, or the same. To use the full set of five commands you need Claude Code installed locally. To use just the main catch-all command on the Claude website, you need a paid or free plan with Skills and code execution turned on. Installing it is a matter of copying files into Claude's skills and commands folders, either for all your projects or for a single repository.

prompts (copy fr)

prompt 1
Run /caliber followed by a description of a coding task to get a model and effort recommendation.
prompt 2
Ask which model and effort level to use for adding rate limiting to a public API.
prompt 3
Use /budget to find the cheapest model setup that still clears a task with high confidence.
prompt 4
Use /splurge to find the strongest model setup worth using for a high-stakes change.
prompt 5
Edit models.md to update the catalog of current model names Caliber recommends from.

Frequently asked questions

what is caliber fr?

An advisory tool that recommends the cheapest AI model and effort level whose risk of a wrong answer is still acceptable for your task.

How hard is caliber to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is caliber for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.