modelharness — tool profile and history

Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • agent-harness
  • benchmark
  • claude-code
  • claude-code-plugin
  • fable
  • haiku
  • llm-harness
  • opus
  • sonnet

Install /plugin marketplace add vitaliikapliuk/modelharness

Current measurement

38GitHub stars-2 (-5.0 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
38GitHub stars
38GitHub stars
38GitHub stars
38GitHub stars
38GitHub stars
40GitHub stars
40GitHub stars
47GitHub stars
47GitHub stars
47GitHub stars
47GitHub stars
47GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars
48GitHub stars

Classifications

Domains
Type
Agent skills
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.