claude-code-eco — tool profile and history

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Active

Canonical source ↗

Language
JavaScript
License
MIT
Created
Last activity
Topics
  • ai-agents
  • anthropic
  • claude
  • claude-ai
  • claude-code
  • claude-code-plugin
  • claude-fable-5
  • claude-opus
  • claude-skills
  • claude-sonnet
  • cost-optimization
  • cost-reduction
  • developer-tools
  • fable-5
  • fable5
  • llm
  • token-optimization
  • tokens

Install /plugin marketplace add sup3x/claude-code-eco

Current measurement

33GitHub starsstable
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
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
33GitHub stars
32GitHub stars
32GitHub stars
32GitHub stars
32GitHub stars
32GitHub stars
31GitHub stars
30GitHub stars
29GitHub stars
29GitHub stars
27GitHub stars
27GitHub stars
27GitHub stars
27GitHub stars

Classifications

Domains
Type
Agent skills
Use cases

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