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.
Source
GitHub
Language
JavaScript
Last activity
Aug 16, 2026
Stars40Measured · Oct 25, 2026
Momentum17.77 days · Measured · +2.56% relative change
Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.
Source
GitHub
Language
Python
Last activity
Oct 24, 2026
Stars165Measured · Oct 25, 2026
Momentum17.57 days · Measured · +1.23% relative change
🎨 World-class AI presentation generator · 26 styles · 18 charts · benchmarked against Linear/Anthropic/Stripe/Apple/NYT — a Claude Code Skill that turns one sentence into design-agency-quality decks (HTML + editable PPTX)
Source
GitHub
Language
Python
Last activity
May 11, 2026
Stars165Measured · Oct 25, 2026
Momentum17.57 days · Measured · +1.23% relative change