Token-saving proxy for Claude Code: renders bulky context (system prompt, tool docs, old history) as dense PNGs to cut input tokens. Runs on Node and Cloudflare Workers.

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: tier routing (Sonnet 5 does the work), Requirements Ledger, enforced guard hooks, automatic teammate reaping

Claude Fable 5.1 prompting guide as Claude Code skills (KO/EN/ZH). Output quality goes up on Opus 5 and Sonnet 5 too.

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.

Frontier model solution tracing, then made the prompting skills so Sonnet, GPT, DeepSeek, GLM, Kimi, ETC models work like that