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.

Claude Code hooks that auto-switch model tier based on task complexity

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

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

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.

Compound V is a multi-model orchestrator for Claude Code, layered on Superpowers: a deterministic router (Opus for risky work, Sonnet for the mechanical), cross-model review (Claude + Codex), 3 scouts (code · docs · domain). The pill that turns one freelancer into a squad.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

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

Claude 3.5 Sonnet Desktop Client for Windows Mac Linux 2026