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.
Skill Claude CodeCodex
Audit this machine's Claude Code configuration for token waste - effort level, oversized CLAUDE.md files, MCP servers, tool-output caps, env keys that do nothing, startup skill load - and print the exact settings.json edit that fixes each finding. Read-only; it never writes settings. Use when the user asks why their…
Skill Claude CodeCodex
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.
Skill Claude CodeCodex
Show where the tokens actually went - per-session output, thinking, input and cache accounting read from this machine's Claude Code transcripts. Use when the user asks what they spent, which sessions were expensive, how their prompt cache is doing, or whether /eco is helping. Works in any language.
Skill Claude CodeCodex
Token-frugal mode - minimize token consumption (concise replies, lean tool use, cheap delegation) at full task quality. Use when the user mentions tokens, cost, budget, quota, or economical operation, in any language. Invoke once; applies for the rest of the session. "/eco setup" configures permanent savings.