Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max with more tests passed. 8.3% fewer tokens in a Sol 6.1 max pilot. Raw data, Docker setup and comparison video included.
Fonte
GitHub
Linguaggio
Python
Ultima attività
29 set 2026
Stelle17Misurato · 22 ott 2026
Momentum07 giorni · Misurato · 0% variazione relativa
DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.
Fonte
GitHub
Linguaggio
Python
Ultima attività
16 mag 2026
Stelle15Misurato · 22 ott 2026
Momentum07 giorni · Misurato · 0% variazione relativa
Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured on Sonnet and Opus, every run published — including the ones that failed. Demote, don't delete.
Fonte
GitHub
Linguaggio
Python
Ultima attività
16 set 2026
Stelle11Misurato · 19 ott 2026
Momentum07 giorni · Misurato · 0% variazione relativa