Drop-in instructions, prompts, and workflows to reduce token usage across Codex, Claude Code, GitHub Copilot, Cursor, and other AI coding agents
Latest release v0.1.0 — AI Token Efficiency Playbook v0.1.0 · 1 Oct 2026
4 files for GitHub Copilot, Codex, OpenCode, Claude Code and Gemini CLI: ai-token-efficiency-playbook copilot-instructions.md, ai-token-efficiency-playbook AGENTS.md, ai-token-efficiency-playbook CLAUDE.md, ai-token-efficiency-playbook GEMINI.md — 1,452 tokens loaded in every session.
.github/copilot-instructions.md A 322 tok AGENTS.md A 445 tok CLAUDE.md A 360 tok GEMINI.md A 325 tok These files are ravinperera/ai-token-efficiency-playbook's own configuration — they tell GitHub Copilot, Codex, OpenCode, Claude Code and Gemini CLI how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.