Token-efficient execution kit for repeated TAO agentic workflows. Compiles a skill into stage cards once (with a strong model), then executes them forever in fresh, small headless sessions coordinated by a bash driver — measured 67-91% token reduction and 3-5x lower peak context vs one long conversation.
Install
npx skills add NVIDIA/skills --skill tao-token-efficient-executionnpx skills add NVIDIA/skills --skill tao-token-efficient-execution -a claude-code -gnpx skills add NVIDIA/skills --skill tao-token-efficient-execution -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-token-efficient-executiongh skill install NVIDIA/skills tao-token-efficient-executiongit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-token-efficient-execution ~/.claude/skills/tao-token-efficient-execution # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-token-efficient-execution ~/.agents/skills/tao-token-efficient-execution # Codex, Cursor, Gemini CLI, Copilot, OpenCode