# Tao token efficient execution

> Tao token efficient execution is an open-source agent skill. Token-efficient execution kit for repeated TAO agentic workflows. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/tao-token-efficient-execution
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** tao-token-efficient-execution
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

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. Use when a TAO workflow will be run repeatedly, when token cost matters, when the target model has a small context window, or on trigger phrases like "token efficient", "reduce token cost", "card pack", "stage cards", "run this workflow on a small model", "compile this skill into cards".

## When your agent uses it

> 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. Use when a TAO workflow will be run repeatedly, when token cost matters, when the target model has a small context window, or on trigger phrases like "token efficient", "reduce token cost", "card pack", "stage cards", "run this workflow on a small model", "compile this skill into cards".

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs shell, Python and TypeScript scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-token-efficient-execution)
- [Asks for: Read, Bash](https://github.com/NVIDIA/skills/blob/HEAD/skills/tao-token-efficient-execution/SKILL.md)
- [No network calls found in its scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-token-efficient-execution)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/tao-token-efficient-execution)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/tao-token-efficient-execution` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/tao-token-efficient-execution &&
cp -R "$tmp/skills/tao-token-efficient-execution" ~/.claude/skills/tao-token-efficient-execution &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/tao-token-efficient-execution` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/tao-token-efficient-execution` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/tao-token-efficient-execution &&
cp -R "$tmp/skills/tao-token-efficient-execution" ~/.agents/skills/tao-token-efficient-execution &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/tao-token-efficient-execution` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/tao-token-efficient-execution` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/tao-token-efficient-execution &&
cp -R "$tmp/skills/tao-token-efficient-execution" ~/.cursor/skills/tao-token-efficient-execution &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/tao-token-efficient-execution` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-token-efficient-execution
```

Or copy the folder to `~/.gemini/skills/tao-token-efficient-execution` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/tao-token-efficient-execution`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/tao-token-efficient-execution &&
cp -R "$tmp/skills/tao-token-efficient-execution" ~/.copilot/skills/tao-token-efficient-execution &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/tao-token-efficient-execution` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/tao-token-efficient-execution` into your agent's skills folder as `tao-token-efficient-execution`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Tao token efficient execution in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/tao-token-efficient-execution to use it in all your projects, or to .claude/skills/tao-token-efficient-execution in one project.

### Does Tao token efficient execution run scripts?

Yes. It runs shell, Python and TypeScript scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Tao token efficient execution?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/tao-token-efficient-execution
