What is tao-token-efficient-execution?

A workflow kit that splits a long agent task into small, independent sessions using written stage cards and files for shared state.

Use it to run repeated, multi-stage agent workflows through a shell driver, with each stage handling one defined part of the job.

Long agent conversations repeatedly resend old instructions and logs, which uses more context. Separate sessions let each stage read only the information it needs.

tao-token-efficient-execution — Skill for Claude Code by NVIDIA-TAO

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add NVIDIA-TAO/tao-skill-bank --skill tao-token-efficient-execution

Clone the repo

git clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bank

Made for: Claude Code.

Or install tao-skills, the plugin that ships this one along with the rest of its 82 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution)

Your own site

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-token-efficient-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,011 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00136	$0.02011
Opus 5.5	$0.00054	$0.00804
Sonnet 5.5	$0.00027	$0.00402
Haiku 4.5	$0.00014	$0.00201

Measured 21d ago against content hash c9fa2e81d301, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tao-token-efficient-execution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (adapters/claude-code/hooks/guard.template.sh, adapters/claude-code/hooks/record.template.sh, adapters/pi/guard.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/core/tao-token-efficient-execution/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TAO Token-Efficient Execution

Run a staged TAO workflow as a series of fresh headless agent sessions — one stage card per session — instead of one long conversation. State lives on disk, never in chat history, so no session ever rereads the run's past.

Historical measurements of the shipped packs (billed tokens; provenance, reproduction protocol, and pass thresholds in references/MEASUREMENT.md):

Workflow	One long conversation	Card execution	Peak context
DEFT AOI loop	9.6M	2.5M (-74%)	242k → 59k
AutoML (VCN classify)	5.8M	0.5M (-91%)	198k → 42k

The mechanism: an agent API is stateless, so a long conversation resends its entire history with every message — by mid-run that is ~100k+ tokens of skill text, spec edits, and training logs reread on every tool call, of which the current step needs ~3k. Cards make each step's 3k explicit and drop the rest.

The three layers

Core (harness-agnostic) — stage cards (markdown, env-var contract), a bash driver (stage routing + job waiting), and on-disk state contracts (references/CONTRACTS.md).
Harness adapters (adapters/) — guard + recorder implemented per harness: hooks for Claude Code, extensions for Pi. Same logic, ~150 lines each. Guards block known dead ends before tokens are burned; the recorder appends executed commands to commands.log so later sessions reuse instead of re-derive.
Card packs (per application skill) — compiled cards living next to the skill they were authored from, e.g. skills/applications/tao-run-deft-aoi/cards/ and skills/applications/tao-run-automl/cards/. Each pack ships its own driver.sh and README.md (version pin, required env, how to run).

Cards shrink the model's job; they don't remove it. The driver owns routing and waiting (deterministic), helper scripts own state commits (deterministic), and the model executes one pre-planned stage: run verbatim commands, read a gate table, decide pass/fail from real output, fill in the one dynamic value. If a stage ever becomes 100% deterministic, graduate it out of the card into the driver or a helper script.

Read the full file on GitHub · 150 lines

Files

What ships with it

20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

21d ago Changed · +7 lines c9fa2e81d301
1mo ago First seen · 143 lines · 136 tokens per session scan A 7f586e3ef38a

Subscribe to this mod's changes

tao-token-efficient-execution is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (97 stars, last pushed 5d ago), licensed Apache-2.0. It adds 136 tokens to every session and 2,011 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.

Building agents Orchestration cards efficiency tokenomics

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

python-development

Workflow guidance for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files under python/.

microsoft/agent-framework · 27 tokens

trigger-authoring-tasks

Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…

triggerdotdev/trigger.dev · 115 tokens