tao-token-efficient-execution SKILL.md skillA
tao-token-efficient-execution from nvidia-tao/tao-skill-bank is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nvidia-tao/tao-skill-bank/tao-token-efficient-execution@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nvidia-tao/tao-skill-bank
- Path
skills/core/tao-token-efficient-execution/SKILL.md- Versions recorded
- 2
- Latest version
- v0.1.0, committed Oct 6, 2026
- First version recorded
- Sep 20, 2026
- Size
- 8,281 bytes
- Repository stars
- 95
- License
- Apache-2.0
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 74-91% token reduction and 4-5x 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…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 1. **Core (harness-agnostic)** — stage cards (markdown, env-var contract), a bash driver (stage routing + job waiting), and on-disk state contracts (`references/CONTRACTS.md`). 2. **Harness adapters** (`adapters/`) — guard + recorder implemented per …
Read the whole file at its exact version.
How to install
mdr add nvidia-tao/tao-skill-bank/tao-token-efficient-execution@sha256:c9fa2e81d30148bcThe line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_f27bxc6gvbfmykvs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 20, 2026 and Oct 6, 2026, about one every 16 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.0 latest | 2026-10-06 | 87ac6f4 | 8,281 B | A | view · diff |
| v0.1.0 | 2026-09-20 | 7e8c293 | 7,557 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8281 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nvidia-tao/tao-skill-bank · 95 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_f27bxc6gvbfmykvs GET https://markdownregistry.com/api/v1/resolve?ref=nvidia-tao/tao-skill-bank/tao-token-efficient-execution GET https://markdownregistry.com/api/v1/blob/c9fa2e81d30148bc7be3c06baf243f792d74dbba8a84b7464ce63fe62986762c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.