Individual skill
tao-token-efficient-execution
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".
skills/tao-token-efficient-execution/SKILL.md
Source commit 25340619336e89bcc40365c28bfe9e790430468e
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3,888
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- cuda Repository topic
- developer-tools Repository topic
- llm Repository topic
- omniverse Repository topic
- tokenomics Declared skill tag
- orchestration Declared skill tag
- efficiency Declared skill tag
- cards Declared skill tag
- operations Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
BENCHMARK.mddoc · 7,425 bytesSKILL.mdcore · 7,557 bytesSKILL.mdcore · 7,557 bytesSKILL.mdcore · 7,557 bytesSKILL.mdcore · 7,557 bytesSKILL.mdcore · 7,557 bytesSKILL.mdcore · 7,557 bytesadapters/claude-code/README.mddoc · 1,313 bytesadapters/claude-code/hooks/guard.template.shruns · 1,147 bytesadapters/claude-code/hooks/record.template.shruns · 860 bytesadapters/claude-code/settings.template.jsonasset · 905 bytesadapters/pi/README.mddoc · 3,779 bytesadapters/pi/guard.tsruns · 10,764 bytesadapters/pi/nvidia-provider.tsruns · 5,052 bytesadapters/pi/recorder.tsruns · 3,858 bytesconfig/skillspector-baseline.yamlasset · 2,023 bytesevals/evals.jsonasset · 2,852 bytesreferences/CARD_AUTHORING.mddoc · 4,471 bytesreferences/CONTRACTS.mddoc · 4,476 bytesreferences/authoring_prompt.mddoc · 2,260 bytesreferences/authoring_prompt_v2.mddoc · 3,033 bytesscripts/analyze_usage.pyruns · 6,167 bytesscripts/install.shruns · 2,893 bytesscripts/smoke_test.shruns · 4,732 bytesskill-card.mddoc · 5,669 bytesskill.oms.sigasset · 8,969 bytestemplates/driver.template.shruns · 5,352 bytestemplates/kit.env.templateasset · 1,881 bytes
Read excerpt
# 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.
Measured on real workflows (same tasks, same outcomes, billed tokens):
| 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 |
| HuggingFace finetune | 1.7M | 0.5M (-67%) | 119k → 42k |
