tao-run-deft-pas

tao-run-deft-pas is a skill for Claude Code from NVIDIA-TAO/tao-skill-bank. It costs 175 tokens per session (3,713 once invoked), scanned A, original, Apache-2.0.

An iterative workflow for improving NVIDIA TAO CLIP or SigLIP image-search models using data labelled with attributes. It evaluates retrieval, finds useful image-text pairs, retrains the model, and stops when a chosen condition is met.

In plain words
What is it for?
Use it to improve image-text retrieval on attribute-labelled data, mine weak examples or caption pairs, and repeat training until a retrieval score, validation trend, or iteration limit says to stop.
Why use it?
It removes the need to manually coordinate repeated evaluation, data mining, retraining, and stopping checks. It also keeps the workflow resumable across supported computing environments.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the tao-skills plugin — 76 skills shipped together , and of tao-skill-bank

Good fit Use it to improve image-text retrieval on attribute-labelled data, mine weak examples or caption pairs, and repeat training until a retrieval score, validation trend, or iteration limit says to stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas
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-run-deft-pas
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 76 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.

agentmods badge for tao-run-deft-pas

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas)
Your own site
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas/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.

agentmods 80×15 button for tao-run-deft-pas

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-pas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,713 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 146
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00175 $0.03713
Opus 5 $0.00088 $0.01857
Sonnet 5 $0.00035 $0.00743
Haiku 4.5 $0.00017 $0.00371

Measured 13d ago against content hash 8b00d15c8c09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tao-run-deft-pas 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 13d ago.

The scan reads SKILL.md. This mod also ships 33 executable files (patches/sitecustomize.py, scripts/audit_deft_run.py, scripts/check_pas_cuda_runtime.py, …), 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/applications/tao-run-deft-pas/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PAS DEFT Workflow

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first for host preflight, credential checks, and cross-skill discovery.

Run the canonical PAS flow as one resumable, disk-backed workflow. All PAS workflow logic, templates, and host adapters ship with this skill; customers do not need a separate source checkout. The bundled scripts make stage calls deterministic without adding another orchestration layer.

This skill supports every packaged TAO execution platform: Docker, SLURM, Kubernetes, Brev, and virtualenv. The workflow produces a platform-neutral, schema-validated action bundle; the selected platform skill owns native submit/status/logs/cancel and the job-record. Virtualenv execution uses separate immutable pyt and ds runtime profiles; the workspace control .venv is not an execution runtime.

Entry Contract

tao-deft-pas and tao-run-deft-pas select this same workflow. If the user did not choose a platform, ask once among Docker, SLURM, Kubernetes, Brev, and virtualenv; never default to Docker. On resume, the immutable platform in deft_state.json is already the selection and must not be changed.

Use two intake phases:

  1. Perform only bounded, lightweight path discovery. Two explicit archive file paths win and suppress all archive searching. An explicit archive directory is treated as one approved search root. Otherwise, resolve the conventional ~/workspace and use only these deduplicated search roots: ~/pas, the workspace root, and its pas/, input/, and inputs/ children. Check the workspace root itself only; beneath each other search root, inspect the root and directories at most two levels below it. This AOI-style bounded-subtree lookup supports nested export/drop directories without turning into a home or repository scan. Never follow symlinks or add the current checkout, source repositories, tutorial/notebook trees, or workspace dataset-output trees as implicit search roots.

Read the full file on GitHub · 317 lines

Files

What ships with it

58 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.

  1. 13d ago First seen · 317 lines · 175 tokens per session scan A 8b00d15c8c09

Subscribe to this mod's changes

tao-run-deft-pas is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 175 tokens to every session and 3,713 once invoked, about $0.0009 per session on Opus 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 2026-08-30.