What is tao-run-deft-aoi?

An end-to-end workflow for improving PCB inspection models that detect visual changes or defects on circuit boards. It evaluates a starting model, investigates errors, creates or mines training examples, retrains the model, and checks whether it meets defined deployment criteria.

Use it for baseline evaluation, root-cause analysis, synthetic defect generation, nearest-neighbour example mining, retraining, and metric-based deployment decisions.

It organises the many steps between finding poor inspection results and deciding whether an improved model is ready to use.

tao-run-deft-aoi — 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-run-deft-aoi

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-run-deft-aoi/github.svg)](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-run-deft-aoi)

Your own site

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

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,636 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: 3 findings, up to high

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 →

high Privilege Escalation · line 158
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
medium MCP Rug Pull · line 128
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Fix: Pin the image: image:tag or image@sha256:abc123
medium Excessive Agency · line 174
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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.04636
Opus 5	$0.00077	$0.02318
Sonnet 5	$0.00031	$0.00927
Haiku 4.5	$0.00015	$0.00464

Measured 12d ago against content hash 7ea9fd09db49, 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-aoi 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 12d ago.

The scan reads SKILL.md. This mod also ships 21 executable files (scripts/align_token_usage.py, scripts/analyze_kpi.py, scripts/changenet_data_pair_prepare.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-aoi/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: tao-run-deft-aoi

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Execution Contract

Treat this as a disk-backed state machine, not as a prose recipe.

Preserve every explicit user value. epoch 1 means num_epochs=1 and iteration 1 means max_iterations=1; a heuristic or spec default applies only when the user did not supply that parameter. Show the source of every run parameter (user, spec, or default) in the Pre-Flight Summary. Preserve the customer's metric name, operator, target, unit, evaluator, and constraints. The approved metric_contract is the source of truth for evaluation, checkpoint selection, completion, and reporting.
After the user approves the Summary, set PYTHON=$(bash scripts/deft_python.sh), then initialize deft_state.json once with "$PYTHON" scripts/init_deft_state.py, passing Preflight's exact GPU model/memory, resolved --network-mode, activation source, and selected absolute Python. The resulting execution_policy is immutable run state. Never hand-author or reinitialize it on resume.
On startup, after context compaction, before every stage, and before any completion claim, run "$PYTHON" scripts/deft_context.py --state ... --stage .... Use its durable next_stage plus the state file's status, current_iteration, iterations.*.status, stage_completed, and latest events entry to resume. Do not infer progress from assistant prose or from an artifact that is not recorded in state.
Invoke the mapped underlying skill after reading the DEFT overlay. Do not replace a missing/unread stage reference or a failed skill call with guessed shell commands, inline Python, a different output tree, or data fabricated from the KPI set.
After initialization, run install/fetch/login/container commands through "$PYTHON" scripts/deft_exec.py --state ... -- <command>. Air-gap mode rejects egress and installs, injects offline flags, and enforces no-pull. Selected platforms must enforce the equivalent policy.
Commit every stage with "$PYTHON" scripts/commit_stage.py; it verifies the stage's required inputs and atomically updates both the resume snapshot and ordered events array inside deft_state.json. Never edit the state file with inline Python, jq, heredocs, or an editor. Fix rejected evidence; never fabricate state. For evaluate, pass the metric result, checkpoint, inference CSV, and threshold directly to commit_stage.py. Pass positive measured --duration-sec from backend elapsed time or a host timer for executed stages. A documented --skip may record 0; negative durations are always rejected.
Claim the loop complete only after "$PYTHON" scripts/finalize_run.py creates the handoff artifacts, successfully commits loop_stop, and a fresh read of deft_state.json shows status == "complete", iterations.baseline.status == "complete", and the final iteration's status == "complete". A checkpoint, inference CSV, report, or assistant message is not completion evidence by itself.

Read the full file on GitHub · 267 lines

Files

What ships with it

47 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.

12d ago First seen · 267 lines · 155 tokens per session scan A 7ea9fd09db49

Subscribe to this mod's changes

tao-run-deft-aoi is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 155 tokens to every session and 4,636 once invoked, about $0.0008 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.

Data and AI Hardware and IoT aoi application deft loop workflow

memory-merger

Merges mature lessons from a domain memory file into its instruction file. Syntax: /memory-merger >domain [scope] where scope is global (default), user, workspace, or ws.

boshi-xixixi/TraeSkill · 49 tokens

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

minicpm5-deploy-litert

Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says "LiteRT", "LiteRT-LM", "litertlm", ".litertlm", "Android"…

OpenBMB/MiniCPM · 121 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens