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.
npx skills add NVIDIA-TAO/tao-skill-bank --skill tao-mine-od-imagesgit clone --depth 1 https://github.com/NVIDIA-TAO/tao-skill-bankWrote 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.
[](https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-mine-od-images)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-mine-od-images"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-mine-od-images/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.
<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-mine-od-images"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-mine-od-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 88 Potential security issue detected. Manual review is recommended.Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- high Privilege Escalation · line 95 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 88 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 MCP Rug Pull · line 151 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
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 | $0.00074 | $0.02118 |
| Opus 5 | $0.00037 | $0.01059 |
| Sonnet 5 | $0.00015 | $0.00424 |
| Haiku 4.5 | $0.00007 | $0.00212 |
Grade A, and why
tao-mine-od-images 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.
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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAO Mine OD Images (Unique Neighbor Matching)
Use this skill to run TAO Data Services TMM unique-neighbor matching mining for object detection. The skill consumes pre-embedded source and target parquets and writes a directory of outputs including final_unique_files.parquet and summary.json. It does not compute embeddings; upstream steps must produce the source and target embedding parquets first.
The container entrypoint is:
tmm unique_neighbor_matching -e /absolute/path/to/unique_neighbor_matching.yaml
Inputs
The user can provide either an existing spec or the fields needed to generate one.
Required spec fields:
| Field | Meaning |
|---|---|
source_path |
Absolute path to the source embeddings parquet or directory of parquets. |
target_path |
Absolute path to the target embeddings parquet or directory of parquets. |
output_dir |
Absolute path to the output directory. Writes final_unique_files.parquet, summary.json, and per-iteration parquets. |
desired_unique_count |
Total number of unique source files to retrieve. |
Common optional fields:
| Field | Default | Meaning |
|---|---|---|
allocation_policy |
global |
global or class_stratified. |
distance_metric |
euclidean |
One of euclidean, cosine, or manhattan. Embeddings are L2-normalized before search. |
candidate_expansion_factor |
5 |
Candidate-pool multiplier per iteration. Increase if desired count is not reached. |
source_embedding_column |
embedding |
Embedding column in source_path. |
target_embedding_column |
embedding |
Embedding column in target_path. |
source_filepath_column |
filepath |
Filepath column in source_path; also the column of final_unique_files.parquet. |
target_filepath_column |
filepath |
Filepath column in target_path. |
exclude_path |
null |
Parquet with a filepath column; those images are removed from the source pool. |
source_detection_file |
null |
COCO .json or KITTI label directory for the source. Required for class_stratified. |
target_detection_file |
null |
COCO .json or KITTI label directory for the target. Required for class_stratified. |
detection_format |
null |
coco or kitti. Required whenever a detection file is set; never inferred from the path. |
rare_class_list |
"" |
Comma-separated rare class names, e.g. "person,bicycle". Required for class_stratified. |
save_embeddings |
false |
Include embeddings in per-iteration parquet outputs. |
visualize |
false |
Save per-class visualization grids (requires Pillow and matplotlib). |
What ships with it
5 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.
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 · 187 lines · 74 tokens per session scan A 776b3d5a6dcd
tao-mine-od-images is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 2,118 once invoked, about $0.0004 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.
Other skills, from other repositories
Data Validation
Data quality checks to run before modeling — distribution summaries, leakage detection, class balance.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.