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-generate-anomaliesgit 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-generate-anomalies)<a href="https://agentmods.dev/skills/nvidia-tao/tao-skill-bank/tao-generate-anomalies"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-generate-anomalies/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-generate-anomalies"><img src="https://agentmods.dev/badge/skills/nvidia-tao/tao-skill-bank/tao-generate-anomalies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 94 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.
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 | $0.00163 | $0.05413 |
| Opus 5 | $0.00081 | $0.02707 |
| Sonnet 5 | $0.00033 | $0.01083 |
| Haiku 4.5 | $0.00016 | $0.00541 |
Grade A, and why
tao-generate-anomalies 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 — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TAO Generate Anomalies
Standalone install? If this session was not initialized by the TAO skill bank plugin, run the
tao-setupskill first (host preflight, credentials, cross-skill discovery).
Multi-phase pipeline (0–7); the mode flag selects which phases run.
| Phase | What runs | Mode(s) |
|---|---|---|
| 0 | Verify / download pretrained checkpoints | all |
| 1 | Fine-tune on dataset_dir |
full, finetune_only |
| 2 | Prepare inference JSONL (AMP routing) | full, inference_only |
| 3 | SDG — generate synthetic anomaly images → original/ |
full, inference_only |
| 4 | Eval original/ — emit per_sample.csv + eval.log, merge nn_score into SDG_result.csv |
full, inference_only |
| 5 | Per-sample (guidance, crop_ratio) search rounds → rounds/round_NN/ (each round runs SDG + eval) |
full, inference_only |
| 6 | Assemble best-of-rounds into searched/ (stitch only), plus rounds/search_summary.csv |
full, inference_only |
| 7 | Filter searched/ by nn_threshold (default 0.4), regen dropped samples, then canonical bucket eval → searched/{per_sample.csv, eval.log} |
full, inference_only |
Run every phase through to completion without mid-run pauses. Collect all required parameters up front, and run every command from the repo root.
Shell setup. All ${ANOMALYGEN_SCRIPTS} references resolve to the packaged
helper-script directory. Inside the container this is preset (ENV ANOMALYGEN_SCRIPTS=<dir>/scripts/utilities); on the host, export it once per
shell:
export ANOMALYGEN_SCRIPTS="$(git rev-parse --show-toplevel)/scripts/utilities"
python3 -m scripts.utilities.<name> invocations work from any CWD inside the
container (PYTHONPATH is preset) and from the repo root on the host. When inside
a product container (ANOMALYGEN_PRODUCT_MODE=1), invoke anomalygen-guard
before any GPU work; if it reports BLOCKED, fix the listed issues before
continuing.
Quick Start
The pipeline runs inside the metropolis_sdg.paidf_anomalygen container
(declared in versions.yaml) or any host with the cosmos-predict2 conda env
active. All phase commands assume that environment, at the repo root, with
ANOMALYGEN_SCRIPTS exported.
What ships with it
20 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.
- assets/ag_config.yaml 1.4 KB
- assets/defect_spec_template.jsonl 462 B
- BENCHMARK.md 3.9 KB
- evals/evals.json 789 B
- references/datasets.md 4.9 KB
- references/docker.md 3.5 KB
- references/error-handling.md 1.9 KB
- references/eval.md 6.1 KB
- references/finetune-commands.md 2.3 KB
- references/finetune.md 8.2 KB
- references/guard-and-custom-counts.md 2.0 KB
- references/inference-commands.md 1.4 KB
- references/inference.md 15 KB
- references/output-layout.md 3.8 KB
- references/prep-testcase.md 7.6 KB
- references/sdg-inference.md 4.8 KB
- references/sdg-refine.md 4.9 KB
- references/setup.md 4.0 KB
- skill-card.md 3.9 KB
- skill.oms.sig 8.2 KB
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 · 395 lines · 163 tokens per session scan A 35e7aa0f6111
tao-generate-anomalies is a skill published in the GitHub repository NVIDIA-TAO/tao-skill-bank (88 stars, last pushed today), licensed Apache-2.0. It adds 163 tokens to every session and 5,413 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.
Other skills, from other repositories
arrowspace
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
malloy-model
Build Malloy semantic models with base source and joined source files. Use when creating or modifying .malloy files, user asks to "create a malloy model", "add dimensions", "add measures", "create a source", or any Malloy model authoring task.
malloy-model-as-you-go
After answering a data question, write down what the answer assumed so the next reader can trust the number. A field with a.
malloy-define
Propose a source plan and field definitions for a Malloy semantic model. Covers picking which sources to model and at what grain, then proposing the specific renames, dimensions, and measures per source, every proposal backed by querying the data.