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 agentmods add skills/aiming-lab/autoresearchclaw/data-loadingnpx skills add aiming-lab/AutoResearchClaw --skill data-loadinggit clone --depth 1 https://github.com/aiming-lab/AutoResearchClawWhat 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 | $0.00022 | $0.00202 |
| Opus 5 | $0.00011 | $0.00101 |
| Sonnet 5 | $0.00004 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
data-loading 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 3d 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.
What it actually says
Efficient Data Loading Best Practice
- Use num_workers = min(8, os.cpu_count()) for DataLoader
- Enable pin_memory=True when using GPU
- Use persistent_workers=True to avoid re-spawning
- Pre-compute and cache transformations when possible
- For image data: use torchvision.transforms.v2 (faster)
- For large datasets: consider memory-mapped files or WebDataset
- Profile with torch.utils.bottleneck to find I/O bottlenecks
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.
- 3d ago First seen · 22 lines · 22 tokens per session scan A 75ae857593ba
data-loading is a skill published in the GitHub repository aiming-lab/AutoResearchClaw (14,306 stars, last pushed 14d ago), licensed MIT. It adds 22 tokens to every session and 202 once invoked, about $0.0001 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
autocontext-creator
Use when an agent needs to CREATE knowledge with Autocontext - run a scenario or plain-language task through the improvement loop, judge or improve a single output, and inspect what the run produced. Host-agnostic; requires only the autoctx CLI.
llm-finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization.
ml-engineer
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps.
data-pipeline
Data pipeline expert for ETL, Apache Spark, Airflow, dbt, and data quality.
prompt-engineer
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization.
geepers-data
Fetch structured data from 17 authoritative APIs — arXiv, Census Bureau, GitHub, NASA, Wikipedia, PubMed, news, weather, finance, FEC, and more — through a single endpoint. Use when you need real data from authoritative sources for research, visualizations, or analysis.