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 metaspartan/cybara --skill huggingface-datasetsgit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/huggingface-datasets)<a href="https://agentmods.dev/skills/metaspartan/cybara/huggingface-datasets"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/huggingface-datasets.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00431 |
| Opus 5 | $0.00015 | $0.00216 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
huggingface-datasets 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 8d 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
Hugging Face Datasets
Prefer the read-only Dataset Viewer API for discovery and validation. Use Cybara's http tool so responses remain structured and visible in the chat.
Read-only workflow
- Validate the dataset with
GET https://datasets-server.huggingface.co/is-valid?dataset=<id>. - Resolve subsets and splits through
/splits. - Inspect representative records with
/first-rows. - Paginate
/rowswith a zero-basedoffsetandlengthno greater than 100. - Use
/searchfor text and/filterfor predicates instead of downloading the full dataset. - Inspect
/size,/statistics, and/parquetbefore training or bulk processing.
URL-encode dataset IDs, subset names, split names, queries, and predicates. Add Authorization: Bearer <token> only for a gated or private dataset, and never expose the token in output.
Training readiness
Before proposing a training run, report:
- dataset ID, revision, subset, and split
- row count and relevant columns
- a small redacted sample
- missing, malformed, duplicate, or unexpectedly long records
- license, gating, and provenance constraints visible in the dataset card
- the exact mapping required by the selected trainer
For SFT, verify text, conversational messages, or prompt-completion records. For preference training, verify prompt, chosen, and rejected values. For reward or RL workflows, verify the expected prompt and reward inputs.
Cybara Lab can export hf_session_trace data. Validate and redact that export before uploading it as a dataset.
Uploading, changing visibility, or deleting a dataset is an external side effect. Confirm the destination repository and affected files immediately before the write.
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.
- 8d ago First seen · 38 lines · 31 tokens per session scan A ad3f8140445f
huggingface-datasets is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 431 once invoked, about $0.0002 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
ecc-cost-aware-llm-pipeline
Skill "ecc-cost-aware-llm-pipeline" from KornLabs/truss, covering cost-aware llm pipeline, when to activate, core concepts, 1. model routing by task complexity and 2. immutable cost tracking.
bigquery-ai-ml
Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
salary-market-scanner
Scan live job boards and salary databases to find real-time compensation data for any role and location. Use this skill when a user asks "what's the going rate for a senior React engineer in London", "software engineer salary Singapore", "how much do ML engineers make", "what should I be earning as a [role]", "is my…
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
weknora-rag-search
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.