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 hf-cligit 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/hf-cli)<a href="https://agentmods.dev/skills/metaspartan/cybara/hf-cli"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/hf-cli/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/metaspartan/cybara/hf-cli"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/hf-cli.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00392 |
| Opus 5.5 | $0.00012 | $0.00157 |
| Sonnet 5.5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
hf-cli 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 1mo 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 CLI
Use the current hf CLI for Hub operations. Do not use the deprecated huggingface-cli command.
Workflow
- Run
hf versionandhf --helpbefore relying on a command that may vary by installed version. - Use public read-only operations without authentication when possible.
- For private or write operations, run
hf auth whoamiwithout printing stored tokens. - Prefer structured output such as
--format jsonwhen another tool will consume the result. - Use
--dry-runwhen supported before downloads, cache cleanup, synchronization, or deletion. - Confirm the repository, revision, visibility, and affected paths before uploads or destructive changes.
Common operations
hf models info namespace/model --format json
hf models list --search "query" --limit 20 --format json
hf datasets info namespace/dataset --format json
hf datasets list --search "query" --limit 20 --format json
hf download namespace/model --include "*.json" --dry-run
hf cache list --limit 30
hf papers list --limit 20 --format json
Use hf upload for a bounded file or directory and hf upload-large-folder for resumable large uploads. Never place a token in command arguments, source files, logs, or chat output. Use the authenticated credential store or HF_TOKEN environment variable.
If hf is unavailable, report that prerequisite clearly. Do not install software unless the user requested installation.
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.
- 1mo ago First seen · 35 lines · 30 tokens per session scan A 5c00d0ac0df6
hf-cli is a skill published in the GitHub repository metaspartan/cybara (32 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 392 once invoked, about $0.0001 per session on Opus 5.5. 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
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
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…
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…
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.