Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.
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/a5c-ai/babysitter/huggingface-classifiernpx skills add a5c-ai/babysitter --skill huggingface-classifiergit clone --depth 1 https://github.com/a5c-ai/babysitterWrote 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/a5c-ai/babysitter/huggingface-classifier)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/huggingface-classifier"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/huggingface-classifier.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00020 | $0.00381 |
| Opus 5 | $0.00010 | $0.00191 |
| Sonnet 5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
huggingface-classifier 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 yesterday.
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
HuggingFace Classifier Skill
Capabilities
- Fine-tune transformer models for classification
- Configure training pipelines with Trainer API
- Implement inference with optimizations
- Design label schemas and mappings
- Set up model evaluation and metrics
- Deploy models with HF Inference API
Target Processes
- intent-classification-system
- entity-extraction-slot-filling
Implementation Details
Model Types
- BERT-based: bert-base-uncased, distilbert
- RoBERTa-based: roberta-base, xlm-roberta
- DeBERTa: deberta-v3-base
- Domain-specific: FinBERT, BioBERT
Training Configuration
- Dataset preparation
- Tokenization settings
- Training arguments
- Evaluation metrics
- Early stopping
Configuration Options
- Model selection
- Number of labels
- Training hyperparameters
- Batch sizes
- Learning rate schedules
Best Practices
- Use appropriate base model
- Proper train/val/test splits
- Monitor for overfitting
- Evaluate on representative data
Dependencies
- transformers
- datasets
- accelerate
What ships with it
1 file 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.
- yesterday First seen · 73 lines · 20 tokens per session scan A d97791bb3386
huggingface-classifier is a skill published in the GitHub repository a5c-ai/babysitter (1,772 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 381 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 2026-09-05.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
AgentDB Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
AgentDB Performance Optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.
V3 Performance Optimization
Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.
stream
Designing ETL/ELT pipelines, visualizing data flows, selecting batch/streaming approaches, and architecting Kafka/Airflow/dbt systems. Use when building data pipelines or managing data quality.