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 skills add a5c-ai/babysitter --skill llm-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/llm-classifier)<a href="https://agentmods.dev/skills/a5c-ai/babysitter/llm-classifier"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/llm-classifier/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/a5c-ai/babysitter/llm-classifier"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/llm-classifier.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 | $0.00018 | $0.00345 |
| Opus 5.5 | $0.00007 | $0.00138 |
| Sonnet 5.5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
llm-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 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
LLM Classifier Skill
Capabilities
- Implement zero-shot classification with LLMs
- Design few-shot classification prompts
- Configure structured output for labels
- Implement confidence scoring
- Design classification taxonomies
- Handle multi-label classification
Target Processes
- intent-classification-system
- dialogue-flow-design
Implementation Details
Classification Patterns
- Zero-Shot: No examples, description-based
- Few-Shot: Example-based classification
- Structured Output: JSON schema for labels
- Chain-of-Thought: Reasoning before classification
- Ensemble: Multiple prompts/models
Configuration Options
- LLM model selection
- Label descriptions
- Example selection strategy
- Output format specification
- Confidence calibration
Best Practices
- Clear label descriptions
- Representative examples
- Consistent output format
- Calibrate confidence scores
- Test with edge cases
Dependencies
- langchain-core
- LLM provider
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.
- 1mo ago First seen · 66 lines · 18 tokens per session scan A 35481ef53759
llm-classifier is a skill published in the GitHub repository a5c-ai/babysitter (1,860 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 345 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 2026-09-05.
Other skills, from other repositories
prompt-library
Maintain a structured, versioned library of the prompts and behavioral templates used by agents in this repository. Use when adding a new agent or skill (to register it in the library).
hybrid-reasoning
Hybrid AI combining deterministic rule engines with LLM reasoning for efficient, auditable, and reliable decision-making.
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
extended-thinking
Use Claude's extended thinking (reasoning) mode effectively — budget tokens, interleaved thinking with tool use, when it helps, when it wastes tokens, and how to inspect the thinking trace. Use this skill when building reasoning-heavy features (math, code generation, multi-step planning), debugging why a model is…
long-context-1m
Use Claude's 1M-token context window effectively — when to use it, how to structure inputs for recall, how to price it, and how to combine with prompt caching to keep it affordable. Use this skill when building apps that feed large codebases, long documents, or entire conversation histories to Claude, or when weighing…
model-recommendation
Analyse chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency.