llm-classifier

llm-classifier is a skill for Claude Code from a5c-ai/babysitter. It costs 18 tokens per session (345 once invoked), scanned A, original, MIT.

A method for using a language model to assign text to one or more labels. It supports zero-shot classification without examples, few-shot classification with examples, structured label output, and confidence scores.

In plain words
What is it for?
Use it for intent detection, multi-label classification, label-taxonomy design, JSON-formatted results, and testing classification edge cases.
Why use it?
It lets you detect intents or categories without building a separate fixed classifier for every use case. Clear taxonomies, examples, and confidence calibration make the results easier to check.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

About the project

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.

a5c-ai/babysitter · 1,770 stars · on GitHub · a5c.ai

Install

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.

agentmods
npx agentmods add skills/a5c-ai/babysitter/llm-classifier
Any agent
npx skills add a5c-ai/babysitter --skill llm-classifier
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

Wrote 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.

agentmods badge for llm-classifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/llm-classifier.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/llm-classifier)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00345
Opus 5 $0.00009 $0.00172
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured yesterday against content hash 35481ef53759, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

library/specializations/ai-agents-conversational/skills/llm-classifier/SKILL.md · 66 lines

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

  1. Zero-Shot: No examples, description-based
  2. Few-Shot: Example-based classification
  3. Structured Output: JSON schema for labels
  4. Chain-of-Thought: Reasoning before classification
  5. 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
Files

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.

Changes

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.

  1. yesterday First seen · 66 lines · 18 tokens per session scan A 35481ef53759

Subscribe to this mod's changes

llm-classifier is a skill published in the GitHub repository a5c-ai/babysitter (1,770 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 345 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.

Related

Other skills, from other repositories