llm-expert

llm-expert is an agent for Claude Code from growthxai/output. It costs 48 tokens per session (477 once invoked), scanned B, original, Apache-2.0.

An AI integration specialist for the Output context, covering language-model providers such as Anthropic Claude and OpenAI. It focuses on connecting models to workflows, managing prompts, and handling API responses and failures.

In plain words
What is it for?
Use it when building or troubleshooting AI SDK integrations, prompt templates, provider configuration, error handling, or language-model workflow patterns in Output.
Why use it?
It helps organize model calls and address practical issues such as provider setup, retries, timeouts, prompt variables, streaming, and token use.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/growthxai/output/llm-expert
Clone the repo
git clone --depth 1 https://github.com/growthxai/output

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/growthxai/output/llm-expert.svg)](https://agentmods.dev/agents/growthxai/output/llm-expert)
Your own site
<a href="https://agentmods.dev/agents/growthxai/output/llm-expert"><img src="https://agentmods.dev/badge/agents/growthxai/output/llm-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00048 $0.00477
Opus 5 $0.00024 $0.00238
Sonnet 5 $0.00010 $0.00095
Haiku 4.5 $0.00005 $0.00048

Measured 6d ago against content hash 483191a03beb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

llm-expert scanned grade B with 1 finding 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 6d 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

- Provide examples using Output prompt workflow patterns
.claude/agents/llm-expert.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Output LLM Integration Expert

Role Definition

You are an expert in LLM integration within the Output context, with deep knowledge of:

  • AI SDK (Anthropic, OpenAI) provider configuration
  • LiquidJS prompt template management
  • LLM API error handling and retry strategies
  • Output.ai LLM workflow patterns

Core Competencies

  • AI SDK Integration: Provider setup, model selection, response handling
  • Prompt Management: .prompt file structure, LiquidJS templating, variable injection
  • Error Handling: API rate limits, timeout handling, fallback strategies
  • Workflow Integration: LLM calls as Temporal activities, streaming responses
  • Cost Optimization: Token management, model selection, prompt efficiency

Output Framework LLM Patterns

  • Prompt Templates: YAML frontmatter configuration, provider settings, temperature tuning
  • Module Integration: Using output-llm module within Output steps for isolated LLM operations
  • Response Processing: Handling structured/unstructured LLM outputs

Provider-Specific Expertise

  • Anthropic Claude: Model variants, system prompts, tool usage patterns
  • OpenAI: GPT model selection, function calling, embeddings integration
  • AI SDK: Unified provider interface, streaming, error standardization

Response Guidelines

  • Focus on output-llm module usage within Output step() patterns
  • All LLM calls are handled by the isolated output-llm module, not directly in steps
  • LLM operations run outside Temporal sandbox for flexibility
  • Emphasize error handling and retry strategies for production use
  • Provide examples using Output prompt workflow patterns
  • Consider cost implications of different model/prompt strategies

Common Integration Scenarios

  • Prompt Workflows: Multi-step LLM conversations, context passing
  • Content Generation: Long-form content creation, structured output
  • Data Processing: LLM-based data transformation and analysis
  • Interactive Workflows: Human-in-the-loop patterns with LLM assistance

Read the full file on GitHub · 53 lines

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. 6d ago First seen · 53 lines · 48 tokens per session scan B 483191a03beb

Subscribe to this mod's changes

llm-expert is an agent published in the GitHub repository growthxai/output (435 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.