What is llm-integration?

A guide to connecting applications to large language models, including tool calling, streamed responses, local models, and model fine-tuning. Fine-tuning means training an existing model further for a specific use.

Use it to build tool-using assistants, streaming endpoints, Ollama-based local inference, LoRA or QLoRA fine-tuning, context management, evaluations, and prompt workflows.

It helps solve common integration problems such as validating tool inputs, delivering responses as they arrive, running models locally, and adapting models to custom data.

llm-integration — Skill for Claude Code by yonatangross/orchestkit

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.

Any agent

npx skills add yonatangross/orchestkit --skill llm-integration

Clone the repo

git clone --depth 1 https://github.com/yonatangross/orchestkit

Made for: Claude Code.

Or install ork, the plugin that ships this one along with the rest of its 111 skills, 38 commands, 36 agents, 32 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yonatangross/orchestkit/llm-integration/github.svg)](https://agentmods.dev/skills/yonatangross/orchestkit/llm-integration)

Your own site

<a href="https://agentmods.dev/skills/yonatangross/orchestkit/llm-integration"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/llm-integration/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yonatangross/orchestkit/llm-integration"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/llm-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,705 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.02705
Opus 5.5	$0.00023	$0.01082
Sonnet 5.5	$0.00012	$0.00541
Haiku 4.5	$0.00006	$0.00270

Measured 11d ago against content hash 79bd8fe92bc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-integration 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 11d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/dpo-training.py, scripts/function-def.py, scripts/ollama-provider-template.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/ork/skills/llm-integration/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Integration

Patterns for integrating LLMs into production applications: tool use, streaming, local inference, and fine-tuning. Each category has individual rule files in rules/ loaded on-demand.

Quick Reference

Category	Rules	Impact	When to Use
Function Calling	3	CRITICAL	Tool definitions, parallel execution, input validation
Streaming	3	HIGH	SSE endpoints, structured streaming, backpressure handling
Local Inference	3	HIGH	Ollama setup, model selection, GPU optimization
Fine-Tuning	3	HIGH	LoRA/QLoRA training, dataset preparation, evaluation
Context Optimization	2	HIGH	Window management, compression, caching, budget scaling
Evaluation	2	HIGH	LLM-as-judge, RAGAS metrics, quality gates, benchmarks
Prompt Engineering	4	HIGH	CoT, few-shot, versioning, DSPy optimization, ReAct, cost optimization

Total: 20 rules across 7 categories

Quick Start

# Function calling: strict mode tool definition
tools = [{
    "type": "function",
    "function": {
        "name": "search_documents",
        "description": "Search knowledge base",
        "strict": True,
        "parameters": {
            "type": "object",
            "properties": {
                "query": {"type": "string", "description": "Search query"},
                "limit": {"type": "integer", "description": "Max results"}
            },
            "required": ["query", "limit"],
            "additionalProperties": False
        }
    }
}]

# Streaming: SSE endpoint with FastAPI
@app.get("/chat/stream")
async def stream_chat(prompt: str):
    async def generate():
        async for token in async_stream(prompt):
            yield {"event": "token", "data": token}
        yield {"event": "done", "data": ""}
    return EventSourceResponse(generate())

Read the full file on GitHub · 226 lines

Files

What ships with it

34 files 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.

11d ago Changed 79bd8fe92bc5
15d ago Changed · -1 lines 0cd145f6b3c5
21d ago Changed f113dba7e862
23d ago Changed · -5 lines d7c7970e577e
24d ago Changed · -1 lines 449d5167ab8a
25d ago Changed 835cc2f3aa63
27d ago Changed 4cb2ef667554
1mo ago Changed 265ba1dcf83d
1mo ago First seen · 233 lines · 58 tokens per session scan A 6878545224ca

Subscribe to this mod's changes

llm-integration is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,705 once invoked, about $0.0002 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 2026-09-03.

Building agents Claude Code Data and AI LLM Prompting agents ai-development claude-plugin langgraph

natural

Render the provided prompt template with Jinja context and send it to the active NPC's LLM. The rendered text becomes the user prompt; the LLM response is placed in context['output'].

NPC-Worldwide/npcpy · 41 tokens

langchain

Use when building LLM applications with LangChain — LCEL chains (prompt | model | parser), tool-calling agents via createagent, @tool definitions, RAG pipelines (loaders, splitters, vector stores, retrievers), short-term memory with LangGraph checkpointers, and GIS workflows such as natural-language PostGIS queries or…

znlgis/opengis-skills · 93 tokens

prompt-enhancer

Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model.

sammcj/agentic-coding · 63 tokens

ambitious-model-use

Use when the user asks to be more ambitious with an AI task: aim at the outcome behind it, work it like a field-leading expert from raw data, or bring in other fields. Do NOT use for plain prompt rewording; use prompt-enhancer.

sammcj/agentic-coding · 58 tokens

llm-prompting-guide

Prompt format rules for generative video and music models. Use when writing or reviewing a prompt for MiniMax H3 (text/image/reference-to-video with native audio) or MiniMax Music 3 (song generation from caption plus lyrics), in ComfyUI or elsewhere. Do NOT use for chat-assistant prompts, or for generative models not…

sammcj/agentic-coding · 79 tokens

meta-harness

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…

001TMF/harness-forge · 217 tokens