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/yonatangross/orchestkit/llm-integrationnpx skills add yonatangross/orchestkit --skill llm-integrationgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/llm-integration)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/llm-integration"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/llm-integration.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 | $0.00058 | $0.02504 |
| Opus 5 | $0.00029 | $0.01252 |
| Sonnet 5 | $0.00012 | $0.00501 |
| Haiku 4.5 | $0.00006 | $0.00250 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 233 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())
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.
- checklists/fine-tuning-decision.md 2.0 KB
- checklists/streaming-checklist.md 547 B
- checklists/tool-checklist.md 1.2 KB
- metadata.json 451 B
- references/model-selection.md 2.7 KB
- references/ork-delta.md 3.3 KB
- rules/_sections.md 3.0 KB
- rules/_template.md 339 B
- rules/calling-parallel.md 3.0 KB
- rules/calling-tool-definition.md 3.3 KB
- rules/calling-validation.md 4.5 KB
- rules/context-caching.md 2.3 KB
- rules/context-window-management.md 2.0 KB
- rules/evaluation-benchmarks.md 2.7 KB
- rules/evaluation-metrics.md 2.4 KB
- rules/local-gpu-optimization.md 3.9 KB
- rules/local-model-selection.md 2.8 KB
- rules/local-ollama-setup.md 3.7 KB
- rules/prompt-design.md 2.6 KB
- rules/prompt-optimization.md 4.5 KB
- rules/prompt-react-pattern.md 3.3 KB
- rules/prompt-testing.md 2.6 KB
- rules/streaming-backpressure.md 3.4 KB
- rules/streaming-sse.md 3.1 KB
- rules/streaming-structured.md 3.9 KB
- rules/tuning-dataset-prep.md 3.1 KB
- rules/tuning-evaluation.md 4.4 KB
- rules/tuning-lora.md 3.9 KB
- scripts/create-lora-config.md 1.9 KB
- scripts/dpo-training.py 12 KB runs code
- scripts/function-def.py 3.8 KB runs code
- scripts/lora-config.yaml 5.6 KB
- scripts/ollama-provider-template.py 13 KB runs code
- test-cases.json 11 KB
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 · 233 lines · 58 tokens per session scan A 6878545224ca
llm-integration is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 2,504 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
data-validation-first
Use this skill before any data analysis, transformation, or modeling. Always inspect and validate the data before drawing conclusions or writing transformations.
input-validation-and-sanitization
Use this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input. Validate and sanitize all untrusted data before processing — never assume input is safe.
robust-error-handling-in-scripts
Use this skill when writing shell scripts, Python automation, or any unattended batch job. Ensure failures are detected, logged, and handled — never silently ignored.
structured-logging-and-observability
Use this skill when building production services, pipelines, or automation that needs to be debugged, monitored, or audited. Add structured logs, metrics, and health checks before shipping any service.
fine-tune-readiness
Decide whether fine-tuning is justified versus prompting or RAG, and gate the training dataset before any LoRA/SFT/DPO run. Use when someone says 'let's fine-tune'.
context-budget-audit
Audit the seven claimants on an LLM call's context window, set a working ceiling, and cut in the right order. Use when prompts grow, agents drift, or token bills surprise you.