QUICKSTART

A short setup guide for connecting OpenSkills to agent frameworks such as LangChain and the Vercel AI SDK. It includes runnable Python and TypeScript examples for discovering and executing skills.

In plain words
What is it for?
Use it to create a minimal agent, load skills from a directory, list available skills, and run a skill from Python or TypeScript.
Why use it?
It removes the uncertainty of starting an OpenSkills integration. Developers can see the basic installation, runtime setup, and tool connection in one place.

Agent

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/geeksfino/openskills/quickstart
Clone the repo
git clone --depth 1 https://github.com/Geeksfino/openskills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 434 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 $0.00000 $0.00434
Opus 5 $0.00000 $0.00217
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash 017e963c6023, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

QUICKSTART 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 2d 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.

examples/agents/QUICKSTART.md · 78 lines

What it actually says

OpenSkills Agent Integration - Quick Start

Get started with OpenSkills in your agent framework in under 5 minutes.

Choose Your Path

Python Developer (LangChain)
cd with_langchain-python
pip install -r requirements.txt
python main.py
TypeScript Developer (Vercel AI SDK Example)
cd with_vercel-ai-sdk
npm install
npm run start
TypeScript Developer (Existing Project - LangChainJS)
cd with_langchain-js
npm install
npm run start
Advanced Example (LangChainJS)
cd with_langchain-js
npm run advanced

What You Get

  • A minimal agent per framework that exposes a run_skill tool
  • A single advanced example (LangChainJS) using one tool per skill
  • Skills loaded from examples/skills

Basic Integration (TypeScript)

import { OpenSkillRuntime } from "@finogeek/openskills";

const runtime = OpenSkillRuntime.fromDirectory("./examples/skills");
runtime.discoverSkills();

const skills = runtime.listSkills();
console.log(skills.map((s) => s.id));

const result = runtime.executeSkill("example-skill", {
  input: JSON.stringify({ query: "hello" }),
  timeout_ms: 5000,
});
console.log(result.outputJson);

Basic Integration (Python)

from openskills import OpenSkillRuntime

runtime = OpenSkillRuntime.from_directory("./examples/skills")
runtime.discover_skills()

skills = runtime.list_skills()
print([s["id"] for s in skills])

result = runtime.execute_skill(
    "example-skill",
    input={"query": "hello"},
    timeout_ms=5000,
)
print(result.get("output", ""))

Next Steps

  • Read the integration guide: GUIDE.md
  • Browse the examples: with_langchain-js/, with_langchain-python/, with_vercel-ai-sdk/
  • Build your own skills under examples/skills
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. 2d ago First seen · 78 lines · 0 tokens per session scan A 017e963c6023

Subscribe to this mod's changes

QUICKSTART is an agent published in the GitHub repository Geeksfino/openskills (70 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 434 tokens. 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 2026-08-30.