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 skills add UpstageAI/upstage-extensions-hub --skill upstage-buildergit clone --depth 1 https://github.com/UpstageAI/upstage-extensions-hubWrote 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/upstageai/upstage-extensions-hub/upstage-builder)<a href="https://agentmods.dev/skills/upstageai/upstage-extensions-hub/upstage-builder"><img src="https://agentmods.dev/badge/skills/upstageai/upstage-extensions-hub/upstage-builder/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.
<a href="https://agentmods.dev/skills/upstageai/upstage-extensions-hub/upstage-builder"><img src="https://agentmods.dev/badge/skills/upstageai/upstage-extensions-hub/upstage-builder.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00145 | $0.02786 |
| Opus 5 | $0.00072 | $0.01393 |
| Sonnet 5 | $0.00029 | $0.00557 |
| Haiku 4.5 | $0.00015 | $0.00279 |
Grade A, and why
upstage-builder 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.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
upstage-builder — Upstage API and Webapp Delivery Skill
You are an expert at generating code that uses the Upstage API (api.upstage.ai). When the user asks you to build features or services using Upstage/Solar models, follow this guide.
For full webapp requests, do not stop at code generation. Treat project location, environment variables, deployment method, and shareable URL delivery as part of the task.
Webapp Setup Rules
When the user asks for a full web service/app built with Upstage, follow this startup flow:
- If deployment system and project root are not already known, ask once:
- Which deployment system should be used?
- Which project root should be used?
- If defaults are already configured, use them.
- For this installation, default to:
- project root:
/data/.openclaw/workspace/projects - deployment provider:
vercel - visibility mode:
password-protected
- project root:
- Prefer password-protected or private delivery over public delivery unless the user explicitly asks for public access.
- Create one folder per app under the configured project root.
- Return these at the end whenever possible:
- project path
- stack used
- required environment variables
- deployment method
- visibility mode
- external deployment URL, or the exact next step if deployment could not be completed
- site password if password-protected mode was used
Read references/webapp-workflow.md for the full project/deployment workflow.
Quick Start
Upstage APIs are OpenAI SDK compatible. Just change base_url:
from openai import OpenAI
import os
client = OpenAI(
api_key=os.environ["UPSTAGE_API_KEY"],
base_url="https://api.upstage.ai/v1"
)
response = client.chat.completions.create(
model="solar-pro3",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
API Key: Always use os.environ["UPSTAGE_API_KEY"]. Never hardcode keys. Users get their key from console.upstage.ai.
What ships with it
16 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.
- config.json 213 B
- examples/chat-example.py 1.0 KB runs code
- examples/document-example.py 3.7 KB runs code
- examples/rag-example.py 1.9 KB runs code
- references/agent-api.md 6.9 KB
- references/chat-completions.md 19 KB
- references/common-patterns.md 9.7 KB
- references/document-classification.md 11 KB
- references/document-processing.md 22 KB
- references/embeddings.md 3.7 KB
- references/information-extraction.md 22 KB
- references/webapp-workflow.md 1.9 KB
- requirements.txt 46 B
- scripts/init_webapp_project.py 1.6 KB runs code
- scripts/refresh_references.py 3.3 KB runs code
- scripts/smoke_test.py 1.1 KB runs code
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 First seen · 249 lines · 145 tokens per session scan A 4d027d9df883
upstage-builder is a skill published in the GitHub repository UpstageAI/upstage-extensions-hub (10 stars, last pushed 4mo ago), licensed MIT. It adds 145 tokens to every session and 2,786 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.