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-document-parsegit 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-document-parse)<a href="https://agentmods.dev/skills/upstageai/upstage-extensions-hub/upstage-document-parse"><img src="https://agentmods.dev/badge/skills/upstageai/upstage-extensions-hub/upstage-document-parse/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-document-parse"><img src="https://agentmods.dev/badge/skills/upstageai/upstage-extensions-hub/upstage-document-parse.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 | $0.00153 | $0.01187 |
| Opus 5 | $0.00077 | $0.00593 |
| Sonnet 5 | $0.00031 | $0.00237 |
| Haiku 4.5 | $0.00015 | $0.00119 |
Grade B, and why
upstage-document-parse scanned grade B with 2 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 9d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post( "https://api.upstage.ai/v1/document-digitization", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post( How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstage Document Parse
Convert documents into structured HTML/Markdown. Recognizes layout elements such as tables, images, equations, and charts with bounding box coordinates.
Quick Start
import os
import requests
with open("report.pdf", "rb") as f:
response = requests.post(
"https://api.upstage.ai/v1/document-digitization",
headers={"Authorization": f"Bearer {os.environ['UPSTAGE_API_KEY']}"},
files={"document": f},
data={"model": "document-parse", "output_formats": "['markdown']"}
)
print(response.json()["content"]["markdown"])
API Key: Always use os.environ["UPSTAGE_API_KEY"]. Get your key at console.upstage.ai.
Supported Formats
JPEG, PNG, BMP, PDF (up to 1000 pages with async), TIFF, HEIC, DOCX, PPTX, XLSX, HWP, HWPX
Sync vs Async
| Mode | Endpoint | Max pages | Max file size | Notes |
|---|---|---|---|---|
| Sync | /v1/document-digitization |
100 | 50 MB | Result returned in response (5 min server timeout). Best for ≤ 100 pages and quick turnaround. |
| Async | /v1/document-digitization/async |
1000 | 50 MB | Returns request_id; processed in 10-page batches. Use when document exceeds sync limits or sync would time out. |
Decision rule:
- ≤ 100 pages and expected to finish within 5 min → sync.
- 100 pages, scanned/complex content, or batch jobs → async.
For async submit/poll workflow, see references/async-workflow.md.
Key Parameters (Sync)
| Parameter | Default | Common Values |
|---|---|---|
model |
required | document-parse |
output_formats |
['html'] |
['markdown'], ['html', 'markdown'] |
mode |
standard |
enhanced (complex tables), auto |
ocr |
auto |
force (always OCR scanned PDFs) |
coordinates |
true |
false to omit bounding boxes |
For full parameter reference and curl variations (enhanced mode, force OCR, base64 table images, LangChain integration), see references/sync-options.md.
What ships with it
2 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.
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.
- 9d ago First seen · 107 lines · 153 tokens per session scan B 258407ca5e71
upstage-document-parse is a skill published in the GitHub repository UpstageAI/upstage-extensions-hub (10 stars, last pushed 4mo ago), licensed MIT. It adds 153 tokens to every session and 1,187 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.