OpenSpace is a skill-management layer for AI agents that stores, retrieves, evaluates, shares, and improves reusable workflows. It is intended for people using multiple coding agents who want skills to be reused and refined based on task outcomes. The catalogue provides 200 skills for use with OpenSpace and the agents it supports.
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 HKUDS/OpenSpace --skill pdf-download-extract-fallback-enhanced-e27e0cgit clone --depth 1 https://github.com/HKUDS/OpenSpaceWrote 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/hkuds/openspace/pdf-download-extract-fallback-enhanced-e27e0c)<a href="https://agentmods.dev/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-e27e0c"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-e27e0c/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/hkuds/openspace/pdf-download-extract-fallback-enhanced-e27e0c"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/pdf-download-extract-fallback-enhanced-e27e0c.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.02539 |
| Opus 5 | $0.00011 | $0.01269 |
| Sonnet 5 | $0.00004 | $0.00508 |
| Haiku 4.5 | $0.00002 | $0.00254 |
Grade A, and why
pdf-extract-shell-first scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" -o target.pdf "URL_HERE" How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Extract with Shell-First Tool Cascade
This skill provides an optimized workflow for extracting text content from PDF documents (local files or downloaded URLs) using a prioritized tool cascade that favors shell-based extraction before falling back to Python libraries.
Why Shell-First?
Analysis of execution patterns shows:
read_fileon PDFs sometimes returns binary/image data instead of textrun_shellwithpdftotexthas higher success rate and fewer sandbox errorsexecute_code_sandboxcan fail with "unknown error" in constrained environments- Shell tools are more reliable for PDF text extraction when available
Entry Point: Determine Your Starting Point
Before beginning, identify your scenario:
| Scenario | Start Here | Skip |
|---|---|---|
| PDF already on local disk | Step 1 (Try read_file) | Shell download steps |
| PDF at a web URL | Shell download, then Step 1 | None |
| Need maximum reliability | Full cascade (all 3 tools) | None |
Complete Workflow
Step 0: Download PDF (URL Only)
If your PDF is at a web URL, download it first using browser user-agent:
curl -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" -o target.pdf "URL_HERE"
Key flags:
-L: Follow redirects-A: Set user-agent header to mimic a real browser-o: Specify output filename
If you already have the PDF locally, skip to Step 1.
Step 1: Try read_file (Primary Attempt)
First, attempt to extract text using the read_file tool:
read_file(filetype="pdf", file_path="target.pdf")
Evaluate the response:
| Response Type | Interpretation | Next Action |
|---|---|---|
| Clean readable text | Success | Proceed to content analysis |
| Binary data / PNG image / garbled | read_file returned raw data |
Go to Step 2 immediately |
| Error / timeout | Tool failure | Go to Step 2 immediately |
Critical: If read_file returns binary image data or garbled content, do not retry read_file. Immediately proceed to Step 2.
What ships with it
1 file 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.
- 6d ago First seen · 307 lines · 22 tokens per session scan A 2fc43bca9e54
pdf-extract-shell-first is a skill published in the GitHub repository HKUDS/OpenSpace (7,552 stars, last pushed 28d ago), licensed MIT. It adds 22 tokens to every session and 2,539 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
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.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…