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 agentmods add skills/hkuds/openspace/prioritize-context-datanpx skills add HKUDS/OpenSpace --skill prioritize-context-datagit 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/prioritize-context-data)<a href="https://agentmods.dev/skills/hkuds/openspace/prioritize-context-data"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/prioritize-context-data.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 | $0.00021 | $0.00710 |
| Opus 5 | $0.00010 | $0.00355 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
prioritize-context-data 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prioritize Context Data
Objective
Prevent data hallucination and inefficiency by mandating that agents inspect and utilize provided reference files (CSV, XLSX, PDF, TXT, etc.) before attempting web searches or generating synthetic data.
Critical Rule
If a reference file is provided in the task context, it is the source of truth. Do not fabricate data or search the web for information that exists within the provided attachments.
Workflow Steps
1. Scan Context for Attachments
At the start of every task, explicitly list all files provided in the context window or attachment panel.
- Check for spreadsheets (
.xlsx,.csv), documents (.pdf,.docx), or data dumps (.json,.txt). - Note the filename and inferred content type.
2. Evaluate Relevance
Determine if any provided file contains the data required to complete the task.
- Match Keywords: Do filenames or column headers match task requirements?
- Check Scope: Does the data cover the necessary timeframe or地域 (region)?
3. Extract Data First
If relevant files are found:
- Read the file content using appropriate tools (e.g.,
read_file,pandas,pdf_reader). - Extract the specific data points needed.
- Do not proceed to web search until you have confirmed the file lacks the necessary information.
4. Cite Source Explicitly
When presenting data in the final output:
- Explicitly state which file the data came from.
- Example: "According to
Massabama_active_listings.xlsx..." - This verifies to the user that real data was used, not hallucinated.
5. Fallback to Search (Only if Necessary)
If the provided files do not contain the specific data needed:
- State clearly what was missing from the files.
- Then proceed with web search or estimation.
- Mark any non-file data as "External Search" or "Estimated".
Checklist
- Did I list all attached files?
- Did I open and read the relevant files?
- Did I verify the data exists in the files before searching?
- Did I cite the file name in my output?
- Did I avoid fabricating numbers that should have come from the file?
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.
- yesterday First seen · 75 lines · 21 tokens per session scan A 0842f166bdb0
prioritize-context-data is a skill published in the GitHub repository HKUDS/OpenSpace (7,506 stars, last pushed 23d ago), licensed MIT. It adds 21 tokens to every session and 710 once invoked, about $0.0001 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
smart-data-collection
智能数据采集技能，用于从图片或文档（PDF、Word、Excel）中提取结构化数据，基于知识网络完成字段映射，生成SQL并写入数据库。当用户提到"数据采集"、"从文档提取数据"、"图片转数据"、"数据导入"、"文档数据入库"、"批量数据提取"或需要从非结构化文件中提取结构化数据并存储时，自动使用此技能。.
office-mcp
MCP server with 39 tools for Word, Excel, PowerPoint, PDF, OCR operations.
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
report-generator
高级报告生成专家，支持多格式输出、数据可视化和交互式报告生成。.
meta-multi-format-export-pack
From one piece of source content, render four deliverables: .docx report, .pptx slides, .xlsx data, and an HTML/PDF public version.