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 spreadsheet-direct-verificationgit 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/spreadsheet-direct-verification)<a href="https://agentmods.dev/skills/hkuds/openspace/spreadsheet-direct-verification"><img src="https://agentmods.dev/badge/skills/hkuds/openspace/spreadsheet-direct-verification.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 5.1 | $0.00036 | $0.03221 |
| Opus 5 | $0.00018 | $0.01611 |
| Sonnet 5 | $0.00007 | $0.00644 |
| Haiku 4.5 | $0.00004 | $0.00322 |
Grade A, and why
spreadsheet-direct-verification 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 3d 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 — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spreadsheet Direct Verification
Use this workflow when a higher-level or delegated agent has interacted with spreadsheet files, but its summaries or claims are inconsistent, incomplete, or hard to trust.
The goal is to replace uncertain narrative summaries with a direct, reproducible inspection from disk before you finalize your answer.
When to use this
Apply this skill when any of the following happen:
- A delegated agent reports conflicting workbook facts across messages
- Sheet names, row counts, headers, or output paths are inconsistent
- The agent says a file was created or modified, but did not verify it from disk
- The task depends on exact workbook contents, especially after edits
- You need a trustworthy final summary of what actually exists on disk
Core principle
When spreadsheet state matters, trust a deterministic script over a conversational summary.
Inspect the workbook directly with Python and openpyxl, and print a compact report covering:
- workbook path
- whether the file exists
- sheet names
- per-sheet headers
- per-sheet row counts
- totals for "marked" rows, if relevant to the task
- whether expected output files exist
Use the script output as the basis for your final response.
Workflow
- Identify the workbook(s) and expected output file(s).
- Determine what "marked row" means for the task.
- Examples:
- rows with a non-empty marker column
- rows with
x,yes,true, or1 - rows highlighted by a prior workflow that also wrote a marker column
- Examples:
- Run a direct Python inspection on the files from disk.
- Compare the script output against any delegated summary.
- If they differ, treat the script as authoritative.
- Only then provide the final user-facing summary.
Minimum verification checklist
Before finalizing, verify and record:
- exact input workbook path inspected
- exact output workbook path inspected
- whether each file exists
- all sheet names in each workbook
- header row for each relevant sheet
- number of non-empty data rows per sheet
- number of marked rows per sheet, if applicable
- whether modifications appear in the saved output 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.
- 3d ago First seen · 375 lines · 36 tokens per session scan A 3a48daa7e483
spreadsheet-direct-verification is a skill published in the GitHub repository HKUDS/OpenSpace (7,510 stars, last pushed 25d ago), licensed MIT. It adds 36 tokens to every session and 3,221 once invoked, about $0.0002 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
define-data
Standalone Phase 4 of SAP UI testing. Authors one tests/ /test-cases/TC-XXX.data.md requirement spec per case marked dataRequired: yes — choosing the narrowest correct source (sql/static/generated/seeded), and generating upload fixtures in the EXACT file format the program parses (xlsx vs csv). Validates that every…
xz-cases
A generator for acceptance-test checklists covering the core feature changes between specified software versions. It writes the checklist to an XLSX spreadsheet, a format used by Microsoft Excel and similar programs.
postman-test-implementation
Converts an approved company-format testcase workbook (from api-test-design + company-testcase-format) into one Postman collection and one Postman environment, using conventions learned from real company artifacts and this project's src/postman builders. Does not execute anything and does not decide what to test.
company-testcase-format
Formats scenarios produced by api-test-design into the company's real QA testcase conventions (spreadsheet columns, TCID scheme, Postman naming/scripting), learned from actual SDA V2 reference artifacts and kept service-agnostic — never copies SDA's API fields/values into another service's testcase sheet.
test-case-generator
Generates comprehensive, structured test cases from feature descriptions, user stories, requirements, or acceptance criteria — and exports them as a formatted Excel (.xlsx) file ready for use in Excel or Google Sheets. Use this skill whenever the user mentions: "write test cases", "generate test cases", "create test…
dcf-model
Build discounted cash flow valuation workbooks in Excel.