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 dream-num/skills --skill univer-cligit clone --depth 1 https://github.com/dream-num/skillsWrote 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/dream-num/skills/univer-cli)<a href="https://agentmods.dev/skills/dream-num/skills/univer-cli"><img src="https://agentmods.dev/badge/skills/dream-num/skills/univer-cli/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/dream-num/skills/univer-cli"><img src="https://agentmods.dev/badge/skills/dream-num/skills/univer-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00057 | $0.01026 |
| Opus 5.5 | $0.00023 | $0.00410 |
| Sonnet 5.5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
univer-cli 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 2mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Univer CLI
Terminal-native authoring and inspection for multi-Unit .univer files. The CLI provides isolated
worktrees, version-matched Facade guidance, model readback, and browser review.
Install:
npm install -g univer-cli
univer doctor
Keep the CLI current
Use these commands to compare the installed CLI with the latest public release:
univer --version
npm view univer-cli@latest version --registry=https://registry.npmjs.org/
When a newer version is available, complete the current Univer task before updating:
univer update
univer doctor --json
univer skills get core
If univer update reports that the shared daemon must stop, rerun it with --force after confirming
that stopping the daemon is safe. Reload core and the target Unit Skill after every update.
Start here
This file is the discovery entry, not the operational guide. Before using Univer commands for a task, load the complete core Skill from the installed CLI:
univer skills get core # shared model, workflow, evidence, and handoff
univer skills get core --full # include direct references and templates
Runtime Skills ship with the CLI so their commands and Facade APIs match the installed version.
Core Model
- A
.univerpath is the authoritative multi-Unit target. Always address the file explicitly. - A Unit is a top-level Sheet, Doc, Slide, Base, or Board identified by
unitId; sheet names, pages, tables, ranges, shapes, and records live inside that Unit. trunkis the reviewed main line. A worktree is an isolated scope for agent changes; there is no implicit current worktree.- Command success is not correctness evidence. Read back the target model, verify task-specific assertions, and inspect rendered output when appearance matters.
Use public CLI and Facade surfaces. The worktree commit path is the durable write boundary, and merge remains an explicit review decision.
Unit Skills
After core, load the Skill matching the target top-level Unit before authoring:
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.
- 2mo ago First seen · 126 lines · 57 tokens per session scan A e5357bb0512d
univer-cli is a skill published in the GitHub repository dream-num/skills (79 stars, last pushed 19d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,026 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
genoffice
Create, convert, read and edit Office documents locally with GenOffice's command line. Build a new presentation (pptx) from a brief through a checked outline, per-page spec and render pipeline, a new spreadsheet (xlsx) from CSV or JSON data with formulas, a new Word document (docx) from Markdown or HTML, or a PDF…
budget-planner
Turn a business plan into an annual or project budget with account lines, monthly spread, summaries and a separate assumptions sheet, delivered as an Excel workbook.
expense-report
Turn a pile of receipts into an expense claim summary that flags missing receipts, over-limit items and duplicates, delivered as an Excel workbook.
data-cleaning
Define cleaning rules, then deduplicate and standardise dirty data into a clean table with a line-by-line cleaning log, delivered as an Excel workbook.
kpi-dashboard
Turn operating data into a KPI dashboard workbook with metric definitions, target vs actual, attainment rates and trend charts, delivered as an Excel workbook.
survey-analyst
Clean raw survey responses, run cross-tabulations and charts, and produce an analysis workbook plus a findings report, delivered as an Excel workbook and a Word document.