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 lianghsun/open-sheet --skill create-sheetgit clone --depth 1 https://github.com/lianghsun/open-sheetWrote 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/lianghsun/open-sheet/create-sheet)<a href="https://agentmods.dev/skills/lianghsun/open-sheet/create-sheet"><img src="https://agentmods.dev/badge/skills/lianghsun/open-sheet/create-sheet/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/lianghsun/open-sheet/create-sheet"><img src="https://agentmods.dev/badge/skills/lianghsun/open-sheet/create-sheet.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 | $0.00112 | $0.01355 |
| Opus 5.5 | $0.00045 | $0.00542 |
| Sonnet 5.5 | $0.00022 | $0.00271 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
create-sheet 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a workbook in open-sheet
This skill owns the workflow. The technical reference — file contract,
components, references, formats — lives in the sheet-authoring skill. Read
it before writing code; do not duplicate its rules here.
You only write files under sheets/<id>/. Never modify package.json,
open-sheet.config.ts, or an existing workbook unless asked.
Step 0 — Pick a theme
List themes/. If any theme markdown exists, offer each theme id via
AskUserQuestion plus a final "no theme — design from scratch" option. If
the user picks one, read themes/<id>.md end to end, copy its palette and
components, and set meta.theme.
Step 1 — Get the numbers before anything else
A spreadsheet is judged entirely on whether its numbers are right. Before structure, before layout, establish:
- Purpose — what decision does this workbook support? A budget to approve, a forecast to argue with, a register to maintain?
- Audience — a CFO wants assumptions they can change; an analyst wants the working; an ops team wants a list they can filter.
- The data — where does it come from? Ask for the file, the query, the
figures. If the user has none yet, build the structure and leave explicit
TODO:markers.
Never invent a figure. Not a revenue number, not a growth rate, not a headcount, not a "typical industry" benchmark. A fabricated number in a spreadsheet is indistinguishable from a real one — it will be formatted, totalled, and charted exactly like the truth, and someone will make a decision on it. This matters more here than in a slide deck or a report.
If you need a placeholder to demonstrate structure, make it obviously fake (
0, or1with a<Note>saying so) and tell the user.
Step 2 — Clarify the shape (ask before writing code)
One AskUserQuestion call, skipping anything the user has already settled:
- Workbook type — propose three that fit this request, with what each
implies structurally:
- "our FY26 numbers" → driver model (assumptions sheet drives a P&L) · budget vs actual (variance columns and a data bar) · exec summary (one sheet, KPI band, no working shown)
- "track our vendors" → register (one row per vendor, filterable) · spend analysis (grouped totals, top-N) · scorecard (weighted criteria)
- Assumptions — which numbers should the reader be able to change? This is the question that decides whether the export is a model or a picture.
- Sheets — one sheet or several? Assumptions separate from calculations is the default and should only be collapsed for a genuinely trivial workbook.
- Output — is this opened in Excel (the usual case), printed as a report,
or read as a dashboard? It changes formats, widths, and whether to add a
--htmlpass.
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.
- 1mo ago First seen · 116 lines · 112 tokens per session scan A 5c66bae8c79d
create-sheet is a skill published in the GitHub repository lianghsun/open-sheet (127 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,355 once invoked, about $0.0004 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
excel-analyst-pro
Create or revise local Excel workbooks for DCF valuation, LBO returns, or budget-versus-actual variance analysis when the user explicitly requests a spreadsheet artifact. Use when evidence-backed finance models need reviewable formulas and checks. Trigger with explicit requests for a DCF, LBO, or variance workbook. Do…
excel-cli
Discover and launch the Excel CLI for ordinary Excel workbook requests on Windows, including reads, writes, formulas, data refreshes, and workbook automation. Use the installed excel-cli plugin's npx launcher and native help to find commands; report presentation conventions are a separate optional skill.
excel-cli-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through excelcli. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query or Data…
excel-mcp-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through Excel MCP tools. Use for readable headers, meaningful number formats, financial-model colours, and report layout. Do not load for ordinary reads, raw exports, targeted data updates, Power Query…
office-documents
Create, edit and convert Word, Excel, PowerPoint and PDF artifacts with format-aware verification. Use when producing docx, xlsx, pptx or PDF files; preserve templates and actual document structure, and render or recalculate before delivery.
calc-spreadsheets
Create, open or edit Calc spreadsheets: ODS default; XLSX for Excel compatibility.