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 sheet-authoringgit 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/sheet-authoring)<a href="https://agentmods.dev/skills/lianghsun/open-sheet/sheet-authoring"><img src="https://agentmods.dev/badge/skills/lianghsun/open-sheet/sheet-authoring.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02107 |
| Opus 5 | $0.00038 | $0.01053 |
| Sonnet 5 | $0.00015 | $0.00421 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
sheet-authoring 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 8d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring an open-sheet workbook
The one rule
Never write a cell address.
Not B5. Not SUM(B2:B13). Not $A$1. The framework assigns every coordinate
after it has laid the blocks out, and references resolve against that layout.
Writing an address by hand means writing a number that is correct only until
someone adds a row — and then it is silently wrong, which in a financial model is
worse than broken.
If you catch yourself counting rows to work out where something landed, stop. The thing you want is a reference.
The single exception is raw('...'), the deliberate escape hatch — see
references/formulas.md.
The file contract
// sheets/<id>/index.tsx
import { Sheet, Table, Workbook, col, sub, type SheetMeta } from '@open-sheet/core'
export const meta: SheetMeta = {
title: 'FY26 Budget', // shown in the viewer and used as the export name
description: 'One line.', // optional
theme: 'corporate-neutral', // optional; links back to themes/<id>.md
createdAt: '2026-08-18T00:00:00.000Z',
}
export const design: DesignSystem = { … } // optional; see the Design panel note
export default (
<Workbook>
<Sheet name="…">…</Sheet>
</Workbook>
)
The default export must be a <Workbook> containing <Sheet> children. meta
and design are plain object literals — the dev UI parses and rewrites them, and
a spread or an imported value makes the workbook untweakable.
Structure in JSX, data in TypeScript
JSX describes the report. Rows are plain arrays.
const quarters = [
{ quarter: 'Q1', revenue: 12_400_000, cogs: 5_100_000 },
{ quarter: 'Q2', revenue: 13_900_000, cogs: 5_600_000 },
]
<Table
name="pl"
data={quarters}
columns={[
col('quarter', { header: 'Quarter', width: 12 }),
col('revenue', { header: 'Revenue', format: 'currency' }),
col('grossProfit', {
header: 'Gross profit',
format: 'currency',
formula: (r) => sub(r.cell('revenue'), r.cell('cogs')),
}),
]}
total={{ revenue: 'sum', grossProfit: 'sum' }}
/>
What ships with it
6 files 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.
- 8d ago First seen · 194 lines · 76 tokens per session scan A db690cfd1ae5
sheet-authoring is a skill published in the GitHub repository lianghsun/open-sheet (122 stars, last pushed 12d ago), licensed MIT. It adds 76 tokens to every session and 2,107 once invoked, about $0.0004 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 2026-08-30.
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…
weekly-crm-report
Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.
publication-chart-skill
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants…
excel-cli
Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges…
excel-mcp
Excel MCP Server skill for Windows workbook automation. Use when an assistant needs rich MCP tools to create, inspect, modify, format, or analyze Excel files. Supports Power Query (M), Data Model/DAX, PivotTables, Tables, Ranges, Charts, Slicers, formatting, screenshots, VBA macros, connections, and calculation mode.…
calc-spreadsheets
Use when creating, opening, or editing LibreOffice Calc ODS spreadsheets, or XLSX workbooks only when Excel compatibility is explicitly required.