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 thewolffish/wolffish-app --skill spreadsheetgit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/spreadsheet)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/spreadsheet"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/spreadsheet/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/thewolffish/wolffish-app/spreadsheet"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/spreadsheet.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.03250 |
| Opus 5.5 | $0.00009 | $0.01300 |
| Sonnet 5.5 | $0.00005 | $0.00650 |
| Haiku 4.5 | $0.00002 | $0.00325 |
Grade A, and why
spreadsheet 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spreadsheet
Interface
- Tools:
spreadsheet_read,spreadsheet_create,spreadsheet_modify,spreadsheet_formula,spreadsheet_chart,spreadsheet_style,spreadsheet_convert,spreadsheet_analyze,spreadsheet_filter,spreadsheet_pivot - Supported formats: .xlsx, .csv, .tsv
- All complex parameters are passed as JSON strings.
- All paths must be absolute.
What makes a workbook good
These are the rules that decide whether a sheet is useful or merely produced. They hold unless the user says otherwise, or the file you are editing already does something else — an existing file's conventions beat every guideline here.
- Formulas, never computed constants. Write
=SUM(B2:B9), not the total you worked out yourself. A sheet whose numbers do not move when its inputs change is a screenshot, not a model. A cell value beginning with=is written as a formula byspreadsheet_createand byset_cell/set_range/insert_rows. - Ship zero formula errors. Every write recalculates and reports
#DIV/0!,#REF!,#VALUE!by address, plus anything that could not be evaluated. Fix what it names. If you think an error predates you, prove it by reading the original. - A clean recalculation proves the formulas evaluate, not that they are right. An
off-by-one range yields a clean file with wrong numbers. Write two or three
formulas first,
spreadsheet_readthem back, check the values are what you expect, and only then build out the grid. - Every assumption in its own labelled cell, referenced by the formulas that use
it —
=B5*(1+$B$6), never=B5*1.05. A rate buried inside a formula is a number nobody can find and nobody can change. - Formulas consistent across a row. One hand-edited cell in the middle of a projection is the commonest silent error in any model. Guard denominators that can be zero.
- Say where a number came from. A hardcoded figure gets a note in the adjacent cell or a real citation. When it came from the user, say so.
- A workbook someone will fill in needs a short legend naming the input cells and one example row in the expected format. Never add such a row to a file you were asked to edit.
- Follow the spec literally — exact sheet names, exact headers, the formula they spelled out. A redesign that computes something else fails however elegant it is.
- Charts last. See the
spreadsheet_chartnote: any other tool run afterwards rewrites the package and drops them.
What ships with it
2 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.
- 1mo ago Changed · +54 lines 6e5f63f00b84
- 1mo ago Changed · +1 lines f9c9977810b2
- 2mo ago First seen · 282 lines · 23 tokens per session scan A 99c23d1eb48e
spreadsheet is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 3,250 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
spreadsheet-authoring
Create and edit Excel spreadsheets (.xlsx) whose formulas carry their computed values, so sums and totals show in every viewer, plus date and time formats, recalculating and verifying an existing workbook.
browser4-web-miner
Groups similar web pages together and produces an interactive HTML report with clusters of related pages, plus Excel spreadsheets for analysis. Use when the user wants to cluster downloaded HTML files, convert detail web pages into interactive views, or analyze a folder of web pages locally.
xlsx
Create, inspect, edit, recalculate, validate, render, and deliver Excel workbooks while preserving formulas, formatting, drawings, links, macros, and metadata.
doc-ingest
Extract readable text from document files — PDF, XLSX/CSV/TSV, DOCX, PPTX, and plain-text formats — so any task that arrives with an attachment can actually consume it.
craft-data-visual
Turn data into a finished visual with ArtCraft apps - GridCraft workbook with a formula-error read-back, chart, VectorCraft/DesignCraft infographic, DeckCraft slide; verified and resumable. Use for "make a chart from this spreadsheet", "build an infographic from these numbers", "put the revenue chart on a slide".