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 agentlas-ai/agentlas-desktop --skill sheetgit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/sheet)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/sheet"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/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/agentlas-ai/agentlas-desktop/sheet"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/sheet.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 | $0.00029 | $0.00484 |
| Opus 5.5 | $0.00012 | $0.00194 |
| Sonnet 5.5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
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 2d 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.
What it actually says
Steps
harness_call {"operation":"document.list"}: reuse an open session. Otherwise callharness_call {"operation":"document.open","args":{"path":"<absolute path>"}}, ordocument.createwith a new.xlsxpath.- The
outlinelists# sheet <name>, thenA1<TAB>valuelines. Formulas appear as=SUM(B2:B3), followed by the cached value. A{…}tag shows the cell's format. - Edit with
document.applyusingsessionIdandops. Write a row or a block at a time. - Save with
document.save. - To check how a sheet looks, call
harness_call {"operation":"document.render","args":{"sessionId":"…"}}. It returns up to 4 sheets' used ranges as images, as the workbook is now (saved or not). When the reply hasnext, call again with itsfromuntil every sheet has been seen.
Ops
{"op":"set_cell","sheet":"Sales","cell":"B4","value":"=SUM(B2:B3)"}writes a cell. A leading=makes a formula, and an empty string clears the cell. Numbers go as plain digits, for example1250.{"op":"add_sheet","name":"Summary"}{"op":"set_format","target":"Sales!A1","format":{"bold":true,"align":"center","color":"#1c7ed6","size":12,"fill":"#ddebf7"}}.fillis the cell background.
Notes
- The cell keeps its number format (percent, thousands, dates) when only its value changes.
- Formulas compute as you write them: the outline shows each result in parentheses after the formula (
=SUMIFS(…) (1500)), so check results there. A function the tab does not know keeps its formula text until Excel opens the file; the save stores computed values for the rest. - On
revision_conflict, calldocument.readand apply again.
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.
- 2d ago Changed 50a62939192e
- 3d ago Changed · +1 lines 092735cbccaa
- 4d ago First seen · 24 lines · 29 tokens per session scan A 6641d391ff83
sheet is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 484 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 2026-10-18.
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.
feishu-bitable
A skill for managing Feishu Bitable, a database-like spreadsheet for organising structured records. It supports tables, fields, views, filters, and bulk changes.
excel-ai-analyst
A method for reverse-engineering business Excel files that contain formulas. It treats columns as named values, formulas as calculations, and links between sheets as data paths.
Google Workspace integration — Gmail, Drive, Calendar, Contacts, Tasks, and Sheets via gogcli.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…