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 components-kit/open-workbook --skill open-workbook-skillsgit clone --depth 1 https://github.com/components-kit/open-workbookWrote 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/components-kit/open-workbook/open-workbook-skills)<a href="https://agentmods.dev/skills/components-kit/open-workbook/open-workbook-skills"><img src="https://agentmods.dev/badge/skills/components-kit/open-workbook/open-workbook-skills/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/components-kit/open-workbook/open-workbook-skills"><img src="https://agentmods.dev/badge/skills/components-kit/open-workbook/open-workbook-skills.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 | $0.00074 | $0.05455 |
| Opus 5.5 | $0.00030 | $0.02182 |
| Sonnet 5.5 | $0.00015 | $0.01091 |
| Haiku 4.5 | $0.00007 | $0.00545 |
Grade B, and why
open-workbook-skills scanned grade B with 2 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Never tell the user you cannot detect the selected row/cell/range before calling `excel.agent.run`. The model cannot see Excel selection by itself, but Open Workbook can read it through the connected add-in. If the user Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`excel://...` result handles returned by Open Workbook are internal MCP/Open Workbook handles, not web URLs. Never use Webfetch, browser fetch, curl, or HTTP tooling for `resultUri`, `fullResultUri`, or `resourceLinks`. How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Workbook Skills
Use Open Workbook MCP for live desktop Excel work. It is the required first path when the workbook is open in Excel and the user expects current cell values, unsaved edits, formatting, formulas, filters, tables, pivots, charts, snapshots, backups, transaction history, and rollback safety to survive.
Do not inspect or modify a connected live workbook with shell scripts, Python, openpyxl, pandas, manual UI automation, or offline .xlsx parsing unless the user explicitly asks for offline file analysis or the MCP path is unavailable and the user approves the fallback. For workbook/worksheet "look at", "inspect", "review", or "what is this" requests, do not run ls, stat, Python, or offline file checks as a preflight; call excel.agent.run first. If Open Workbook is connected but returns an empty live-read diagnostic or cannot_complete, report that Open Workbook live-read failure instead of switching to saved-file parsing.
Public Surface
Normal agents call one tool:
excel.agent.run
Use modes deliberately:
status: check Excel/add-in readiness and shared-agent coordination.prepare: cache workbook identity, sheet/table/name/region metadata, and collaboration state.find: locate candidate sheets, tables, headers, named ranges, regions, formulas, and summary blocks.answer: targeted live reads, schemas, summaries, comparisons, and deterministic inspection.preview_update: preview mutations and get anoperationIdplusconfirmationTokenwhen review is required.apply_update: apply only a previewed operation with the returned token.operation_status: check a returned operation without reissuing preview/apply.cancel_operation: cancel a pending preview before apply starts.validate: validate workbook, sheet, table, formula, style, filter, print-layout, or unintended-change scope.rollback: inspect or apply recovery through returned transaction, snapshot, or backup guidance.auto: default route for casual prompts and small explicit value edits; safe narrow edits may apply in one call after workbook write access is allowed for the session unlessautoApply: false.
What ships with it
7 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 First seen · 147 lines · 74 tokens per session scan B db04b1c2eb59
open-workbook-skills is a skill published in the GitHub repository components-kit/open-workbook (4 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 5,455 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (subtle steering, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.