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 Rockielab/rockie-claude --skill excelgit clone --depth 1 https://github.com/Rockielab/rockie-claudeWrote 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/rockielab/rockie-claude/excel)<a href="https://agentmods.dev/skills/rockielab/rockie-claude/excel"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/excel/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/rockielab/rockie-claude/excel"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-claude/excel.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 | $0.00026 | $0.01045 |
| Opus 5 | $0.00013 | $0.00522 |
| Sonnet 5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
excel 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- excel — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
excel
Use this skill when the user asks for an Excel workbook or an .xlsx
artifact, including creating, modifying, formatting, analyzing,
validating, or exporting workbook content. For read-only analysis or
validation requests, inspect the workbook and report findings without
writing a new file unless the user asks for one.
In tenant runtimes, new workbook generation is productized through
skills/excel/runtime/renderer.py. Generate the workbook locally in the
tenant workspace, verify it, then publish it with the emit_artifact
tool using:
kind: "spreadsheet"content_encoding: "base64"filename: "<safe-name>.xlsx"mime_type: "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"destinations: ["ui", "chat"]
Core rules
- Produce a real
.xlsxworkbook. Do not rename CSV, TSV, HTML, JSON, or plain text files to.xlsx. - Use
runtime/sanitize.pyat the cell-write boundary. Strings starting with=,+,-, or@are text unless the cell is explicitly typed as a formula. - Preserve source data. Keep raw inputs available when appropriate,
such as a
Source DataorRaw Datasheet, and avoid silently replacing user-provided values with summaries. - Use workbook features that fit the task: multiple sheets, formulas, number formats, styles, column widths, freeze panes, filters, charts, data validation, named ranges, and notes/comments when they materially improve usability.
- Keep formulas as formulas unless the user explicitly asks for static values.
- When writing a workbook, reopen and verify the finished file before reporting it.
- When writing a workbook, report the emitted artifact id or final path.
- Cap new workbook generation at 20 sheets. If the user asks for more, create the most useful 20 or fail clearly before writing, depending on the task.
Verification
After writing the .xlsx, reopen it with an Excel-capable parser or by
inspecting the ZIP/XML package when no dependency is available. Verify:
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.
- 10d ago First seen · 133 lines · 26 tokens per session scan A bb1456f51b38
excel is a skill published in the GitHub repository Rockielab/rockie-claude (21 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,045 once invoked, about $0.0001 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
excel-author
Build auditable financial workbooks headless via openpyxl.
xlsx
Create, read, edit Excel .xlsx workbooks and CSVs.