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 agentmods add skills/atomicbot-ai/atomic-agent/xlsxnpx skills add AtomicBot-ai/atomic-agent --skill xlsxgit clone --depth 1 https://github.com/AtomicBot-ai/atomic-agentWrote 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/atomicbot-ai/atomic-agent/xlsx)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/xlsx"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/xlsx.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.00898 |
| Opus 5 | $0.00022 | $0.00449 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
xlsx 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xlsx
Create and modify .xlsx workbooks with the openpyxl Python library.
Reading an existing spreadsheet to plain text is best done with the built-in
os.fs.read_document tool (no install). Use the scripts below to write:
new workbooks, cell values, formulas, and basic formatting.
The pattern is python3 -c "<inline script>" (or python3 script.py for longer
logic). Keep scripts short and idempotent; always write to a fresh output path.
Setup health check (run first, every session)
Verify with one solo step:
[{ "tool": "os.shell.run", "args": { "cmd": "python3", "args": ["-c", "import openpyxl; print(openpyxl.__version__)"] } }]
Outcome map:
exit 0+ version → ready, proceed.ModuleNotFoundError: openpyxl→ enter Setup playbook → "openpyxl missing".command not found: python3→ reply that Python 3 is required and stop.
Setup playbook (when prerequisites are missing)
openpyxl missing
Reply (solo reply step):
"The
openpyxllibrary is not installed. I can install it:python3 -m pip install --user openpyxl. Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "python3", "args": ["-m", "pip", "install", "--user", "openpyxl"] } }]
If pip is externally managed (PEP 668), use pipx run --spec openpyxl python or
a venv; ask the user which they prefer.
When to use
- "Create an Excel file with these rows", "build a budget spreadsheet".
- "Add a column / formula", "update cell B2", "add a second sheet".
- Generating reports/exports as
.xlsx.
When NOT to use
- Reading an
.xlsxto summarise — useos.fs.read_document. - CSV-only work — prefer plain
os.fs.writewith comma-separated text. - Charts / pivot tables / macros — out of scope on v1.
Common operations
Create a workbook with a header row and two data rows:
[{ "tool": "os.shell.run", "args": { "cmd": "python3", "args": ["-c", "import openpyxl; wb=openpyxl.Workbook(); ws=wb.active; ws.title='Report'; ws.append(['Name','Amount']); ws.append(['Coffee',4.5]); ws.append(['Tea',3]); ws['B4']='=SUM(B2:B3)'; wb.save('report.xlsx'); print('wrote report.xlsx')"] } }]
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.
- 4d ago First seen · 86 lines · 44 tokens per session scan A 88e8558f1911
xlsx is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (2,438 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 898 once invoked, about $0.0002 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
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
xlsx
Read and extract cell data from .xlsx Excel spreadsheets as TSV. Use when the user uploads or references an Excel file to read or summarize.
excel-spreadsheets
Create, modify, and manage Excel spreadsheets.
document-parsing
Extract readable Markdown from local Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and text-based PDF files using the preinstalled AnyDoc runtime.
data-analysis
Analyze Excel/CSV files with DuckDB SQL via bash.