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 PostOakLabs/ainumbers --skill excel-to-receiptgit clone --depth 1 https://github.com/PostOakLabs/ainumbersWrote 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/postoaklabs/ainumbers/excel-to-receipt)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/excel-to-receipt"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/excel-to-receipt/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/postoaklabs/ainumbers/excel-to-receipt"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/excel-to-receipt.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 | $0.00052 | $0.00529 |
| Opus 5.5 | $0.00021 | $0.00212 |
| Sonnet 5.5 | $0.00010 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
excel-to-receipt 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 15d 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
Excel to receipt
My numbers live in a workbook. Evaluate it deterministically, digest the range, and give the auditor a receipt.
Prompt
Take a spreadsheet out of email-and-trust and put it under a receipt.
- Export one workbook sheet to CSV. Use a synthetic copy if the sheet has real counterparty data.
- Call workbook_csv_parse. Record the parsed shape (rows, columns, types) and any cell that failed to parse.
- Call workbook_evaluate over the formula range. Record the computed values and the evaluation order the engine used.
- Call workbook_range_digest over the evaluated range. Record the digest; this is what the auditor will re-verify.
- Call workbook_roundtrip_verify to prove the evaluated workbook round-trips to the same digest. State pass/fail.
- build_evidence_pack over the parse, evaluate, and digest hashes.
- Give me the ledger link for the pack and the one command an auditor runs to recompute the digest from the same CSV.
- Write the note for your finance lead: which range is under receipt, the digest, and what the receipt does and does not claim (it covers the numbers as given, not the business judgment behind them). If a named tool is not in your tool list, call call_tool with { "name": "", "arguments": { … } }. It runs the same validation and returns the same receipt.
How to run
Connect an MCP-capable host to https://mcp.ainumbers.co/mcp, then give the prompt above to the assistant.
Use synthetic inputs only. Never paste personal or production data.
Verify what came back
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.
- 15d ago Changed ee86e268386c
- 19d ago First seen · 40 lines · 52 tokens per session scan A 8cf331a4bdad
excel-to-receipt is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 529 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
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.
excel-author
Build auditable financial workbooks headless via openpyxl.
lbo-model
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.