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 commands/proompteng/bilig/bilig-workpaper-proofgit clone --depth 1 https://github.com/proompteng/biligWrote 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/commands/proompteng/bilig/bilig-workpaper-proof)<a href="https://agentmods.dev/commands/proompteng/bilig/bilig-workpaper-proof"><img src="https://agentmods.dev/badge/commands/proompteng/bilig/bilig-workpaper-proof.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 | $0.00023 | $0.00573 |
| Opus 5 | $0.00012 | $0.00287 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
bilig-workpaper-proof 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.
What it actually says
Bilig WorkPaper Formula Check
Use this command when the task is workbook-shaped: pricing, quotes, payouts, budgets, import validation, forecasts, WorkPaper tools, workbook validation, or formula readback after changing cells.
User task:
$ARGUMENTS
Start with the smallest check that fits the task:
npm exec --yes --package @bilig/workpaper@latest -- bilig-evaluate --door agent-mcp --json
npm exec --yes --package @bilig/workpaper@latest -- bilig-evaluate --door agent-mcp --scenario provider-backed --json
npm exec --package @bilig/workpaper@latest -- bilig-agent-challenge --json
npm exec --package @bilig/workpaper@latest -- bilig-mcp-challenge --json
npm exec --package @bilig/workpaper@latest -- bilig-workpaper-mcp --workpaper ./.bilig/pricing.workpaper.json --init-demo-workpaper --writable
npm exec --package @bilig/workpaper@latest -- bilig-workpaper-mcp --from-xlsx ./pricing.xlsx
npm exec --package @bilig/workpaper@latest -- bilig-workpaper-mcp --from-xlsx ./pricing.xlsx --workpaper ./.bilig/pricing.workpaper.json --writable
Use the hosted stateless MCP endpoint only for tool discovery or smoke tests:
https://bilig.proompteng.ai/mcp
For private project state, use the local file-backed stdio server. Do not drive Excel, LibreOffice, Google Sheets, browser grids, or screenshots when WorkPaper JSON can be the source of truth.
Return readback, not a status sentence:
{
"editedCell": "Inputs!B3",
"before": {},
"after": {},
"afterRestore": {},
"persistedDocumentBytes": 0,
"verified": false,
"limitations": []
}
Rules:
- read the relevant input and dependent output before editing;
- write one small input or formula change;
- read the dependent calculated output after recalculation;
- export or serialize the WorkPaper document;
- restore or restart when file boundaries matter;
- report unsupported formulas or Excel-only behavior honestly;
- do not claim success from a write call alone.
Reference docs:
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 · 68 lines · 23 tokens per session scan A a2aebca5e431
bilig-workpaper-proof is a command published in the GitHub repository proompteng/bilig (35 stars, last pushed 11d ago), licensed MIT. It adds 23 tokens to every session and 573 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 commands, from other repositories
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
numbers-to-excel
Convert a Numbers document to Excel.
vizagent-dashboard
Build an offline HTML dashboard from the user's CSV/Excel data using the vizagent CLI. No database, server, or API key — the compiler is deterministic and reproducible.
batch-fill
Fill a form once per row of a CSV with Emboss.
convert-table
将 Excel 表格转为 CSV 或在对话中展示.