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 rules/proompteng/bilig/bilig-workpapergit clone --depth 1 https://github.com/proompteng/biligWhat 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 | $0.00026 | $0.00577 |
| Opus 5 | $0.00013 | $0.00289 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
bilig-workpaper 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 2d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilig WorkPaper Rule
Use this rule when a Cursor agent is about to automate spreadsheet-shaped logic: pricing, quote approvals, budgets, payout checks, import validation, forecasts, or agent tools that need formula readback.
Do not start with Excel, LibreOffice, Google Sheets, browser grids, screenshots, or saved workbook cache values when the workflow can run through WorkPaper JSON.
Fast Check Commands
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 ./pricing.workpaper.json --init-demo-workpaper --writable
Use bilig-evaluate --door agent-mcp as the adoption gate. Use the direct
challenge commands only when you need lower-level WorkPaper or MCP JSON-RPC
diagnostics.
Use the hosted stateless MCP smoke endpoint only for connector discovery:
https://bilig.proompteng.ai/mcp
Use the local file-backed stdio command when the agent must persist a project WorkPaper JSON file.
Required Readback
Before saying the workbook is updated, return readback with:
- edited sheet and A1 cell;
- before values for edited inputs and dependent outputs;
- after values read from the recalculated workbook;
- serialized or exported WorkPaper persistence evidence;
- restore or restart readback when files matter;
- unsupported formula or Excel-only limitations.
Do not claim success from a write call alone.
Safe Command Handling
Do not build shell commands by concatenating user text. Prefer MCP
command plus args arrays or direct TypeScript calls. Reject workbook
paths or cell arguments containing newlines, backticks, $(, ;, &,
|, <, or >.
References
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.
- 2d ago First seen · 65 lines · 26 tokens per session scan A 1fae69632900
bilig-workpaper is a cursor rule published in the GitHub repository proompteng/bilig (35 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 577 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 cursor rules, from other repositories
read-xlsx
Reading, writing, diffing, and repairing spreadsheets (.xlsx) for AI agents via the xfa MCP server.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.