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/proompteng/bilig/workpapernpx skills add proompteng/bilig --skill 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 | $0.00029 | $0.02088 |
| Opus 5 | $0.00015 | $0.01044 |
| Sonnet 5 | $0.00006 | $0.00418 |
| Haiku 4.5 | $0.00003 | $0.00209 |
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 3d 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.
This is a copy
100% identical to bilig-workpaper — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilig WorkPaper Agent Skill
Use this skill when an agent needs spreadsheet-style formulas but the work should run through files, terminal commands, TypeScript, HTTP routes, or MCP tools instead of Excel UI automation.
When To Trigger
Trigger this skill for tasks involving:
- workbook-shaped business logic in Node.js services;
- formula readback after writing cells;
- quote, budget, payout, pricing, import-validation, or forecast models;
- agent spreadsheet tools that need deterministic cell addresses;
- MCP clients that can run a stdio server or call a Streamable HTTP endpoint;
- reduced formula/import bugs that need a local report.
Do not trigger it for manual spreadsheet editing, Office macros, VBA, pivots, charts, COM automation, or exact Excel desktop behavior unless the user explicitly asks to compare Bilig against an Excel oracle.
Command Safety
Do not build shell commands by concatenating user text. Treat the commands below as literal templates, validate workbook paths before use, and reject values containing newlines, backticks, $(, ;, &, |, <, or >. Prefer MCP client command plus args arrays or direct TypeScript calls when inserting user-provided paths or cell references.
First Check: Agent Triage
Before wiring a client or opening a spreadsheet UI, print the compact decision card:
{
"command": "npm",
"args": ["exec", "--yes", "--package", "@bilig/workpaper@latest", "--", "bilig-agent-start", "--json"]
}
First Check: Agent Evaluator
Before wiring a client, prove the published agent door with the package-owned evaluator.
It exercises MCP discovery, cell mutation, formula readback, JSON export, restart restore, and returns verified: true:
{
"command": "npm",
"args": ["exec", "--yes", "--package", "@bilig/workpaper@latest", "--", "bilig-evaluate", "--door", "agent-mcp", "--json"]
}
For service-owned WorkPaper logic without MCP, run bilig-evaluate --door workpaper-service --json.
Use the lower-level challenge commands only when debugging the direct API loop or file-backed MCP JSON-RPC transcript:
What ships with it
29 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.
- AGENTS.md 5.7 KB
- bin/bilig-agent-challenge.js 76 B runs code
- bin/bilig-agent-start.js 63 B runs code
- bin/bilig-evaluate.js 61 B runs code
- bin/bilig-formula-clinic.js 66 B runs code
- bin/bilig-mcp-challenge.js 65 B runs code
- bin/bilig-n8n-formula-server.js 71 B runs code
- bin/bilig-workpaper-mcp.js 72 B runs code
- LICENSE 1.0 KB
- package.json 2.8 KB
- README.md 11 KB
- server.json 702 B
- src/__tests__/work-paper-mcp-xlsx-risk-tool.test.ts 3.6 KB runs code
- src/__tests__/workpaper-evaluator.test.ts 335 B runs code
- src/a1-facade.test.ts 832 B runs code
- src/agent-start-bin.ts 148 B runs code
- src/agent-workbook-challenge-bin.ts 172 B runs code
- src/ai-sdk.test.ts 2.4 KB runs code
- src/ai-sdk.ts 6.8 KB runs code
- src/evaluator-bin.ts 144 B runs code
- src/evaluator.ts 328 B runs code
- src/formula-clinic-bin.ts 207 B runs code
- src/index.ts 32 B runs code
- src/mcp-challenge-bin.ts 152 B runs code
- src/mcp.ts 36 B runs code
- src/n8n-forecast-server-bin.ts 182 B runs code
- src/work-paper-mcp-stdio-bin.ts 1.5 KB runs code
- src/xlsx.ts 37 B runs code
- tsconfig.json 312 B
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.
- 3d ago First seen · 231 lines · 29 tokens per session scan A 1d02c3fd8fe3
bilig-workpaper is a skill published in the GitHub repository proompteng/bilig (35 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 2,088 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bilig-workpaper, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Assistant needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
xlsx
Create and edit Excel .xlsx workbooks (sheets, cells, formulas, formatting) via Python openpyxl. Use to generate spreadsheets or write/update cells. Reading is via os.fs.readdocument.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
excel-cli
Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges…
excel-mcp
Excel MCP Server skill for Windows workbook automation. Use when an assistant needs rich MCP tools to create, inspect, modify, format, or analyze Excel files. Supports Power Query (M), Data Model/DAX, PivotTables, Tables, Ranges, Charts, Slicers, formatting, screenshots, VBA macros, connections, and calculation mode.…