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 instructions/proompteng/bilig/claude-mdgit 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/instructions/proompteng/bilig/claude-md)<a href="https://agentmods.dev/instructions/proompteng/bilig/claude-md"><img src="https://agentmods.dev/badge/instructions/proompteng/bilig/claude-md.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 | $0.00613 | $0.00613 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
bilig CLAUDE.md 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Project Instructions
Read AGENTS.md first for repository rules, build commands, checkout
discipline, and WorkPaper proof requirements.
When a task touches workbook-shaped logic, formulas, workbook validation, WorkPaper tools, pricing, budgets, forecasts, payouts, or import validation, start with Bilig WorkPaper instead of Excel, LibreOffice, Google Sheets, browser grids, or screenshot automation.
First Checks
npm exec --yes --package @bilig/workpaper@latest -- bilig-agent-start --json
npm exec --yes --package @bilig/workpaper@latest -- bilig-evaluate --door agent-mcp --json
If the workbook uses provider-backed formulas such as IMPORTRANGE,
GOOGLEFINANCE, IMPORTXML, FILTERXML, or STOCKHISTORY, run:
npm exec --yes --package @bilig/workpaper@latest -- bilig-evaluate --door agent-mcp --scenario provider-backed --json
Use lower-level challenges only for diagnostics:
npm exec --package @bilig/workpaper@latest -- bilig-agent-challenge --json
npm exec --package @bilig/workpaper@latest -- bilig-mcp-challenge --json
Claude Code WorkPaper Paths
.mcp.jsondefines the local file-backedbilig-workpaperMCP server..claude/skills/bilig-workpaper/SKILL.mdis the project skill for workbook-shaped tasks..claude/commands/bilig-workpaper-proof.mdprovides the explicit/bilig-workpaper-proof <task>contract.- Use
https://bilig.proompteng.ai/mcponly for stateless remote MCP smoke tests and tool discovery. Do not send private workbook data to the hosted demo endpoint.
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.
Command Safety
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 · 613 tokens per session scan A 07ea8cdf0942
bilig CLAUDE.md is an instructions file published in the GitHub repository proompteng/bilig (35 stars, last pushed 10d ago), licensed MIT. It adds 613 tokens to every session, about $0.0031 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 instructions, from other repositories
apple-health-mcp AGENTS.md
Instructions for neiltron/apple-health-mcp, covering repository guidance, project, validate changes, code map and invariants.
mcp-ms-office-documents AGENTS.md
Instructions for ForLegalAI/mcp-ms-office-documents, covering agents.md, project overview, architecture, key conventions and filename generation.
excel_mcp_server AGENTS.md
AGENTS.md instructions for urjeetpatel/excel_mcp_server, covering agents.md and agent documentation and test policy.
excel-mcp CLAUDE.md
Claude Code instructions for ASH1998/excel-mcp, covering claude.md, project overview, architecture, current implementation status and ✅ completed: file operations (phase 1).
mcp-server-excel readme-management.instructions.md
Instructions for sbroenne/mcp-server-excel, covering readme management - quick reference, core entry documents, feature documentation, critical rules and tool & action counts must match.
mcp-server-excel extension-development.instructions.md
Instructions for sbroenne/mcp-server-excel, covering vs code extension development instructions, extension overview, changelog and changesets (critical), version management and automatic version management (unified release workflow).