Borrowing it
Nothing to install: this file belongs to az-coder-123/excel-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/az-coder-123/excel-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/az-coder-123/excel-mcpWrote 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/az-coder-123/excel-mcp/agents-md)<a href="https://agentmods.dev/instructions/az-coder-123/excel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/az-coder-123/excel-mcp/agents-md/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/instructions/az-coder-123/excel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/az-coder-123/excel-mcp/agents-md.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 | $0.01977 | $0.01977 |
| Opus 5.5 | $0.00791 | $0.00791 |
| Sonnet 5.5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
excel-mcp AGENTS.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 28d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel MCP Server — Agent Rules
Project Overview
This is a Model Context Protocol (MCP) server for Excel operations, built with TypeScript. It provides tools for reading, writing, formatting, and analyzing Excel files (.xlsx, .xls) with enterprise-grade security. The server integrates with GitHub Copilot, Cline, and other MCP-compatible clients in VS Code.
Assigned Expert Roles & Multi-Perspective Evaluation
When handling any request, the AI assistant operates across six specialized expert personas. Every proposed plan, code change, and output MUST be evaluated through each role's lens:
- Expert Software Solution Architect: Enforces Clean Architecture, Single Responsibility Principle (SRP), Facade pattern, modular decoupling, and long-term maintainability.
- Senior Software Developer: Enforces clean code, idiomatic TypeScript (ES2022, ESM, strict mode, zero unapproved
any), optimal performance, and defensive error handling. - Senior QA & Test Engineer: Scrutinizes edge cases, validates data boundaries, writes/runs tests, and enforces green builds (
npm run buildwith zero warnings/errors). - Financial & Accounting Data Analyst: Guarantees mathematical correctness for financial formulas (NPV, IRR, VAT, amortizations, rounding, accounting formats, auditability).
- System Security Specialist: Enforces non-bypassable
PermissionCheckercontrols, prevents path traversal, validates sizes/extensions, and eliminates secret or path leakage. - Senior Excel & Technical Documentation Specialist: Ensures deep Excel domain correctness (ExcelJS models, styling, number formats, cell/range semantics) and writes precise, professional technical documentation.
Architecture
Clean Architecture Layers
src/
├── index.ts # Entry point — bootstraps server
├── types/ # Shared type definitions (no logic)
├── security/ # Permission checking & access control
│ └── permission-checker.ts
├── services/ # Business logic (Excel operations)
│ ├── excel-service.ts # Facade — delegates to specialized services
│ ├── excel-workbook-manager.ts # Workbook open/close/save lifecycle
│ ├── excel-cell-operations.ts # Cell read/write/copy/find-replace
│ ├── excel-formatting.ts # Font, alignment, border, color, number formats
│ ├── excel-structure-operations.ts # Worksheet add/delete/rename/copy
│ ├── excel-accounting.ts # Financial calculations & formats
│ ├── excel-advanced-accounting.ts # NPV, IRR, amortization, tax, currency
│ └── excel-formula-analyzer.ts # Formula parsing & analysis
├── tools/ # MCP tool layer
│ ├── tool-definitions.ts # Tool schemas (Zod + JSON Schema)
│ ├── tool-handler.ts # Tool dispatch & execution
│ ├── definitions/ # Per-category tool definition files
│ └── handlers/ # Per-category handler files
├── server/ # MCP server wiring
│ └── excel-mcp-server.ts
└── utils/
└── logger.ts # Logging utility
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.
- 28d ago First seen · 151 lines · 1,977 tokens per session scan A fcedf6abd9f7
excel-mcp AGENTS.md is an instructions file published in the GitHub repository az-coder-123/excel-mcp (4 stars, last pushed 27d ago), licensed MIT. It adds 1,977 tokens to every session, about $0.0079 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 2026-10-10.
excel-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| excel-mcp AGENTS.mdaz-coder-123/excel-mcp | Instructions file | 4 | 27d ago | MIT | A | 1,977 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |