excel-mcp: Instructions file for Codex

AGENTS.md

excel-mcp AGENTS.md is an instructions file for Codex, OpenCode from az-coder-123/excel-mcp. It costs 1,977 tokens per session, scanned A, original, MIT.

A set of project instructions for an Excel MCP server, a program that lets compatible coding tools work with Excel files. It describes the project structure, required coding practices, expert review roles, and checks for TypeScript changes.

In plain words
What is it for?
Use it when planning or implementing features for reading, writing, formatting, or analysing Excel files, and when checking builds, errors, edge cases, and design choices.
Why use it?
It gives an AI coding assistant consistent rules for changing the server, handling Excel-related code, and reviewing work from software, testing, and accounting perspectives.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: built for cline.

This is az-coder-123/excel-mcp's own configuration. It tells Codex and OpenCode how to work on excel-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything excel-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/az-coder-123/excel-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/az-coder-123/excel-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for excel-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/az-coder-123/excel-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/az-coder-123/excel-mcp/agents-md)
Your own site
<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.

agentmods 80×15 button for excel-mcp AGENTS.md

Your own site · 80×15
<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>
Per session 1,977 This file is loaded in full into every session.
When invoked 1,977 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 28d ago against content hash fcedf6abd9f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

AGENTS.md · 151 lines

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:

  1. Expert Software Solution Architect: Enforces Clean Architecture, Single Responsibility Principle (SRP), Facade pattern, modular decoupling, and long-term maintainability.
  2. Senior Software Developer: Enforces clean code, idiomatic TypeScript (ES2022, ESM, strict mode, zero unapproved any), optimal performance, and defensive error handling.
  3. Senior QA & Test Engineer: Scrutinizes edge cases, validates data boundaries, writes/runs tests, and enforces green builds (npm run build with zero warnings/errors).
  4. Financial & Accounting Data Analyst: Guarantees mathematical correctness for financial formulas (NPV, IRR, VAT, amortizations, rounding, accounting formats, auditability).
  5. System Security Specialist: Enforces non-bypassable PermissionChecker controls, prevents path traversal, validates sizes/extensions, and eliminates secret or path leakage.
  6. 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

Read the full file on GitHub · 151 lines

Changes

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.

  1. 28d ago First seen · 151 lines · 1,977 tokens per session scan A fcedf6abd9f7

Subscribe to this mod's changes

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.

Related

excel-mcp AGENTS.md compared with instructions from other repositories

excel-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
excel-mcp AGENTS.mdaz-coder-123/excel-mcpInstructions file427d agoMITA1,977Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode