agentmods.dev

mcp-server-excel meta.instructions.md

Repository-wide instructions for maintaining guidance files in a project that automates Microsoft Excel through an MCP server or command-line tool. They explain where rules belong and how to keep them current and focused.

In plain words
What is it for?
Writing repository and path-specific guidance, excluding rules from code review when appropriate, checking instructions against the implementation, and removing obsolete or one-off advice.
Why use it?
They prevent duplicated, outdated, or overly broad instructions from confusing coding agents. They also require instructions to match the actual code and use normal repository paths and commands.

Instructions file for GitHub Copilot

645 3d ago A scan 211 tokens original MIT
View the source file sbroenne/mcp-server-excel
Install

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.

agentmods
npx agentmods add instructions/sbroenne/mcp-server-excel/meta
Clone the repo
git clone --depth 1 https://github.com/sbroenne/mcp-server-excel

Made for: GitHub Copilot.

Per session 211 This file is loaded in full into every session.
When invoked 211 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00211 $0.00211
Opus 5 $0.00105 $0.00105
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 3d ago against content hash 1e3fa939465b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-excel meta.instructions.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 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.

.github/instructions/meta.instructions.md · 22 lines

What it actually says

Maintaining Copilot instructions

  • Repository-wide guidance belongs in .github/copilot-instructions.md and should stay short, durable, and task-independent.
  • Path guidance uses NAME.instructions.md under .github/instructions with a quoted applyTo glob in YAML frontmatter.
  • Add excludeAgent: "code-review" to implementation guidance that should not influence review; the dedicated review file excludes cloud-agent.
  • Put a rule at the narrowest useful scope. Do not repeat it in repository-wide, critical, and feature files.
  • Describe the current architecture and commands. Remove incident history, obsolete tool names, dated counts, and one-off examples.
  • Use natural language and real repository paths. Do not prescribe a specific assistant's private tool names.
  • When implementation and instructions diverge, verify the code and update the stale instruction in the same change.
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. 3d ago First seen · 22 lines · 211 tokens per session scan A 1e3fa939465b

Subscribe to this mod's changes

mcp-server-excel meta.instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-server-excel (645 stars, last pushed 3d ago), licensed MIT. It adds 211 tokens to every session, about $0.0011 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.

DocumentsSpreadsheetsclaude-aiexcelexcel-automationgithub-copilotmcp-servermodel-context-protocol
Related

Other instructions, from other repositories

excel_mcp_server AGENTS.md

AGENTS.md instructions for urjeetpatel/excel_mcp_server, covering agents.md and agent documentation and test policy.

urjeetpatel/excel_mcp_server · 204 tokens

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).

ASH1998/excel-mcp · 951 tokens

apple-health-mcp AGENTS.md

Instructions for neiltron/apple-health-mcp, covering repository guidance, project, validate changes, code map and invariants.

neiltron/apple-health-mcp · 561 tokens

open-sheet AGENTS.md

Instructions for lianghsun/open-sheet, covering open-sheet — repository guide, repo layout, commands, the one invariant and core pipeline.

lianghsun/open-sheet · 1,070 tokens

mcp-ms-office-documents AGENTS.md

Instructions for ForLegalAI/mcp-ms-office-documents, covering agents.md, project overview, architecture, key conventions and filename generation.

ForLegalAI/mcp-ms-office-documents · 1,679 tokens

bilig bilig-workpaper.instructions.md

Instructions for proompteng/bilig, covering bilig workpaper formula proof, first checks, required readback, command safety and references.

proompteng/bilig · 677 tokens