mcp-server-excel llm-testing-philosophy.instructions.md

mcp-server-excel llm-testing-philosophy.instructions.md is an instructions file for GitHub Copilot from sbroenne/mcp-server-excel. It costs 3,451 tokens per session, scanned A, original, MIT.

Testing guidance for AI agents that use command-line tools and MCP tools. It treats these tests as checks of whether real users can discover and use the product, rather than tests of the AI model itself.

In plain words
What is it for?
Use it to design and review AI-agent tests, diagnose failed workflows, and improve documentation, command help, tool descriptions, and recovery messages.
Why use it?
It helps teams trace failures to unclear instructions, tool descriptions, help text, errors, or parameter names instead of weakening the test.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

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/llm-testing-philosophy
Clone the repo
git clone --depth 1 https://github.com/sbroenne/mcp-server-excel

Made for: GitHub Copilot.

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 mcp-server-excel llm-testing-philosophy.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sbroenne/mcp-server-excel/llm-testing-philosophy.svg)](https://agentmods.dev/instructions/sbroenne/mcp-server-excel/llm-testing-philosophy)
Your own site
<a href="https://agentmods.dev/instructions/sbroenne/mcp-server-excel/llm-testing-philosophy"><img src="https://agentmods.dev/badge/instructions/sbroenne/mcp-server-excel/llm-testing-philosophy.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,451 This file is loaded in full into every session.
When invoked 3,451 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 5.1 $0.03451 $0.03451
Opus 5 $0.01725 $0.01725
Sonnet 5 $0.00690 $0.00690
Haiku 4.5 $0.00345 $0.00345

Measured 6d ago against content hash 59b92a5a2acd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-server-excel llm-testing-philosophy.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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/instructions/llm-testing-philosophy.instructions.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Testing Philosophy

⚠️ CORE PRINCIPLE: Tests simulate real users. Failures expose product gaps, not test gaps.

What Are LLM Tests?

LLM tests use an AI coding agent (with its own default system prompt) to exercise our CLI and MCP tools. The agent receives a natural language prompt — the same kind a real user would type — and must figure out how to accomplish the task using our tools.

These tests do NOT test the LLM. They test our product's usability surface:

  • Skill documentation (SKILL.md)
  • CLI --help output
  • MCP tool descriptions (XML /// <summary>)
  • Error messages and recovery hints
  • Parameter naming and discoverability
  • Workflow coherence

The Golden Rule

If the LLM can't figure it out, fix the product — never fix the test.

When an LLM test fails, the root cause is ALWAYS one of:

  1. Our skill docs don't explain the workflow clearly enough
  2. Our tool descriptions are misleading or incomplete
  3. Our CLI --help output doesn't show the right examples
  4. Our error messages don't guide recovery
  5. Our parameter names are confusing or undiscoverable
  6. The test itself is unreasonable (rare — only fix if a human couldn't do it either)

What NEVER Belongs in a Test

❌ xfail or skip Markers

NEVER use @pytest.mark.xfail or @pytest.mark.skip to hide failing tests.

Tests either pass or fail. There is no middle ground.

  • xfail masks real failures and creates a false sense of progress
  • skip hides broken code instead of fixing it
  • If a test fails, fix the product — the test is exposing a real problem (Golden Rule)
  • If a test is flaky, fix the flakiness — don't paper over it with xfail

❌ CLI Command Guidance in Prompts

A real user doesn't know our CLI syntax. Neither should the test prompt.

# ❌ WRONG: Teaching the LLM how to use our CLI
prompt = """
Create a PivotTable then set layout to Compact using 
'excelcli pivottablecalc' (run --help to see options).
The compact layout uses row-layout value 0.
"""

# ✅ CORRECT: Natural user request
prompt = """
Create a PivotTable with Compact layout showing
Department and Team as rows, Hours as values.
"""

Read the full file on GitHub · 381 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. 6d ago First seen · 381 lines · 3,451 tokens per session scan A 59b92a5a2acd

Subscribe to this mod's changes

mcp-server-excel llm-testing-philosophy.instructions.md is an instructions file published in the GitHub repository sbroenne/mcp-server-excel (656 stars, last pushed yesterday), licensed MIT. It adds 3,451 tokens to every session, about $0.0173 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.

Related

Other instructions, from other repositories

mcp-server-powerpoint copilot-instructions.md

Copilot instructions for sbroenne/mcp-server-powerpoint, covering project instructions — powerpointmcp, critical files (read these first), sister projects, what is powerpointmcp? and session model (mcp server).

sbroenne/mcp-server-powerpoint · 3,630 tokens

mcp-server-powerpoint mcp-server-guide.instructions.md

Instructions for sbroenne/mcp-server-powerpoint, covering mcp server development guide, llm-facing content rules, two kinds of tools: hand-written vs. generated, implementation pattern: single hand-written dispatch tool and error handling (mandatory).

sbroenne/mcp-server-powerpoint · 1,737 tokens

mcp-server-powerpoint architecture-patterns.instructions.md

Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).

sbroenne/mcp-server-powerpoint · 1,597 tokens

mcp-server-powerpoint critical-rules.instructions.md

Instructions for sbroenne/mcp-server-powerpoint, covering critical rules - must follow, rule 1: success/errormessage invariant, rule 1b: no exception suppression in core, rule 30: real-com integration tests only, strict tdd and rule: 1-based indexing everywhere.

sbroenne/mcp-server-powerpoint · 1,486 tokens

mcp-server-powerpoint testing-strategy.instructions.md

Instructions for sbroenne/mcp-server-powerpoint, covering testing strategy, strict tdd (red → green), test project layout, serialization is mandatory and trait tagging (required for surgical filtering).

sbroenne/mcp-server-powerpoint · 1,409 tokens

mcp-server-amazon CLAUDE.md

Instructions for rigwild/mcp-server-amazon, covering claude.md, development commands, install dependencies (use -d flag for puppeteer), build typescript to javascript and clean mock html files.

rigwild/mcp-server-amazon · 628 tokens