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/trsdn/mcp-server-ppt/llm-testing-philosophygit clone --depth 1 https://github.com/trsdn/mcp-server-pptWrote 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/trsdn/mcp-server-ppt/llm-testing-philosophy)<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy.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 5.1 | $0.03434 | $0.03434 |
| Opus 5 | $0.01717 | $0.01717 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00343 | $0.00343 |
Grade A, and why
mcp-server-ppt 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.
This is a copy
89% identical to mcp-server-excel llm-testing-philosophy.instructions.md — 138 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 373 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
--helpoutput - 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:
- Our skill docs don't explain the workflow clearly enough
- Our tool descriptions are misleading or incomplete
- Our CLI --help output doesn't show the right examples
- Our error messages don't guide recovery
- Our parameter names are confusing or undiscoverable
- 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.
xfailmasks real failures and creates a false sense of progressskiphides 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 slide layout then set it to use a custom master using
'pptcli slidemaster' (run --help to see options).
The custom layout uses layout-type value 0.
"""
# ✅ CORRECT: Natural user request
prompt = """
Create a presentation with a custom slide layout showing
title and content areas.
"""
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.
- 6d ago First seen · 373 lines · 3,434 tokens per session scan A e4c02ad881d1
mcp-server-ppt llm-testing-philosophy.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed yesterday), licensed MIT. It adds 3,434 tokens to every session, about $0.0172 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to mcp-server-excel llm-testing-philosophy.instructions.md, differing in 138 lines, and is treated as a copy.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
mcp-dotnet-samples AGENTS.md
AGENTS.md instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa(必須), 互換性とパフォーマンス, 既知の制約(設計上の割り切り) and regionの活用.
nina AGENTS.md
AGENTS.md instructions for isbeorn/nina, covering agents.md, scope, documentation boundary, repository knowledge and code style and formatting.