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

A test execution guide for the project's .NET test suites. It separates fast business-logic tests from diagnostic, VBA, screenshot, and session or batch infrastructure tests, which have different requirements and run times.

In plain words
What is it for?
Use it when validating slide features, session and batch changes, VBA behavior, screenshots, diagnostics, or other targeted changes.
Why use it?
It helps developers run the relevant tests without accidentally running every test project or triggering tests that need special PowerPoint, VBA, or clipboard setup.

Instructions file for GitHub Copilot

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/trsdn/mcp-server-ppt/testing-strategy
Clone the repo
git clone --depth 1 https://github.com/trsdn/mcp-server-ppt

Made for: GitHub Copilot.

Per session 1,734 This file is loaded in full into every session.
When invoked 1,734 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.01734 $0.01734
Opus 5 $0.00867 $0.00867
Sonnet 5 $0.00347 $0.00347
Haiku 4.5 $0.00173 $0.00173

Measured 3d ago against content hash 8c1cbca5798f, 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-ppt testing-strategy.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/testing-strategy.instructions.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing Strategy - Quick Reference

Test Execution

⚠️ CRITICAL: Always specify the test project explicitly to avoid running all test projects!

Core.Tests (Business Logic)

# Development (fast - excludes VBA and Screenshot)
dotnet test tests/PptMcp.Core.Tests/PptMcp.Core.Tests.csproj --filter "Category=Integration&RunType!=OnDemand&Feature!=VBA&Feature!=VBATrust&Feature!=Screenshot"

# Diagnostic tests (validate patterns, slow ~20s each)
dotnet test tests/PptMcp.Diagnostics.Tests/PptMcp.Diagnostics.Tests.csproj --filter "RunType=OnDemand&Layer=Diagnostics"

# VBA tests (manual only - requires VBA trust)
dotnet test tests/PptMcp.Core.Tests/PptMcp.Core.Tests.csproj --filter "(Feature=VBA|Feature=VBATrust)&RunType!=OnDemand"

# Screenshot tests (isolated run only - clipboard contention when parallel)
dotnet test tests/PptMcp.Core.Tests/PptMcp.Core.Tests.csproj --filter "Feature=Screenshot"

# Specific feature
dotnet test tests/PptMcp.Core.Tests/PptMcp.Core.Tests.csproj --filter "Feature=Slide"

ComInterop.Tests (Session/Batch Infrastructure)

# Session/batch changes (MANDATORY - see CRITICAL-RULES.md Rule 3)
dotnet test tests/PptMcp.ComInterop.Tests/PptMcp.ComInterop.Tests.csproj --filter "RunType=OnDemand"

McpServer.Tests (End-to-End Tool Tests)

# All MCP tool tests
dotnet test tests/PptMcp.McpServer.Tests/PptMcp.McpServer.Tests.csproj

# Specific tool
dotnet test tests/PptMcp.McpServer.Tests/PptMcp.McpServer.Tests.csproj --filter "FullyQualifiedName~SlideTool"

CLI.Tests (Command-Line Interface)

# All CLI tests
dotnet test tests/PptMcp.CLI.Tests/PptMcp.CLI.Tests.csproj

# Specific command
dotnet test tests/PptMcp.CLI.Tests/PptMcp.CLI.Tests.csproj --filter "FullyQualifiedName~Slide"

Run Specific Test by Name

# Use full project path + filter
dotnet test tests/PptMcp.Core.Tests/PptMcp.Core.Tests.csproj --filter "FullyQualifiedName~TestMethodName"

Round-Trip Validation Pattern

Read the full file on GitHub · 203 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. 3d ago First seen · 203 lines · 1,734 tokens per session scan A 8c1cbca5798f

Subscribe to this mod's changes

mcp-server-ppt testing-strategy.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed 8d ago), licensed MIT. It adds 1,734 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories