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/mcp-server-guidegit 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/mcp-server-guide)<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/mcp-server-guide"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/mcp-server-guide.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 | $0.03384 | $0.03384 |
| Opus 5 | $0.01692 | $0.01692 |
| Sonnet 5 | $0.00677 | $0.00677 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade A, and why
mcp-server-ppt mcp-server-guide.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Development Guide
All action methods are synchronous. Tool signatures are
async Task<string>only to satisfy MCP SDK requirements, but action method implementations use NO async/await.
LLM-Facing Content Rules
NO EMOJIS in LLM-consumed content - Never use emoji characters in:
- Tool XML comments (
/// <summary>) - MCP SDK extracts these - MCP Prompt files (
Prompts/Content/*.mdandskills/shared/*.md) - Direct LLM consumption - Any code documentation consumed by LLMs
Use plain text markers: "IMPORTANT:", "WARNING:", "NOTE:", "CRITICAL:", "TIP:"
DO keep emojis in user-facing content: READMEs, FEATURES.md, user documentation, examples - humans appreciate visual aids.
Implementation Patterns
Action-Based Routing
[McpServerTool]
public async Task<string> PptSlide(string action, string pptPath, ...)
{
return action.ToLowerInvariant() switch
{
"list" => List(...), // Synchronous methods
"view" => View(...), // No await!
_ => ThrowUnknownAction(action, "list", "view", ...)
};
}
The file tool is hand-written — parity is NOT structural there
Every other MCP tool is generated from a Core interface marked [ServiceCategory], so
the CLI counterpart appears by construction and cannot drift. PptFileTool.cs is the
one exception, and its own header comment says so: "hand-coded because session
management is not generated."
That makes it the only tool where adding an action to MCP silently leaves the CLI behind
— and it is the bootstrap layer every workflow calls first. This already happened: test
shipped on MCP and never reached the CLI (#131), while the CLI README documented a
file test command that did not exist.
When you touch PptFileAction:
- Add the matching command in
src/PptMcp.CLI/Commands/SessionCommands.cs - Register it in the
sessionbranch insrc/PptMcp.CLI/Program.cs - Run
scripts\check-session-parity.ps1— it is a pre-commit gate and will fail otherwise
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.
- today Changed · +21 lines · +261 tokens per session c1d0634de20f
- 4d ago First seen · 364 lines · 3,123 tokens per session scan A b4afec52f38a
mcp-server-ppt mcp-server-guide.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed today), licensed MIT. It adds 3,384 tokens to every session, about $0.0169 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
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.
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.
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.
NeuroAPI AGENTS.md
Instructions for neurogen-dev/NeuroAPI, a project described as: NeuroAPI: российский AI API для Codex CLI и Claude Code — безопасные one-click установщики для Windows и macOS.
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.