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/ytthuan/powerpoint-python-pptx-mcp/agents-mdgit clone --depth 1 https://github.com/ytthuan/powerpoint-python-pptx-mcpWhat 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 | $0.00862 | $0.00862 |
| Opus 5 | $0.00431 | $0.00431 |
| Sonnet 5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
powerpoint-python-pptx-mcp AGENTS.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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Quick Reference - Development
📖 For using this MCP server in your AI agent, see docs/guides/AI_AGENT_GUIDE.md
📖 For GitHub Copilot Skills, see .github/skills/pptx-mcp-server/SKILL.md
What this repo is for
A PowerPoint MCP Server for automated PPTX processing, with a primary focus on speaker notes workflows (read/translate/summarize/update).
This file provides quick reference for developing the server.
Development Focus
When developing speaker notes features:
- Server-side processing: Implement tools for reading, validating, and updating notes
- Safe editing: Use zip-based editing to preserve animations and transitions
- Batch operations: Design for efficient multi-slide processing (50-100x faster)
- Validation: Ensure all inputs are validated and sanitized
- Error handling: Provide clear error messages and handle edge cases
Implementation Guidelines
Notes Format Structure
The server supports a two-version notes format:
- Short version:
[Brief summary - 30-50% of original length]
- Original:
[Full translation/explanation with all details]
When implementing validation or formatting features:
- Validate this structure exists when required
- Don't modify the format structure itself
- Support both structured and unstructured notes
Zip-based Editing Pattern
For notes updates, prefer zip-based editing over python-pptx write path:
import zipfile
from lxml import etree
def update_notes_zip(pptx_path: str, slide_number: int, notes_text: str):
"""Update notes using zip-based editing."""
with zipfile.ZipFile(pptx_path, 'r') as zip_in:
notes_path = f'ppt/notesSlides/notesSlide{slide_number}.xml'
# Read, modify XML, write back
# Only touch notesSlide*.xml files
Batch Operations Design
Design tools to support batch operations:
- Accept lists/ranges of slides in single request
- Process all operations before writing
- Make updates atomic (all or nothing)
- Provide progress tracking for large operations
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.
- yesterday First seen · 117 lines · 862 tokens per session scan A b0091dcabd36
powerpoint-python-pptx-mcp AGENTS.md is an instructions file published in the GitHub repository ytthuan/powerpoint-python-pptx-mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.