Changing slides, reading or updating speaker notes, translating or summarising notes, and running the project's tests, formatting, linting, and type checks.

They give the coding agent the project context, tools, setup commands, and checks needed to work safely with PowerPoint files.

powerpoint-python-pptx-mcp copilot-instructions.md

Q: What is powerpoint-python-pptx-mcp copilot-instructions.md?

Project instructions for a Python MCP server that reads and edits PowerPoint files. They cover presentation editing and processing speaker notes, including translation, summarisation, and batch updates.

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/ytthuan/powerpoint-python-pptx-mcp/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/ytthuan/powerpoint-python-pptx-mcp

Made for: GitHub Copilot.

Per session 2,650 This file is loaded in full into every session.

When invoked 2,650 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.

Model	Per session	Once invoked
Fable 5	$0.02650	$0.02650
Opus 5	$0.01325	$0.01325
Sonnet 5	$0.00530	$0.00530
Haiku 4.5	$0.00265	$0.00265

Measured yesterday against content hash 2da8ebd20983, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

powerpoint-python-pptx-mcp copilot-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 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.

.github/copilot-instructions.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions

Project context

This repository is a Model Context Protocol (MCP) server for PowerPoint (PPTX) file manipulation. It enables AI agents to interact with PowerPoint presentations through natural language commands, with a primary focus on automated speaker notes processing.

The project includes:

MCP server implementation for PPTX operations (read, edit, slide management)
Automated speaker notes processing (translation, summarization, batch updates)
Safe zip-based editing that preserves animations and transitions
Comprehensive validation, caching, and security features
Support for multi-language note processing (Vietnamese/English - configurable)

Primary audience: Developers building AI-powered presentation tools and content creators working with PowerPoint presentations.

Tech stack

Language: Python 3.11+ (strictly typed with mypy)
Core libraries:
- python-pptx for PPTX manipulation
- lxml for XML processing
- mcp for Model Context Protocol server
- Pillow for image handling
Testing: pytest, pytest-asyncio, pytest-cov
Code quality: black, isort, flake8, mypy, bandit, interrogate
Dependency management: pip, requirements.txt
Pre-commit hooks: Configured for automatic code quality checks

Build, test, and lint commands

Setup

python3 -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip3 install -r requirements.txt
pip3 install -e .

Running the server

python3 -m mcp_server.server

Testing

# Full test suite
python3 -m pytest tests/ -v

# Quick server test
python3 tests/integration/test_mcp_server.py --quick

# Specific feature tests
python3 -m pytest tests/integration/test_batch_operations.py
python3 -m pytest tests/integration/test_slide_visibility.py

# With coverage report
python3 -m pytest --cov=src/mcp_server --cov-report=html

Linting and formatting

# Format code
black src/ tests/ --line-length=100
isort src/ tests/ --profile black --line-length 100

# Lint
flake8 src/ tests/ --max-line-length=100 --extend-ignore=E203,W503

# Type checking
mypy src/ --strict --ignore-missing-imports

# Security checks
bandit -r src/ -c pyproject.toml

# Docstring coverage
interrogate src/ --config=pyproject.toml

# Run all pre-commit hooks
pre-commit run --all-files

Read the full file on GitHub · 327 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.

yesterday First seen · 327 lines · 2,650 tokens per session scan A 2da8ebd20983

Subscribe to this mod's changes

powerpoint-python-pptx-mcp copilot-instructions.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 2,650 tokens to every session, about $0.0132 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.

Code review Localization Testing

recharts AGENTS.md

Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.

recharts/recharts · 310 tokens