PPTAgent is an agent framework for generating PowerPoint presentations, including free-form and template-based slide decks. It supports workflows such as research, visual design, asset creation, text-to-image generation, and exporting presentations to PPTX.
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/icip-cas/pptagent/agents-mdgit clone --depth 1 https://github.com/icip-cas/PPTAgentWrote 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/icip-cas/pptagent/agents-md)<a href="https://agentmods.dev/instructions/icip-cas/pptagent/agents-md"><img src="https://agentmods.dev/badge/instructions/icip-cas/pptagent/agents-md.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 | $0.01429 | $0.01429 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
PPTAgent 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project and User Background
Do not use plan mode unless user explicitly mentioned
Purpose
This repository contains an agentic PowerPoint generation system with two closely related codepaths:
deeppresenter/: the current runtime, CLI, multi-agent loop, MCP tool wiring, and HTML-to-PPTX pipeline.pptagent/: the earlier core generation and evaluation library, still shipped in the package and still used for the MCP server entrypointpptagent-mcp.
When making changes, treat deeppresenter as the primary product surface unless the task is explicitly about legacy pptagent generation internals or the MCP server.
Ground Truth
- Python package metadata and console entrypoints live in
pyproject.toml. - The main CLI command is
pptagent, which points todeeppresenter.cli:main. - The MCP server command is
pptagent-mcp, which points topptagent.mcp_server:main. - Default runtime workspaces are created under
~/.cache/deeppresenterunlessDEEPPRESENTER_WORKSPACE_BASEis set. - Configuration templates live at
deeppresenter/config.yaml.exampleanddeeppresenter/mcp.json.example.
Do not assume the root README.md is fully current. It still references paths like webui.py that are not present in this checkout. Prefer the code and pyproject.toml over prose docs when they conflict.
Core Philosophy
1. Good Taste First
"Sometimes you can look at a problem differently, restate it, and the special case disappears."
- Prefer restructuring the code so edge cases become ordinary cases.
- Good taste is mostly accumulated engineering judgment.
- Removing special-case branches is better than piling on conditionals.
2. Pragmatism Over Theory
"I am a pragmatic bastard."
- Solve the real problem in this repository, not a hypothetical one.
- Reject theoretically elegant but operationally heavy designs when simpler approaches work.
- Code serves reality, not paper architecture.
3. Simplicity As A Constraint
"If you need more than 3 levels of indentation, you're screwed and should fix your program."
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.
- 5d ago First seen · 123 lines · 1,429 tokens per session scan A 3e07ab7fa93a
PPTAgent AGENTS.md is an instructions file published in the GitHub repository icip-cas/PPTAgent (4,984 stars, last pushed 4d ago), licensed MIT. It adds 1,429 tokens to every session, about $0.0071 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 2026-08-30.
Other instructions, from other repositories
agentfield CLAUDE.md
Claude Code instructions for Agent-Field/agentfield, covering claude.md, project overview, development setup, prerequisites and initial setup.
ii-agent CLAUDE.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent project guide, project overview, architecture, domain structure and orm base & id conventions.
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
connectonion AGENTS.md
AGENTS.md instructions for openonion/connectonion, covering agents.md, project overview, architecture, core components and key design patterns.
connectonion CLAUDE.md
Claude Code instructions for openonion/connectonion, covering claude.md, project overview, architecture, core components and key design patterns.
agentfield AGENTS.md
AGENTS.md instructions for Agent-Field/agentfield, covering learned user preferences and learned workspace facts.