Borrowing it
Nothing to install: this file belongs to JoeSangAI/nano-banana-ppt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JoeSangAI/nano-banana-ppt/main/CLAUDE.mdgit clone --depth 1 https://github.com/JoeSangAI/nano-banana-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/joesangai/nano-banana-ppt/claude-md)<a href="https://agentmods.dev/instructions/joesangai/nano-banana-ppt/claude-md"><img src="https://agentmods.dev/badge/instructions/joesangai/nano-banana-ppt/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/joesangai/nano-banana-ppt/claude-md"><img src="https://agentmods.dev/badge/instructions/joesangai/nano-banana-ppt/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01418 | $0.01418 |
| Opus 5 | $0.00709 | $0.00709 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
nano-banana-ppt CLAUDE.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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Nano Banana PPT is a multi-agent pipeline that converts documents (Markdown, PDF, text) into professional PowerPoint presentations using Google Gemini (via OpenAI-compatible API). It is designed to be invoked as a Skill from AI agents (Cursor, Claude Code).
Environment Setup
Install dependencies:
pip install openai python-pptx pillow pymupdf requests python-dotenv matplotlib
Configure API keys in .env (auto-discovered at project root or ~/.cursor/skills/nano-banana-ppt/.env):
OPENAI_API_KEY=sk-...
OPENAI_API_BASE=https://your-proxy/v1
GOOGLE_API_KEY is also accepted as a fallback for OPENAI_API_KEY.
CLI Commands
The module must be invoked from the parent directory of nano-banana-ppt/ (i.e., the directory containing tools/), since main.py uses sys.path.insert to resolve tools.nano_banana_ppt.*.
# Phase 1a: Generate content outline (saves content_plan.md)
python3 -m tools.nano_banana_ppt.main plan-content <content_file> [template_file] [logo_file] [output_name] [--pages N]
# Phase 1b: Generate visual plan (saves visual_plan.md / master_plan.md)
python3 -m tools.nano_banana_ppt.main plan-visual <project_dir> [--style <style_name>]
# Phase 1 shortcut (runs both 1a + 1b):
python3 -m tools.nano_banana_ppt.main plan <content_file> [template_file] [logo_file] [output_name] [--style <style_name>] [--pages N]
# Optional: text-only prototype PPTX (no image generation)
python3 -m tools.nano_banana_ppt.main prototype <project_dir_or_plan_md> [output_name] [--slides 1 2]
# Phase 2: Generate images + assemble PPTX
python3 -m tools.nano_banana_ppt.main execute <project_dir_or_plan_md> [output_name] [--resolution 1K|2K|4K] [--slides 3 5 7]
# Upscale existing slides
python3 -m tools.nano_banana_ppt.main upscale <project_dir> [--resolution 4K] [--slides 1 3 5]
# Legacy one-shot (non-interactive)
python3 -m tools.nano_banana_ppt.main auto <content_file> [template_file] [logo_file] [output_name]
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.
- 12d ago First seen · 108 lines · 1,418 tokens per session scan A 5cc41a1d77fa
nano-banana-ppt CLAUDE.md is an instructions file published in the GitHub repository JoeSangAI/nano-banana-ppt (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,418 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 2026-08-31.
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).