What is OperaGenerator CLAUDE.md?

Repository instructions for an AI system that creates complete multimedia operas using Java, language models, image generation and speech synthesis. They document the project's technology choices and important model details.

Maintaining or extending opera creation, scene writing, illustrations, narration, formatted libretti and generated reviews.

They give a coding agent the context needed to work with the project's Java features, AI services, image data and audio output correctly.

How kousen/OperaGenerator configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kousen/OperaGenerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kousen/OperaGenerator/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kousen/OperaGenerator

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kousen/operagenerator/claude-md.svg)](https://agentmods.dev/instructions/kousen/operagenerator/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kousen/operagenerator/claude-md"><img src="https://agentmods.dev/badge/instructions/kousen/operagenerator/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,428 This file is loaded in full into every session.

When invoked 2,428 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 5.1	$0.02428	$0.02428
Opus 5	$0.01214	$0.01214
Sonnet 5	$0.00486	$0.00486
Haiku 4.5	$0.00243	$0.00243

Measured 6d ago against content hash e1365fddfec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

OperaGenerator 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 6d 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.

CLAUDE.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Assistant Context

This document provides context for Claude when working on the Opera Generator project.

Project Overview

This is an AI-powered opera generation system built with Java 21 and LangChain4j 1.10.0. The system creates complete multimedia operas by:

Using GPT-5.2 and Claude Opus 4.5 to alternately write scenes
Generating illustrations with Google's Gemini Nano Banana (gemini-3-pro-image-preview)
Creating dramatic voice narration with ElevenLabs text-to-speech
Playing audio with JLayer for live demonstrations
Creating formatted libretti with embedded images and automatic stanza formatting
Generating critical reviews with Google Gemini 3 Pro

Key Technical Details

Java 21 Features Used

Virtual threads for concurrent image generation
Records for domain modeling (Opera and Scene)
Pattern matching in switch expressions
Text blocks for multi-line strings

Important Model Information

Gemini Nano Banana (gemini-3-pro-image-preview): Returns binary image data in response parts, requires GOOGLE_API_KEY and Pro account
Image generation: Uses Google GenAI SDK (com.google.genai:google-genai:1.36.0) with Client pattern
Rate limiting: Max 2 concurrent image requests with 1-second delays to avoid API throttling (configurable)
Chat Models: GPT-5.2 (OpenAI), Claude Opus 4.5 (Anthropic), Gemini 3 Pro/Flash (Google)
ElevenLabs: Uses HttpClient for API calls, streams audio directly to files
Voice IDs: Bella (narrator) and Antoni (critic) for different character voices

Project Structure

src/main/java/com/kousenit/
├── IntegratedOperaGenerator.java  # Main entry point
├── Opera.java                     # Domain model (Opera and Scene records)
├── Conversation.java              # AI scene generation logic
├── LibrettoWriter.java           # File output handling with automatic formatting
├── GeminiImageGenerator.java     # Image generation using Nano Banana with rate limiting
├── ImageSaver.java               # Handles base64 and URL image saving (legacy)
├── NarratorVoice.java            # ElevenLabs voice narration
├── AudioPlayer.java              # JLayer audio playback
├── AiModels.java                 # Model configurations
├── ApiKeys.java                  # Environment variable access
└── OperaCritic.java             # Generates critical reviews using Gemini

Read the full file on GitHub · 228 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.

6d ago First seen · 228 lines · 2,428 tokens per session scan A e1365fddfec0

Subscribe to this mod's changes

OperaGenerator CLAUDE.md is an instructions file published in the GitHub repository kousen/OperaGenerator (22 stars, last pushed 6mo ago), licensed MIT. It adds 2,428 tokens to every session, about $0.0121 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.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

OperaGenerator: Instructions file for Claude Code