What is openuser CLAUDE.md?

Project instructions for OpenUser, a system for creating AI avatars with personal voices, images, and videos, plus plugins, scheduled tasks, and service integrations.

Use them when modifying OpenUser's Python services, avatar engine, plugin and agent systems, integrations, scheduler, or configuration.

They explain the project structure and rules, including its expectation that plugins, skills, prompts, and settings can reload without restarting.

openuser CLAUDE.md — Instructions file by yxhpy

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/yxhpy/openuser/claude-md

Clone the repo

git clone --depth 1 https://github.com/yxhpy/openuser

Per session 2,127 This file is loaded in full into every session.

When invoked 2,127 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	$0.02127	$0.02127
Opus 5	$0.01064	$0.01064
Sonnet 5	$0.00425	$0.00425
Haiku 4.5	$0.00213	$0.00213

Measured 2d ago against content hash a091960babfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openuser 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 2d 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 · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 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 when working with the OpenUser project.

Project Overview

OpenUser is an intelligent digital human system that enables users to create personalized AI avatars with their own voice, images, and videos. The system features hot-reloadable plugins, skills, scheduled tasks, and multi-platform integrations.

Core Components:

Digital Human Engine - Custom solution integrating Wav2Lip, GFPGAN, SadTalker
Plugin System - Hot-reloadable plugins with auto-installation
Agent System - Self-updating AI agents with parameterized environments
Integration Layer - Feishu, WeChat Work, Web interface
Scheduler - Cron-based task automation

Tech Stack: Python 3.10+, FastAPI, SQLAlchemy, Redis, Celery

Core Principles

1. Hot Reload Everything

Plugins can be installed/updated without restart
Skills can be modified on-the-fly
System prompts are dynamically reloadable
Configuration changes apply immediately

2. Agent Self-Evolution

Agents can update themselves via prompts
Auto-install required plugins
Create custom plugins programmatically
All environments are parameterized

3. Maximum Extensibility

Plugin-based architecture
Event-driven design
API-first approach
Modular components

4. Documentation-Driven Development

All features documented in docs/modules/REGISTRY.md
API docs auto-generated from code
Known issues tracked in docs/troubleshooting/
Check registry before implementing new features

5. Test-Driven Development

100% test coverage required
Tests run automatically after code changes
Integration tests for all plugins
E2E tests for critical workflows

Architecture

Directory Structure

openuser/
├── .claude/                    # Claude Code extensions
│   ├── skills/                # Project-specific skills
│   ├── hooks/                 # Event hooks
│   ├── agents/                # AI agents
│   └── scripts/               # Helper scripts
├── src/
│   ├── core/                  # Core system
│   │   ├── plugin_manager.py # Plugin hot-reload
│   │   ├── agent_manager.py  # Agent lifecycle
│   │   └── config_manager.py # Dynamic config
│   ├── plugins/               # Plugin implementations
│   ├── agents/                # Agent definitions
│   ├── api/                   # FastAPI endpoints
│   ├── integrations/          # Platform integrations
│   │   ├── feishu/
│   │   └── wechat/
│   ├── models/                # Digital human models
│   └── utils/                 # Utilities
├── tests/                     # Test suites
├── docs/                      # Documentation
└── scripts/                   # Deployment scripts

Read the full file on GitHub · 307 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.

2d ago First seen · 307 lines · 2,127 tokens per session scan A a091960babfd

Subscribe to this mod's changes

openuser CLAUDE.md is an instructions file published in the GitHub repository yxhpy/openuser (2 stars, last pushed 7mo ago), licensed MIT. It adds 2,127 tokens to every session, about $0.0106 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.

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

openuser CLAUDE.md