ConnectOnion is an open-source, template-first toolkit for building, debugging, deploying, and operating AI agents. Developers use its command-line tools and Python runtime to create agents, add tools, connect services, deploy them, and make them callable by other agents, while the catalogue entries are related agents, skills, and instructions.
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/openonion/connectonion/claude-mdgit clone --depth 1 https://github.com/openonion/connectonionWrote 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/openonion/connectonion/claude-md)<a href="https://agentmods.dev/instructions/openonion/connectonion/claude-md"><img src="https://agentmods.dev/badge/instructions/openonion/connectonion/claude-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 | $0.05757 | $0.05757 |
| Opus 5 | $0.02878 | $0.02878 |
| Sonnet 5 | $0.01151 | $0.01151 |
| Haiku 4.5 | $0.00576 | $0.00576 |
Grade A, and why
connectonion 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 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 — 500 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
ConnectOnion is a Python framework for creating AI agents with automatic activity logging, interactive debugging, and multi-agent collaboration. Philosophy: "Keep simple things simple, make complicated things possible" - simple 2-line agent creation, but production-ready with trust verification, event system, and plugin architecture.
Architecture
Core Components
- Agent (
connectonion/core/agent.py): Main orchestrator with LLM integration, tool execution, event system, and trust verification - LLM (
connectonion/core/llm.py): Unified abstraction supporting OpenAI, Anthropic, Gemini, and managed keys via factory pattern - Tool Executor (
connectonion/core/tool_executor.py): Executes tools with xray context injection, timing, error handling, and trace recording - Tool Factory (
connectonion/core/tool_factory.py): Converts Python functions to OpenAI-compatible tool schemas automatically - Logger (
connectonion/logger.py): Unified logging facade (terminal + plain text + YAML sessions) withquietandlogparameters - Console (
connectonion/console.py): Low-level terminal output with Rich formatting (used internally by Logger) - Events (
connectonion/core/events.py): Lifecycle hooks (after_user_input, before_iteration, after_iteration, before_llm, after_llm, before_each_tool, before_tools, after_each_tool, after_tools, on_error, on_agent_ready, on_complete, on_stop_signal) - Trust System (
connectonion/network/trust/): Three-level verification (open/careful/strict) with custom policy support - XRay Debug (
connectonion/debug/xray.py): Runtime context injection for interactive debugging with@xraydecorator
Key Design Patterns
Tool System
- Function-based (recommended): Regular Python functions auto-convert to tools via type hints and docstrings
- Class-based (legacy): Inherit from
Toolbase class with explicit schemas - Auto-conversion:
create_tool_from_function()inspects signatures and generates OpenAI schemas
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 · 500 lines · 5,757 tokens per session scan A 6abbc3bcef15
connectonion CLAUDE.md is an instructions file published in the GitHub repository openonion/connectonion (1,481 stars, last pushed today), licensed Apache-2.0. It adds 5,757 tokens to every session, about $0.0288 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.
PPTAgent AGENTS.md
AGENTS.md instructions for icip-cas/PPTAgent, covering project and user background, purpose, ground truth, core philosophy and 1. good taste first.
agentfield AGENTS.md
AGENTS.md instructions for Agent-Field/agentfield, covering learned user preferences and learned workspace facts.
OpenContracts CLAUDE.md
Claude Code instructions for Open-Source-Legal/OpenContracts, covering claude.md, project overview, baseline commit rules, essential commands and backend (django).