opensquad_intro

opensquad_intro is a skill for Claude Code, Codex from opensquad-ai/opensquad. It costs 37 tokens per session (1,147 once invoked), scanned A, original, MIT.

An overview and navigation guide for OpenSquad, a framework where separate AI agents run as independent processes and collaborate through chats and workflows. It explains the system's services and documentation paths.

In plain words
What is it for?
Use it when learning the architecture, agent runtime, communication channels, gateway, launcher, or plugin and skill systems.
Why use it?
It gives newcomers a map of how OpenSquad is structured and where to find information about each feature.

Skill for Claude CodeCodex

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 skills/opensquad-ai/opensquad/opensquad_intro
Any agent
npx skills add opensquad-ai/opensquad --skill opensquad_intro
Clone the repo
git clone --depth 1 https://github.com/opensquad-ai/opensquad

Made for: Claude Code, Codex.

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.

agentmods badge for opensquad_intro

README.md
[![agentmods](https://agentmods.dev/badge/skills/opensquad-ai/opensquad/opensquad_intro.svg)](https://agentmods.dev/skills/opensquad-ai/opensquad/opensquad_intro)
Your own site
<a href="https://agentmods.dev/skills/opensquad-ai/opensquad/opensquad_intro"><img src="https://agentmods.dev/badge/skills/opensquad-ai/opensquad/opensquad_intro.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,147 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.01147
Opus 5 $0.00018 $0.00574
Sonnet 5 $0.00007 $0.00229
Haiku 4.5 $0.00004 $0.00115

Measured 4d ago against content hash a67e602e0a70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opensquad_intro 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 4d 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.

src/skills/opensquad_intro/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSquad System Overview

OpenSquad is a multi-agent framework. Each agent runs as an independent process with its own LLM connection, tool set, and session state. Agents communicate via natural language through ChatPro group chats, define structured collaboration workflows through Blueprints, and extend their capabilities through Plugin/Skill mechanisms.

               Telegram / Feishu / External API
                             |
                       Gateway (9555)
                      /      |      \
                 WebSocket  HTTP   Proxy
                 (realtime) (REST) (-> Launcher)
                     |       |        |
                Frontend  Backend   Launcher (9600)
                 (9530)   (FastAPI)   |
                                   Agent Process
                                  /    |    \
                              PM    Coder   QA
                            (8003) (8002) (8006)
                               \     |     /
                            ChatPro Group Chat

Feature Modules and Documentation Paths

Feature Module Key Content Documentation Path
System Architecture & Core Modules Agent Runtime, Session/Memory, Prompt placeholder architecture, built-in tool list, plugin loading mechanism, bootstrap flow doc_en/ARCHITECTURE.md
Multi-Agent Collaboration Blueprint workflows, Task Board, shared workspace workspace/collab/, PM monitoring protocol doc_en/COLLABORATION.md
Agent Management Directory structure, config fields, profile/memory layout, lifecycle, plugin/agent creation flow, collab cards doc_en/agent_management.md
MCP Dynamic Integration Add/remove/restart MCP servers at runtime without restarting the agent doc_cn/MCP_DYNAMIC_SETUP.md (Chinese only)
External Resource Download Conventions Landing path conventions when downloading Skills/MCPs/files from the internet; writing to root or framework directories is prohibited doc_cn/DOWNLOAD_CONVENTIONS.md (Chinese only)
Group Chat Integration Group chat architecture, configuration, and messaging flow doc_en/group_chat_agent.md

Read the full file on GitHub · 98 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.

  1. 4d ago First seen · 98 lines · 37 tokens per session scan A a67e602e0a70

Subscribe to this mod's changes

opensquad_intro is a skill published in the GitHub repository opensquad-ai/opensquad (5 stars, last pushed 21d ago), licensed MIT. It adds 37 tokens to every session and 1,147 once invoked, about $0.0002 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.