Kyoso — AI skill for Claude Code
Kyo-so (Kyoso / 協奏) is an MCP-native, ACP-powered multi-agent review gate for AI coding workflows.
How to install Kyoso
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open hokupod/kyoso and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Kyoso does
Kyo-so (Kyoso / 協奏) is an MCP-native, ACP-powered multi-agent review gate for AI coding workflows.
Alternatives in AI
- Fast Agent — Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support 3.7k ★
- Coding Agent Template — Multi-agent AI coding platform powered by Vercel Sandbox and AI Gateway 1.8k ★
- Loushang — AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool 1.3k ★
README
Kyo-so
[](https://deepwiki.com/hokupod/kyoso)
[English](README.md) | [日本語](README.ja.md) | [简体中文](README.zh-CN.md)
Kyo-so (Kyoso / 協奏) is an MCP-native, ACP-powered multi-agent review gate for AI coding workflows.
The Japanese word 協奏 translates to concerto in English: multiple independent players performing one coordinated piece.
It coordinates Codex and Claude reviewers for:
- implementation plan review
- security review with CISA Secure by Design gates
- diff review after implementation
Kyoso does not apply code changes.
Review Flow
All three review tools run the same pipeline: scan for secrets, snapshot the workspace read-only, run the reviewer ensemble in parallel over ACP, then aggregate findings, apply gates, and decide.
With a single backend enabled, one agent runs as `combined_reviewer` instead of the two-role ensemble (see [Single-backend mode](#single-backend-mode)). The Mermaid sources for this diagram live in [docs/assets/](docs/assets/).
Quick Start
No global install is required. Run Kyoso through `npx` or `bunx`. Running the packaged CLI requires Node.js 20 or newer.
Integration modes
| Mode | Installs | MCP | Clients |
|---|---|---|---|
| Marketplace Plugin | Skill plus local stdio MCP | Yes | Codex / Claude Code |
| CLI plus Skill-only | npm CLI plus Skill |
Related Skills
Satori
Self-learning loop for Claude Code — corrections and failures become skills, behind a human gate. MCP + hooks,
Codeseek
Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes
Lad MCP Server
Lad MCP Server: Autonomous code & system design review for AI coding agents (Claude Code, Cursor, Codex, etc.)
Agentic Engineering Protocol
Verification-driven operating protocol for AI coding agents - Explore/Plan/Implement/Verify/Deliver with adver
Apronagents
Multi-agent AI coding with a human merge gate — sandboxed git for agents, small reviewed diffs, your call on e
Airlock
Runtime firewall for AI coding agents. Gate every tool, MCP and skill call against a least-privilege policy.
Related Agents
Acp Client
The Agent Client Protocol standardizes how editors talk to coding agents, but each editor needs a client imple
Development Orchestrator Agent
Owns everything between contract lock and Gate 2 — branch verification, conditional shared-package-agent, para
Consult Agent
Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from
