A Claude agent that coordinates multi-step projects by maintaining purpose, plans, and research logs, ensuring steady progress without owning scope, budget, or decisions.
Coordinates project investigation as an Agent Teams teammate. Prevents getting lost in uncertain work by monitoring investigator, maintaining purpose.md alignment, and detecting loops/drift/dead ends. **Requires Agent Teams** (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS`). Designed as a teammate, not a standalone subagent. **Target scenarios:** - Bug investigation, performance debugging - New library/API exploration (docs vs reality gaps) - Environment setup issues - Work requiring multiple approach attempts - Tasks where you keep coming back to 'what was I doing?' **NOT for:** Predictable, low-risk tasks that existing agents handle well. <example> Context: Complex bug investigation via Agent Teams. assistant: [project-coordinator skill spawns Agent Team with coordinator and investigator] coordinator: [reads purpose.md, sends task to investigator, monitors progress] coordinator → investigator: "Stop. You've tested the same config path 3 times with minor variations. Check work_summary.md Dead Ends and try a different hypothesis." </example>
Handles uncertain, exploratory investigation tasks where the cause is unknown, multiple hypotheses exist, and careful methodology prevents wasted effort. Specializes in patient, systematic research. **Target scenarios:** - Bug investigation (unknown root cause) - Performance issues (unclear bottleneck) - 'It works on my machine' mysteries - Intermittent failures - Complex system behavior analysis **NOT for:** Known issues with clear solutions, simple debugging, predictable tasks. <example> Context: Uncertain issue requiring systematic investigation. user: "Tests randomly fail in CI but I can't reproduce locally" assistant: "This needs careful investigation without jumping to conclusions." [Assistant uses Task tool with subagent_type: "investigator"] <commentary> Uncertain investigation requiring systematic hypothesis testing, not hasty conclusions. </commentary> </example>
This skill should be used when the user asks to "manage this complex task", "track this project", "coordinate this work", "I keep losing track", "investigate this bug", "このタスクを管理して", "進捗を追跡して", "迷子になってきた", "このバグを調査して", or mentions project coordination, purpose tracking, or plan management. Provides orchestration for complex, uncertain tasks while maintaining focus on original objectives.
This skill should be used when the user asks to "clarify the goal", "what's the purpose", "why are we doing this", "extract the purpose", "目的を明確にして", "なぜこれをやるの", "ゴールは何", or mentions purpose clarification, goal alignment, or plan-purpose mismatch. Helps crystallize vague intentions into clear, actionable objectives.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
このリポジトリは、私個人が日常的に使っている Claude Code 用のエージェント/プラグインを公開しているものです。
主用途は 自分自身と自分の所属する環境で使うことですが、他の方が使うことを妨げる意図はありません。
自由に使ってください。
このリポジトリの内容は Apache License 2.0 のもとで公開されています。
詳細は LICENSE ファイルを参照してください。
このリポジトリは 個人利用を主目的としているため、
あらかじめご了承ください。
ただし、
ので、必要に応じて好きな形に育ててください。
理由はシンプルです。
そのため「共同開発前提」にはしていません。
一方で、
ことは歓迎しています。
Claude のモデルや公式エージェントは今後確実に進化していくと思っています。
このリポジトリのエージェントたちは、最終的には不要になる可能性が高いです。
それでも今これを作っている理由は、
現時点では、エージェントやプロジェクトが
「迷子にならないためのガードレール」がまだ足りない
と感じているからです。
そういったことを防ぐための 暫定的な補助輪として、このエージェント群を追加しています。
project-coordinator プラグインは Agent Teams に対応しています。
coordinator と investigator がチームメイトとして並行動作し、直接メッセージをやり取りできます。
Agent Teams は実験的機能のため、デフォルトでは無効です。
有効にするには settings.json に以下を追加してください:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
無効の場合は従来のサブエージェント方式にフォールバックします。
これは「完成されたフレームワーク」ではありません。
あくまで 今の自分にとって必要な道具です。
そのくらいの距離感で付き合ってもらえると嬉しいです。
This repository contains Claude Code agents and plugins that I primarily use for my own work.
While it is published publicly, its main purpose is personal use, not community-driven development.
Anyone is free to use it.
The contents of this repository are released under the Apache License, Version 2.0.
See the LICENSE file for full details.
This repository is not intended as a collaborative project.
Please understand this in advance.
However:
The reasons are simple:
That is why this is not run as a shared project.
At the same time, I welcome others who:
Claude models and official agents will almost certainly improve over time.
These agents may eventually become unnecessary.
They exist now because I believe:
At the moment, there are not enough guardrails to keep agents and projects from drifting.
Specifically:
These agents serve as temporary guardrails to prevent that.
The project-coordinator plugin supports Agent Teams.
The coordinator and investigator run as teammates, communicating directly via messages.
Agent Teams is experimental and disabled by default.
To enable, add the following to your settings.json:
{
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
When disabled, the plugin falls back to the traditional subagent approach.
This is not a polished framework.
It is simply a set of tools that are useful to me right now.
That is the intended relationship.
npx claudepluginhub suzuki0keiichi/claude-plugins-suzuki0keiichi --plugin project-coordinatorGenerate project-tailored AI review skills by collecting system-specific knowledge. Complements pr-review-toolkit with project-specific review perspectives.
Operate remote machines via SSH
Enforces alignment between all product decisions and the product’s declared concept, preventing vision erosion caused by convenience, politics, or technical shortcuts.
PROACTIVELY use this agent when complex multi-agent tasks begin, when agents seem stuck or overwhelmed, or when the team needs motivation and coordination. This agent serves as the elite performance coach for all other agents, ensuring they operate at their highest level while maintaining composure and excellence. Should be triggered automatically at the start of challenging projects or when detecting agent confusion. Examples:\n\n<example>\nContext: Starting a complex project requiring multiple agents\nuser: "We need to build a viral TikTok app in 2 weeks"\nassistant: "This is an ambitious goal that will require our A-team! Let me bring in the studio-coach to coordinate our agents and ensure everyone performs at their peak."\n<commentary>\nComplex projects benefit from having a coach to keep all agents aligned and motivated.\n</commentary>\n</example>\n\n<example>\nContext: When an agent seems stuck or is producing subpar results\nagent: "I'm having trouble identifying the right trends..."\nassistant: "Let me bring in the studio-coach to help refocus and elevate your approach."\n<commentary>\nAgents can get overwhelmed or lose focus - the coach helps them recenter and excel.\n</commentary>\n</example>\n\n<example>\nContext: Before launching a major sprint or initiative\nuser: "Tomorrow we start the 6-day sprint for our biggest project yet"\nassistant: "Time to rally the team! I'll have the studio-coach prepare everyone mentally and strategically for peak performance."\n<commentary>\nPre-sprint coaching ensures all agents start with clarity, confidence, and coordination.\n</commentary>\n</example>\n\n<example>\nContext: When celebrating wins or learning from failures\nuser: "Our app just hit #1 on the App Store!"\nassistant: "Incredible achievement! Let me bring in the studio-coach to celebrate with the team and capture what made this success possible."\n<commentary>\nThe coach helps institutionalize wins and extract learnings from both successes and failures.\n</commentary>\n</example>
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
AI Agent Team Operating System for Claude Code — persistent team management, meetings, task wall, company loop engine, and real-time dashboard
Intelligently compose and deploy Claude Code Agent Teams. Auto-selects optimal team composition from 24+ agents and 83+ skills across 5 scopes, generates task dependency graphs, and orchestrates multi-agent workflows with a single command.
Agent Teams スキルを設計・構築するためのベストプラクティスガイド。サブエージェント定義、SendMessage 通信プロトコル、タスク依存管理、PostToolUse Hook ログ、MCP ツール統合、コンテキストファイル設計を網羅。7つの実績あるチームスキルから抽出したパターン集
A structured orchestration system for Claude Code that plans, delegates, reviews, and learns. Includes coordinator, worker, and reviewer agents.