By skyremote
Install a customised team of AI agents — a chief-of-staff orchestrator that routes to division leads and specialists — tailored to your own business, departments, or the people you manage. Works with Claude Code and Codex.
A customisable team of AI agents for Claude Code and Codex. Install a chief-of-staff orchestrator that triages your work and routes it to division leads and specialists — all scaffolded to fit your org through a short interview. No two installs look the same.

One team shape, instantiated to fit anyone:
chief-of-staff ← triages, routes, synthesises
┌───────────────┼───────────────┐
lead A lead B lead C ← one lead per "division"
└───────────────┼───────────────┘
(any lead pulls in any specialist)
architect · code-auditor · program-manager · problem-solver
presentation-writer · voice-scriptwriter · growth-marketer
product-designer · ops-steward ← 9 specialists
inbox-reader · email-writer · notes-archivist · memory-harvester ← 4 opt-in comms
A "division" is whatever unit you run: a business, a department, a team, a product line, a client portfolio, or a person you manage. You might have four companies; someone else has two departments and five reports. The installer learns your structure and generates one lead per division, then wires the chief-of-staff to route across exactly that team.
The value isn't the names — it's the operating doctrine baked into each agent: clean-brief delegation, explicit ownership boundaries, "work alone vs convene a council", generator-plus-reviewer pairing, and decisive synthesis instead of a menu of options.
You need Claude Code. Then it's about two minutes:
/plugin marketplace add skyremote/chief-of-staff-kit
/plugin install chief-of-staff-kit@skyremote
(Or run /plugin, choose Browse marketplaces, and install chief-of-staff-kit
from the menu.)install the crew. The installer interviews you (or reads your
existing CLAUDE.md), shows you a plan to approve, then writes your agents into your
project (.claude/agents/) or globally (~/.claude/agents/).@chief-of-staff for anything cross-cutting.git clone https://github.com/skyremote/chief-of-staff-kit
cp -r chief-of-staff-kit/skills/install-crew ~/.claude/skills/
Then ask Claude to install the crew.
The same personas render for Codex too: each
agent becomes an invokable prompt under ~/.codex/prompts/, plus a root AGENTS.md
that documents the team and the routing doctrine. Be aware of one honest limitation —
Codex has no auto-orchestrating subagent system, so in Codex you invoke the personas
manually; the content ports, the automatic delegation does not.
CLAUDE.md / AGENTS.md, the installer
proposes a draft org from it rather than interrogating you cold.README.Everything is plain Markdown. There's no build step — the "rendering" is the
installer model following skills/install-crew/SKILL.md.
.claude-plugin/ plugin + marketplace manifests
skills/install-crew/
SKILL.md the installer (interview → render → write)
templates/ the canonical agent personas (generic, placeholder-driven)
references/ how to render for Claude Code and Codex
assets/ README art
MIT. Use it, fork it, make it yours.
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.
npx claudepluginhub skyremote/chief-of-staff-kit --plugin chief-of-staff-kitAI Agent Team Operating System for Claude Code — persistent team management, meetings, task wall, company loop engine, and real-time dashboard
Multi-agent team orchestration for Claude Code. Set up parallel AI agent teams with file-based planning, progress tracking, and role-based collaboration.
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.
The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use, with six pre-defined team-architecture patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical Delegation). Claude Code용 팀 아키텍처 팩토리: 도메인 한 문장을 에이전트 팀과 스킬 세트로 변환하는 메타 스킬.
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>
AI team role and worker manager for multi-agent development workflows.