convez.ai
Agente
advisely

claude-code-agents-team-nation-of-elites

advisely/claude-code-agents-team-nation-of-elites

Ver no GitHub
InicialPluginScore · de 0 a 100

Instalação

$npx convez-ai advisely/claude-code-agents-team-nation-of-elites

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
1
Acompanhando
0
Saúde
42%
Último commit
há 1 mês
Versão
v4.3.0
Issues abertas
0
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

Claude Code Agents - Team Nation of Elites

An orchestrated AI workforce that functions like a real-world company.

Supercharge your work with a complete, role-based AI team that takes projects from concept to production — and from lead to revenue.

Agents Divisions Skills SDK License Version Opus

Created by Yassine Boumiza

Quick Start | Agent Roster | Skills | Docs | Contributing


The Problem & The Solution

A single, generalist AI, no matter how powerful, lacks the specialized expertise and structured workflow of a real-world company. Complex projects require a team of specialists -- architects, managers, developers, testers, and security experts -- all working in concert.

The "Nation of Elites" is the solution. It's not just a collection of agents; it's a fully-realized, virtual IT organization. Each agent has a specific role, a clear mission, and defined responsibilities, mirroring the structure of a high-performing tech company.


Platform Compatibility

Agents are platform-independent .md files -- they work identically on Windows, Linux, macOS, and WSL2.

InterfaceSupportedConfig Path
Claude Code CLI (terminal)Yes~/.claude/agents/
VS Code + Claude Code extensionYes~/.claude/agents/
JetBrains + Claude Code extensionYes~/.claude/agents/

Quick Start

Get your AI workforce operational in under one minute.

Prerequisites

PlatformRequirement
WindowsGit for Windows
Linux / WSL2git, rsync
macOSgit (included with Xcode CLI tools)

Step 1: Install Claude Code

# npm (if Node.js is installed)
npm install -g @anthropic-ai/claude-code

# Or use the official installer
curl -fsSL https://claude.ai/install.sh | sh
# PowerShell (recommended)
irm https://claude.ai/install.ps1 | iex

# Or via WinGet
winget install Anthropic.ClaudeCode

Git for Windows is required. If using a portable Git, set:

$env:CLAUDE_CODE_GIT_BASH_PATH = "C:\Program Files\Git\bin\bash.exe"

Verify with claude doctor.

Step 2: Deploy the Agents

Automated Deployment (Recommended)

git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
cd claude-code-agents-team-nation-of-elites
bash scripts/deploy_agents.sh

Done! All 74 agents are now in ~/.claude/agents/ and ready to use.

WSL2 note: The path ~/.claude appears in Windows Explorer as \\wsl.localhost\Ubuntu\home\<USER>\.claude.

git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
cd claude-code-agents-team-nation-of-elites
powershell -ExecutionPolicy Bypass -File scripts\deploy_agents.ps1

Done! All 74 agents are now in %USERPROFILE%\.claude\agents\ and ready to use.

Plugin Installation (Alternative)

Nation of Elites is a third-party plugin, so you add its marketplace first, then install from it (two steps):

# 1. Register this repo as a marketplace
/plugin marketplace add advisely/claude-code-agents-team-nation-of-elites

# 2. Install the plugin from it
/plugin install nation-of-elites@nation-of-elites

All 74 agents become available as scoped subagents (e.g. nation-of-elites:03_Engineering_Division:backend-developer), plus the 33 skills.

To hack on the plugin locally without installing, load it straight from a clone:

git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
claude --plugin-dir ./claude-code-agents-team-nation-of-elites

Manual Installation

git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
cd claude-code-agents-team-nation-of-elites
mkdir -p ~/.claude && cp -r agents ~/.claude/agents
git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
cd claude-code-agents-team-nation-of-elites
New-Item -ItemType Directory -Force -Path "$env:USERPROFILE\.claude\agents" | Out-Null
Copy-Item -Recurse -Force agents\* "$env:USERPROFILE\.claude\agents\"

Using the Agents

cd my-project

# Strategic planning - auto-spawns project-sponsor, program-manager, product-manager
claude "Initialize a new e-commerce project. Define goals, roadmap, and tech stack."

# Development - spawns chief-operations-orchestrator and specialists
claude "Build user authentication with React frontend and Django REST API backend"

# Code review - spawns code-reviewer with Semgrep SAST
claude "Review the payment integration code for security and best practices"

# Deployment - spawns devops-engineer and cloud-architect
claude "Setup production infrastructure with CI/CD pipeline on AWS"

Complete Agent Roster by Department

Executive Office

AgentRole
project-sponsorStrategic vision, budget, ROI
program-managerPortfolio oversight, cross-project

Strategy & Planning

AgentRole
business-analystRequirements, gap analysis (opus)
functional-analystProcess modeling, specs (opus)
product-managerVision, roadmap, priorities (opus)
solution-architectTech architecture, stacks (opus)
ux-ui-architectUX research, interfaces

Project Management

AgentRole
project-manager-scrum-masterAgile delivery, sprints

Orchestration & Integration

AgentRole
chief-operations-orchestratorCentral coordinator
team-configuratorStack detection, setup
integration-specialistMCP, APIs, OAuth
AgentRoleModel
api-architectREST/GraphQL API designopus
graphql-architectSchemas, federation, subscriptionsopus
backend-developerServer-side APIs, business logicsonnet
frontend-developerUI frameworks, responsive designsonnet

Python & Web Frameworks

AgentSkills PreloadedModel
django-expertdjango-patternssonnet
laravel-expertlaravel-patternssonnet
rails-expertrails-patternssonnet

JavaScript & Frontend Frameworks

AgentSkills PreloadedModel
react-expertreact-patternssonnet
react-typescript-expertreact-patterns, typescript-patternssonnet
vue-expertvue-patternssonnet
nextjs-expertnextjs-patternssonnet

Backend Languages

AgentSkills PreloadedModel
java-expertjava-patternssonnet
go-expertgo-patternssonnet
rust-expert--sonnet

Data & Finance

AgentSkills PreloadedModel
database-expert--sonnet
financial-systems-expertfinancial-trading-patternssonnet
crypto-api-developercrypto-defi-patternssonnet

UI & Styling

AgentSkills PreloadedModel
tailwind-css-experttailwind-patternssonnet
antd-ui-developerantd-patternssonnet

CAD, BIM & Game Engines

AgentSkills PreloadedModel
unreal-engine-expert--sonnet
catia-design-expert--sonnet
autodesk-cloud-construction-expert--sonnet
revit-bim-expert--sonnet
AgentRoleMemory
code-reviewerSecurity-aware PR reviews (opus)project
code-archaeologistLegacy codebase analysis (opus)project
documentation-specialistREADMEs, API docs, guides (opus)--
performance-optimizerBottleneck diagnosis--
accessibility-specialistWCAG 2.1 AA/AAA--
noe-general-purposeVersatile multi-language--
noe-statusline-setupTerminal/shell config--
output-style-setupCLI output, ANSI colors--
AgentRoleSkills
qa-test-plannerTest strategy, case design--
qa-engineerAutomated suites, CI/CDpytest, semgrep, pipeline-quality
automated-test-scripterTest framework implementationpytest, semgrep
visual-regression-specialistUI consistency, visual defects--
AgentRoleMemory
cyber-sentinelVulnerability scanning, audits (opus)project
storage-security-specialistData protection, encryption--
AgentRoleSkills
devops-engineerCI/CD, automationgithub-actions, k8s, semgrep, pipelines
cloud-architectCloud infra, IaCterraform-patterns
infrastructure-specialistServers, networking--
platform-engineerDeveloper platforms, DevEx--
sre-specialistSLO/SLI, incident mgmt--
observability-engineerMetrics, logs, traces--
message-queue-specialistKafka, RabbitMQ, events--
AgentRoleModel
ai-strategistAI opportunities, visionopus
data-scientistEDA, modeling, ML prototypingsonnet
data-engineerETL pipelines, data platformssonnet
ml-engineerMLOps, model productionizationsonnet
aiops-specialistML model lifecycle, ops healthsonnet
AgentRoleModel
mobile-architectCross-platform strategysonnet
ios-developerSwift/SwiftUI, App Storesonnet
android-developerKotlin/Compose, Play Storesonnet
AgentRoleModel
construction-ai-orchestratorIMPARARIA AI-Stimate/Takeoff/Coordinatesonnet
AgentRoleModelSkills
book-authorDrafting, ghostwriting, narrative voiceopushumanizer
book-editorDevelopmental editing, copy editing, proofreadopushumanizer
publishing-specialistKDP, IngramSpark, metadata, ISBNssonnethumanizer
translation-localization-specialistMultilingual translation with cultural fidelityopushumanizer
AgentRoleModelSkills
business-development-managerPipeline strategy, deal lifecycle, win/lossopushumanizer
lead-generation-specialistProspecting, outreach, lead scoringopushumanizer
proposal-architectRFP response, proposals, compliance matricesopushumanizer
client-success-managerClient lifecycle, retention, renewalsopushumanizer
market-intelligence-analystCompetitive intel, market analysis, pricingopus--
social-media-strategistSocial content, paid ads, campaignsopushumanizer, adspirer

Organization at a Glance

agents/
  00_Executive_Wing/              (2)   Strategic vision & portfolio management
  01_Strategy_and_Planning/       (5)   Architecture, requirements, UX design
  02_Project_Management/          (1)   Agile delivery & sprint management
  03_Engineering_Division/       (31)   Core dev + 19 framework specialists + 8 code excellence
  04_Quality_Assurance/           (4)   Testing strategy, automation, visual regression
  05_SecOps_and_Infrastructure/   (9)   Security, DevOps, cloud, SRE, observability
  06_AI_and_ML_Division/          (5)   Data science, ML engineering, AIOps
  07_Orchestrators/               (3)   Coordination, team config, MCP integration
  08_Mobile_Development/          (3)   iOS, Android, cross-platform architecture
  09_Construction_Industry/       (1)   Construction AI (IMPARARIA methodology)
  10_Content_and_Localization/    (4)   Books, publishing, translation, localization
  11_Business_Development/        (6)   BD pipeline, proposals, social media, market intel
                                 ----
                                  74 agents total

Key Capabilities

Claude Agent SDK Features

FeatureDescription
Claude Opus 4.8opus alias resolves to claude-opus-4-8 — adaptive thinking, high default effort (all surfaces), sharper judgment (~4× fewer unremarked code flaws), better long-context & compaction recovery, high-res vision (2576px / 3.75MP)
Subagent CoordinationParallel processing with isolated context windows (4.8 has better tool triggering; Dynamic Workflows can fan out to hundreds of verified subagents)
Dynamic Workflows (research preview)Plan a task, then spin up hundreds of parallel verified subagents in a single Claude Code session
Agent Teams (experimental)Multi-agent parallel work with shared task lists (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)
Mid-conversation system messagesrole: "system" after a user turn (no beta header) — preserves prompt cache on long agentic loops
Task Budgets (beta)Advisory token countdown across a full agentic loop (task-budgets-2026-03-13 beta header)
Context CompactionAutomatic summarization at 80% usage (47% token reduction)
Persistent Memory13 agents retain project knowledge across sessions via memory: project
Skills Preloading18 specialists preload matching skills at startup via skills: frontmatter
Permission Modes16 code-writing agents use permissionMode: acceptEdits for frictionless flow
MCP IntegrationExternal services (Slack, GitHub, Jira, Figma, Sentry) via Model Context Protocol
Worktree IsolationSubagents work in isolated git worktrees for parallel development
Official PluginsAuto-detection and setup of Anthropic official plugins (GitHub, Slack, Jira, etc.)
Semgrep SASTAutomated security scanning via CLI and MCP plugin integration
Universal PipelinesStack-adaptive quality gates and full build pipelines

Thinking Policies & Budgets

Scratchpad token budgets (internal reasoning) mapped to Opus 4.8 effort levels:

ComplexityTokensEffort LevelAgents
High600-800xhigh / maxSolution, UX/UI, API, Cloud Architects
Medium400-600highBusiness/Functional Analysts, QA Planner, AI Strategist
Medium-Low200-300mediumFramework Specialists, DevOps, Security
Low100-200low / mediumBackend/Frontend Devs, QA Engineer, Performance
Orchestration<=300mediumChief Operations Orchestrator, Team Configurator

On Opus 4.8, effort defaults to high on all surfaces (API + Claude Code); use xhigh for hard design/architecture or large-codebase work, overriding per-agent via effort: frontmatter only when warranted.

Official Plugin Integrations

The deploy script auto-detects and offers to configure these official Anthropic plugins:

PluginCategoryBest For
GitHubDevelopmentcode-reviewer, devops-engineer
SlackCommunicationchief-operations-orchestrator, program-manager, client-success-manager
JiraProject Managementproject-manager-scrum-master, product-manager
LinearProject Managementproduct-manager, business-development-manager
FigmaDesignux-ui-architect, frontend-developer
SentryMonitoringsre-specialist, observability-engineer
VercelDeploymentnextjs-expert, devops-engineer
FirebaseBackendmobile-architect, backend-developer
SupabaseDatabasedatabase-expert, backend-developer
NotionDocumentationdocumentation-specialist, business-analyst, proposal-architect
ConfluenceDocumentationfunctional-analyst
AsanaProject Managementprogram-manager

Agent Skills System

33 custom skills + 9 official Anthropic skills with progressive 3-level loading.

How Skills Work

AspectAgentsSkills
WhatTeam members (74 specialists)Training manuals & toolkits
Where~/.claude/agents/~/.claude/skills/
LoadingTask-based spawningProgressive disclosure

Skills Library

SkillPurpose
pdfPDF manipulation, forms, extraction
docxWord document creation/editing
pptxPowerPoint presentations
xlsxExcel with formulas and charts
mcp-builderMCP server development
webapp-testingPlaywright UI testing
skill-creatorInteractive skill development
artifacts-builderReact/Tailwind components
canvas-designVisual art creation
SkillFrameworkPreloaded By
django-patternsDjango ORM, DRF, authdjango-expert
react-patternsReact hooks, performancereact-expert, react-typescript-expert
vue-patternsVue 3 Composition API, Piniavue-expert
nextjs-patternsNext.js 14 App Router, RSCnextjs-expert
rails-patternsRuby on Rails, ActiveRecordrails-expert
java-patternsSpring Boot, JPA, microservicesjava-expert
go-patternsConcurrency, interfacesgo-expert
laravel-patternsEloquent, API resourceslaravel-expert
SkillPurposePreloaded By
security-auditOWASP Top 10 checklistcyber-sentinel
semgrep-sastSAST scanning + MCP plugincyber-sentinel, code-reviewer, qa-engineer
pipeline-qualityUniversal quality gatecode-reviewer, qa-engineer, devops-engineer
pipeline-full-buildUniversal build pipelinedevops-engineer
github-actionsCI/CD templatesdevops-engineer
kubernetes-deploymentK8s patterns, autoscalingdevops-engineer
terraform-patternsIaC modules, state mgmtcloud-architect
SkillCategory
humanizerWriting Quality (removes AI writing patterns)
tailwind-patternsUI/Styling
antd-patternsUI/Styling
financial-trading-patternsSpecialized Domain
crypto-defi-patternsSpecialized Domain
pytest-patternsTesting
silent-failure-auditQuality Assurance
feature-workflowWorkflow Automation
quick-fixWorkflow Automation
pr-readyWorkflow Automation
SkillFocus
nodejs-patternsAsync, streams, worker threads
python-patternsType hints, async, dataclasses
fastapi-patternsDI, async DB, auth
express-patternsMiddleware, error handling
typescript-patternsAdvanced types, generics
vite-patternsBuild config, plugins
zustand-patternsState management, slices

For detailed skills documentation, see SKILLS.md.


Documentation

DocumentPurpose
README.mdQuick start and overview (this file)
CLAUDE.mdProject configuration and rule index
SKILLS.mdAgent Skills system documentation
CHANGELOG.mdVersion history and release notes
MIGRATION_GUIDE.mdUpgrading from v1.x to v2.0+
CONTRIBUTING.mdCommunity contribution guidelines
docs/SDK_COMPLIANCE_REPORT.md10/10 SDK compliance certification
docs/CONTEXT_ENGINEERING.mdContext management best practices
docs/rules/Modular rule files (7 files)

Upgrading

git clone https://github.com/advisely/claude-code-agents-team-nation-of-elites.git
cd claude-code-agents-team-nation-of-elites
bash scripts/deploy_agents.sh     # Linux/macOS/WSL2
# or
powershell -ExecutionPolicy Bypass -File scripts\deploy_agents.ps1  # Windows

All 74 agents support both natural language invocation (v2+) and explicit agent mentions (v1 legacy). No breaking changes.


Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

  1. Fork the project
  2. Create your feature branch (git checkout -b feature/AmazingNewAgent)
  3. Follow the Agent Development Guidelines
  4. Commit with conventional commits
  5. Open a Pull Request

Credits & References

Resource
AuthorYassine Boumiza -- GitHub
Repositoryadvisely/claude-code-agents-team-nation-of-elites
Anthropic DocsBuilding Effective Agents
Agent SkillsEquipping Agents for the Real World
Agent SDKBuilding Agents with Claude Agent SDK
PluginsClaude Code Plugins Announcement
Agent TeamsBuilding a C Compiler with Agent Teams
Construction AIIMPARARIA -- Progressive Deployment Methodology

License

Distributed under the MIT License. See LICENSE.md for details.

If you find this project useful:


Nation of Elites v3.12.0 -- Claude Opus 4.8 | 74 Agents | 12 Divisions | 33 Skills | Dynamic Workflows | Task Budgets | Adaptive Thinking | BD & Content Wings | Official Plugins | Agent Teams | Semgrep SAST

Yassine Boumiza

Ver o original no GitHub

Bom para

Relacionados