{"id":47959010,"url":"https://github.com/frankxai/agentic-creator-os","last_synced_at":"2026-04-04T09:39:39.624Z","repository":{"id":333922563,"uuid":"1130736356","full_name":"frankxai/agentic-creator-os","owner":"frankxai","description":"Agentic Creator OS v11 — The operating system for AI-powered creators. 90+ skills, 65+ commands, 38 agents, 8 plugins. Works with Claude Code, Cursor, Windsurf, Gemini.","archived":false,"fork":false,"pushed_at":"2026-03-23T08:28:15.000Z","size":38038,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-03-24T05:52:12.640Z","etag":null,"topics":["agentic-skills","ai-agents","autonomous-coding","claude-code","claude-code-plugins","context-engineering","developer-tools","hooks","llm","multi-agent","orchestration","skills","subagents"],"latest_commit_sha":null,"homepage":"https://frankx.ai/products/agentic-creator-os","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/frankxai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-08T23:55:54.000Z","updated_at":"2026-03-23T08:28:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/frankxai/agentic-creator-os","commit_stats":null,"previous_names":["frankxai/agentic-creator-os"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/frankxai/agentic-creator-os","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frankxai%2Fagentic-creator-os","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frankxai%2Fagentic-creator-os/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frankxai%2Fagentic-creator-os/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frankxai%2Fagentic-creator-os/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/frankxai","download_url":"https://codeload.github.com/frankxai/agentic-creator-os/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/frankxai%2Fagentic-creator-os/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31395436,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T09:13:02.600Z","status":"ssl_error","status_checked_at":"2026-04-04T09:13:01.683Z","response_time":60,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-skills","ai-agents","autonomous-coding","claude-code","claude-code-plugins","context-engineering","developer-tools","hooks","llm","multi-agent","orchestration","skills","subagents"],"created_at":"2026-04-04T09:39:38.975Z","updated_at":"2026-04-04T09:39:39.615Z","avatar_url":"https://github.com/frankxai.png","language":"Python","funding_links":[],"categories":["Source Catalog"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\r\n\r\n# Agentic Creator OS\r\n\r\n**The Operating System for AI-Powered Creators**\r\n\r\n*One install. Any coding agent. 90+ skills, 65+ commands, 38 agents — auto-activating.*\r\n\r\n![Agentic Creator OS — FRANK-Ω Command Center](docs/infographics/acos-hero-omega.png)\r\n\r\n[![Version](https://img.shields.io/badge/version-11.0.0-cyan?style=for-the-badge)](https://github.com/frankxai/agentic-creator-os)\r\n[![License](https://img.shields.io/badge/license-MIT-green?style=for-the-badge)](LICENSE)\r\n[![Platforms](https://img.shields.io/badge/platforms-Claude%20%7C%20Cursor%20%7C%20Windsurf%20%7C%20Gemini-purple?style=for-the-badge)](#multi-platform-install)\r\n\r\n\u003c/div\u003e\r\n\r\n---\r\n\r\n## What Is the Agentic Creator OS?\r\n\r\nA **production-grade skill and agent system** for AI coding assistants. It ships skills (domain knowledge), commands (reusable workflows), agents (specialized personas), and safety hooks — configured to auto-activate based on what you're working on.\r\n\r\nWorks with **Claude Code, Cursor, Windsurf, Gemini Code Assist**, and any AI coding agent that reads markdown context files.\r\n\r\n```\r\nYou: \"write a blog post about AI agents\"\r\n  → Agentic Creator OS detects: creation + blog\r\n  → Auto-loads: content-strategy skill\r\n  → Routes to: /article-creator workflow\r\n  → Result: Guided article with SEO, images, social distribution\r\n```\r\n\r\n### System Architecture\r\n\r\n\u003cdiv align=\"center\"\u003e\r\n\r\n![Agentic Creator OS — Layered Architecture](docs/infographics/acos-architecture.png)\r\n\r\n\u003c/div\u003e\r\n\r\nThe Agentic Creator OS is structured in four layers, each auto-activating based on context:\r\n\r\n| Layer | What It Does | Count |\r\n|-------|-------------|-------|\r\n| **Skills** | Domain knowledge modules that load automatically | 75+ |\r\n| **Commands** | Reusable workflows triggered via slash commands | 35+ |\r\n| **Agents** | Specialized personas with distinct expertise | 38 |\r\n| **Safety Hooks** | Circuit breaker, audit trail, IAM, self-modify gate | 5 |\r\n\r\n---\r\n\r\n## Quick Start\r\n\r\n### Claude Code (Full Feature Set)\r\n\r\n```bash\r\ngit clone https://github.com/frankxai/agentic-creator-os.git\r\ncd agentic-creator-os\r\n./install.sh\r\n\r\n# Open any project with Claude Code\r\nclaude\r\n/acos\r\n```\r\n\r\n### Cursor / Windsurf\r\n\r\n```bash\r\ngit clone https://github.com/frankxai/agentic-creator-os.git\r\ncd agentic-creator-os\r\n./install.sh --platform=cursor    # or --platform=windsurf\r\n```\r\n\r\nThis generates a `.cursorrules` or `.windsurfrules` file with all skills embedded.\r\n\r\n### Gemini Code Assist\r\n\r\n```bash\r\ngit clone https://github.com/frankxai/agentic-creator-os.git\r\ncd agentic-creator-os\r\n./install.sh --platform=gemini\r\n```\r\n\r\nThis generates a `GEMINI.md` context file for Gemini to read on session start.\r\n\r\n### Any AI Coding Agent\r\n\r\n```bash\r\ngit clone https://github.com/frankxai/agentic-creator-os.git\r\ncd agentic-creator-os\r\n./install.sh --platform=generic\r\n```\r\n\r\nGenerates a `CONTEXT.md` file. Point your agent at it as a system prompt or project instructions file.\r\n\r\n\u003e **See [QUICKSTART.md](QUICKSTART.md) for detailed setup per platform**\r\n\r\n---\r\n\r\n## Core Concepts\r\n\r\nThe Agentic Creator OS is built around six foundational concepts. Understanding these unlocks the full system.\r\n\r\n### Skills — Auto-Activating Domain Knowledge\r\n\r\nSkills are markdown files containing deep domain expertise. They **activate automatically** when the Agentic Creator OS detects relevant context in your work.\r\n\r\n```\r\nYou start writing a blog post\r\n  → skill-rules.json matches: \"blog\" + \"write\"\r\n  → Auto-loads: content-strategy + seo-content-writer + schema-markup\r\n  → Your AI agent now has SEO expertise, content structure, and metadata knowledge\r\n```\r\n\r\n| Skill Category | Examples | Trigger Patterns |\r\n|---------------|----------|-----------------|\r\n| **Technical** | TDD, React patterns, TypeScript, debugging | `test`, `component`, `error` |\r\n| **Creative** | Brand voice, music mastery, book writing | `blog`, `music`, `create` |\r\n| **Infrastructure** | Oracle Cloud, Kubernetes, Terraform | `deploy`, `cloud`, `infra` |\r\n| **Business** | Product management, financial modeling | `product`, `strategy`, `pricing` |\r\n\r\n### Commands — Reusable Slash Workflows\r\n\r\nCommands are multi-step workflows triggered by a single slash command. Each command orchestrates skills, agents, and tools in sequence.\r\n\r\n| Command | What It Does | Steps |\r\n|---------|-------------|-------|\r\n| `/article-creator` | Full blog pipeline | Research → Outline → Draft → SEO → Images → Social |\r\n| `/factory` | Mass content production | Batch input → Parallel agents → Quality gate → Export |\r\n| `/spec` | Feature specification | Requirements → Design → Task breakdown → Validation |\r\n| `/infogenius` | Visual intelligence | Topic → Research → 4K image generation → Metadata |\r\n| `/create-music` | Music production | Genre → Prompt engineering → Generation → Metadata |\r\n| `/council` | Strategic decisions | Multi-agent deliberation → Weighted synthesis → Verdict |\r\n\r\n### Agents — Specialized AI Personas\r\n\r\nEach agent has distinct expertise, voice, and tool access. The Agentic Creator OS routes to the best agent based on task type.\r\n\r\n| Agent | Specialty | When It Activates |\r\n|-------|----------|------------------|\r\n| **Developmental Editor** | Story structure, pacing, narrative architecture | Book/long-form writing |\r\n| **Music Producer** | Suno prompts, genre production, audio engineering | Music creation |\r\n| **Technical Architect** | System design, Oracle Cloud, enterprise patterns | Architecture tasks |\r\n| **UI/UX Expert** | Design systems, accessibility, Figma integration | Frontend work |\r\n| **SEO Intelligence** | Keywords, citations, structured data | Content optimization |\r\n| **Starlight Orchestrator** | Multi-agent coordination, strategic decisions | Complex workflows |\r\n\r\n### Smart Router — Intent-Based Routing\r\n\r\nThe `/acos` command analyzes your request and routes to the optimal subsystem:\r\n\r\n```\r\n/acos \"create an infographic about machine learning\"\r\n  ├── Intent detected: visual + educational\r\n  ├── Agent selected: Visual Creator\r\n  ├── Skills loaded: infogenius, design-excellence\r\n  ├── Command chain: /research → /infogenius\r\n  └── Output: 4K infographic with research-grounded content\r\n```\r\n\r\n### Safety Hooks — Autonomous Protection\r\n\r\nFive systems that run automatically to keep the Agentic Creator OS reliable:\r\n\r\n| Hook | What It Prevents |\r\n|------|-----------------|\r\n| **Circuit Breaker** | Stops the agent from brute-forcing broken approaches (3→warn, 5→restrict, 8→block) |\r\n| **Audit Trail** | Append-only JSONL log of every operation — tamper-proof ground truth |\r\n| **Agent IAM** | Role-based scoping — a content writer can't modify build configs |\r\n| **Self-Modify Gate** | Snapshots state before config changes, auto-reverts if intelligence drops |\r\n| **Quality Gate** | Blocks edits to secrets files, warns on production file modifications |\r\n\r\n### Self-Learning — Gets Smarter Every Session\r\n\r\nThe Agentic Creator OS tracks tool sequences and outcomes across sessions, then injects successful patterns as context for similar future tasks. No external API — pure local intelligence.\r\n\r\n---\r\n\r\n## v10 — Autonomous Intelligence\r\n\r\nv10 introduces **5 safety-first autonomous systems** that make your AI coding agent smarter over time:\r\n\r\n### 1. Experience Replay\r\nThe agent remembers what worked. Past successful tool sequences are injected as context for similar new tasks.\r\n\r\n### 2. Agent IAM (Identity \u0026 Access Management)\r\nPer-profile scoping — a content writer can't modify your build config, a music producer can't run shell commands. 6 profiles with tool and directory restrictions.\r\n\r\n### 3. Confidence Circuit Breaker\r\nTracks failures per file. After 3 failures: warn. After 5: restrict. After 8: block. Prevents the agent from brute-forcing broken approaches.\r\n\r\n### 4. Conservative Self-Modify Gate\r\nBefore changing its own config, ACOS snapshots the current state and measures intelligence score. If the score drops more than 5 points after a change: auto-revert.\r\n\r\n### 5. Immutable Audit Trail\r\nAppend-only JSONL logging of every tool use, IAM decision, gate verdict, and config change. The ground truth for what happened in a session.\r\n\r\n\u003cdetails\u003e\r\n\u003csummary\u003e\u003cstrong\u003ev10 Architecture Diagram\u003c/strong\u003e\u003c/summary\u003e\r\n\r\n```\r\n                        /acos (Smart Router)\r\n                            |\r\n              +-------------+-------------+\r\n              |             |             |\r\n         Commands (35+)  Skills (75+)  Agents (38)\r\n              |             |             |\r\n              +------+------+------+------+\r\n                     |             |\r\n              +------+------+  +--+--+\r\n              |             |  |     |\r\n          Hooks (v10)   Workflows  MCP Servers\r\n              |\r\n    +---------+---------+---------+\r\n    |         |         |         |\r\n Circuit   Audit    Self-Mod   Agent\r\n Breaker   Trail    Gate       IAM\r\n```\r\n\u003c/details\u003e\r\n\r\n---\r\n\r\n## What's Included\r\n\r\n### Commands (35+)\r\n\r\n| Category | Count | Examples |\r\n|----------|-------|----------|\r\n| **Creation** | 8 | `/article-creator`, `/create-music`, `/infogenius`, `/factory` |\r\n| **Strategy** | 6 | `/starlight-architect`, `/council`, `/research`, `/plan-week` |\r\n| **Development** | 4 | `/spec`, `/nextjs-deploy`, `/ux-design`, `/automation-dev` |\r\n| **System** | 5 | `/acos`, `/inventory-status`, `/mcp-status`, `/publish` |\r\n| **Quality** | 3 | `/review-content`, `/classify-content`, `/polish-content` |\r\n\r\n\u003e Commands are Claude Code slash commands. On other platforms, describe the task and ACOS skills guide the agent to the same workflows.\r\n\r\n### Skills (75+ Auto-Activating)\r\n\r\nSkills are domain knowledge modules that **activate automatically** based on what you're doing. No manual invocation needed.\r\n\r\n| Category | Count | Examples |\r\n|----------|-------|----------|\r\n| **Technical** | 25+ | TDD, systematic-debugging, mcp-architecture, react-nextjs-patterns |\r\n| **Creative** | 10+ | frankx-brand, suno-ai-mastery, excellence-book-writing |\r\n| **Content** | 15+ | content-strategy, social-media-strategy, video-production |\r\n| **Oracle/Cloud** | 5+ | oci-services-expert, oracle-database-expert, oracle-ai-architect |\r\n| **Business** | 5+ | product-management, coaching-program, financial-modeling |\r\n| **System** | 15+ | swarm-orchestration, agentic-jujutsu, planning-with-files |\r\n| **Personal** | 5+ | spartan-warrior, gym-training, health-nutrition |\r\n\r\n**How Auto-Activation Works:**\r\n```\r\nskill-rules.json → 22 pattern rules\r\n  \"tests\" + \"component\" → loads test-driven-development + react-patterns\r\n  \"blog\" + \"write\"      → loads content-strategy + seo-content-writer\r\n  \"deploy\" + \"vercel\"   → loads vercel-deployment + nextjs-best-practices\r\n```\r\n\r\n### Agents (38 Specialized)\r\n\r\n| Domain | Agents | Examples |\r\n|--------|--------|----------|\r\n| **Writing** | 8 | Developmental Editor, Line Editor, Content Polisher, Story Architect |\r\n| **Strategy** | 5 | Starlight Orchestrator, Visionary, Oracle AI Architect |\r\n| **Design** | 4 | UI/UX Expert, Website Builder, Frankx Content Creation |\r\n| **Production** | 4 | Music Production, Sonic Engineer, Nano Banana Image Gen |\r\n| **Business** | 4 | Product Launch, Coaching Program, Product Development |\r\n| **Technical** | 5 | Technical Architect, Oracle Database, OpenAI AgentKit |\r\n| **Publishing** | 6 | Master Story Architect, Character Psychologist, Sensitivity Reader |\r\n| **System** | 3 | Skill Expert, Project Discovery, Rapid Content |\r\n\r\n### v10 Safety Hooks\r\n\r\n| Hook | Trigger | Purpose |\r\n|------|---------|---------|\r\n| **Circuit Breaker** | PostToolUse (failure) | Track failures per file, escalate at thresholds |\r\n| **Audit Trail** | All tool use | Append-only JSONL logging |\r\n| **Self-Modify Gate** | Config changes | Snapshot + validate intelligence score |\r\n| **Agent IAM** | PreToolUse | Enforce per-profile tool/path scopes |\r\n| **Quality Gate** | PreToolUse (Edit/Write) | Block edits to secrets, warn on production files |\r\n\r\n---\r\n\r\n## How It Works\r\n\r\n### The `/acos` Smart Router\r\n\r\n\u003cdiv align=\"center\"\u003e\r\n\r\n![Agentic Creator OS — Smart Router](docs/infographics/acos-smart-router.png)\r\n\r\n\u003c/div\u003e\r\n\r\nEverything starts with `/acos`. It parses intent and routes to the best subsystem:\r\n\r\n```\r\n/acos \"write a blog post about AI agents\"\r\n  → Detects: creation + blog\r\n  → Routes to: /article-creator\r\n  → Auto-loads: content-strategy skill\r\n  → Result: Guided article creation workflow\r\n```\r\n\r\nFor multi-domain requests, it chains commands:\r\n```\r\n/acos \"Create a blog post about AI music with images and social posts\"\r\n  → /research \"AI music production\"\r\n  → /article-creator (with research context)\r\n  → /infogenius (hero image)\r\n  → /generate-social (distribution)\r\n```\r\n\r\n### Orchestration Patterns\r\n\r\n| Pattern | Description | Best For |\r\n|---------|-------------|----------|\r\n| **Pipeline** | Sequential: Research → Plan → Create → Optimize → Publish | Blog posts, newsletters |\r\n| **Parallel** | Concurrent agents with synthesis | Code review, multi-analysis |\r\n| **Weighted Synthesis** | Expert voting with percentage weights | Strategic decisions |\r\n\r\n### Self-Learning\r\n\r\n\u003cdiv align=\"center\"\u003e\r\n\r\n![Agentic Creator OS — Self-Learning Cycle](docs/infographics/acos-self-learning.png)\r\n\r\n\u003c/div\u003e\r\n\r\nThe Agentic Creator OS learns from every session through a four-stage cycle:\r\n\r\n| Stage | What Happens |\r\n|-------|-------------|\r\n| **1. Session Start** | Creates a trajectory record for the current session |\r\n| **2. Track Operations** | Monitors tool sequences, file changes, and outcomes |\r\n| **3. Extract Patterns** | Identifies successful workflows and tool combinations |\r\n| **4. Apply Intelligence** | Injects learned patterns as context for future sessions |\r\n\r\n```\r\nSession Start → Create trajectory record\r\nSession Active → Track operations and outcomes\r\nSession End → Extract patterns → Store learnings\r\nFuture Sessions → Apply accumulated intelligence\r\n```\r\n\r\n---\r\n\r\n## Multi-Platform Install\r\n\r\n\u003ca id=\"multi-platform-install\"\u003e\u003c/a\u003e\r\n\r\nThe install script detects your platform and configures accordingly:\r\n\r\n```bash\r\n./install.sh                      # Auto-detect platforms\r\n./install.sh --platform=claude    # Claude Code only\r\n./install.sh --platform=cursor    # Cursor only\r\n./install.sh --platform=windsurf  # Windsurf only\r\n./install.sh --platform=gemini    # Gemini Code Assist only\r\n./install.sh --platform=generic   # Any agent (CONTEXT.md)\r\n./install.sh --platform=all       # All detected platforms\r\n```\r\n\r\n### What Gets Installed Per Platform\r\n\r\n| Component | Claude Code | Cursor | Windsurf | Gemini | Generic |\r\n|-----------|:-----------:|:------:|:--------:|:------:|:-------:|\r\n| Skills (knowledge) | ~/.claude/skills/ | .cursorrules | .windsurfrules | GEMINI.md | CONTEXT.md |\r\n| Commands (workflows) | ~/.claude/commands/ | — | — | — | — |\r\n| Agents (personas) | ~/.claude/agents/ | .cursorrules | .windsurfrules | GEMINI.md | CONTEXT.md |\r\n| Hooks (safety) | settings.json | — | — | — | — |\r\n| Auto-activation | skill-rules.json | — | — | — | — |\r\n| MCP servers | Optional | — | — | — | — |\r\n\r\n\u003e **Claude Code gets the full feature set** including slash commands, lifecycle hooks, and auto-activation rules. Other platforms get skills and agent definitions embedded in their context files.\r\n\r\n---\r\n\r\n## Directory Structure\r\n\r\n```\r\nagentic-creator-os/\r\n├── .claude/\r\n│   ├── commands/           # 35+ slash commands\r\n│   ├── skills/             # 75+ auto-activating skills\r\n│   ├── agents/             # 38 specialized agents\r\n│   ├── hooks/              # v10 safety hooks\r\n│   │   ├── circuit-breaker.sh\r\n│   │   ├── audit-trail.sh\r\n│   │   ├── self-modify-gate.sh\r\n│   │   └── quality-gate.sh\r\n│   ├── agent-iam.json      # Role-based access control\r\n│   ├── skill-rules.json    # 22 auto-activation rules\r\n│   └── hooks.json          # Hook lifecycle config\r\n│\r\n├── adapters/               # Platform adapters\r\n│   ├── cursor/             # .cursorrules generator\r\n│   ├── windsurf/           # .windsurfrules generator\r\n│   ├── gemini/             # GEMINI.md generator\r\n│   └── generic/            # CONTEXT.md generator\r\n│\r\n├── departments/            # Agent team definitions\r\n│   ├── content/\r\n│   ├── design/\r\n│   ├── dev/\r\n│   ├── marketing/\r\n│   └── business/\r\n│\r\n├── mcp-servers/            # MCP integrations (optional)\r\n├── templates/              # Reusable templates\r\n├── workflows/              # Workflow definitions\r\n├── docs/infographics/      # Visual documentation\r\n├── install.sh              # Multi-platform installer\r\n├── CLAUDE.md               # Claude Code context\r\n└── package.json            # v10.1.0\r\n```\r\n\r\n---\r\n\r\n## The Starlight Connection\r\n\r\nACOS is the **Claude Code implementation** of the [Starlight Intelligence System](https://github.com/frankxai/Starlight-Intelligence-System) — a universal, platform-agnostic framework for multi-agent orchestration.\r\n\r\n```\r\nStarlight Intelligence System (Framework)\r\n├── 5-layer cognitive architecture\r\n├── 7 council agents with emergent leadership\r\n├── 6 orchestration patterns\r\n└── Platform adapters\r\n     └── ACOS (Claude Code + Multi-Platform)\r\n         ├── 35+ commands routed through /acos\r\n         ├── 38 agents aligned to Starlight council\r\n         ├── 75+ auto-activating skills\r\n         ├── v10 safety systems (IAM, circuit breaker, audit)\r\n         └── Self-learning via trajectory patterns\r\n```\r\n\r\n---\r\n\r\n## Design Principles\r\n\r\n1. **Configuration over Code** — Markdown + JSON + AI's native abilities. Zero install friction.\r\n2. **Commands over Prompts** — Reusable workflows beat one-off prompts. Build once, use forever.\r\n3. **Agents over Chat** — Specialized expertise beats general conversation.\r\n4. **Files over Memory** — Persistent artifacts beat ephemeral threads. Everything is git-trackable.\r\n5. **Progressive Disclosure** — Load only what you need. ~100 tokens metadata before 5K skill definition.\r\n6. **Open and Forkable** — MIT licensed. Every component replaceable.\r\n\r\n---\r\n\r\n## Plugin Marketplace\r\n\r\nExtend ACOS with installable domain plugins from **[agentic-creator-skills](https://github.com/frankxai/agentic-creator-skills)**:\r\n\r\n| Plugin | Purpose |\r\n|--------|---------|\r\n| **core** | Session management, workspace memory, task tracking |\r\n| **content-engine** | Content creation, voice enforcement, publishing |\r\n| **visual-studio** | Style-governed image generation, 7-gate quality filter |\r\n| **music-lab** | AI music production, Suno prompt engineering |\r\n| **brand-architect** | Brand voice system, tone adaptation, terminology |\r\n| **product-launcher** | Product specs, sprint management, deployment |\r\n| **intelligence** | Intelligence scoring, pattern analysis, reporting |\r\n| **design-excellence** | Design system governance, 5-gate QA, Figma integration |\r\n\r\n```bash\r\n# Install plugins (Claude Code)\r\nclaude plugin marketplace add frankxai/agentic-creator-skills\r\nclaude plugin install core content-engine design-excellence\r\n```\r\n\r\n\u003e ACOS = the operating system. Plugins = the app store. Install only what you need.\r\n\r\n---\r\n\r\n## Version History\r\n\r\n| Version | Date | Highlights |\r\n|---------|------|------------|\r\n| **v11.0** | Feb 2026 | Plugin ecosystem, design swarm, v11 skills absorbed from acos-intelligence-system |\r\n| v10.1 | Feb 2026 | Deep clean — removed claude-flow artifacts, honest metrics, clean repo |\r\n| v10.0 | Feb 2026 | Autonomous Intelligence — 5 safety systems, multi-platform, Agent IAM |\r\n| v8.0 | Feb 2026 | Starlight integration, GitHub release assets, swarm orchestration |\r\n| v7.0 | Feb 2026 | Visionary agent, premium infographics, expanded commands |\r\n| v6.0 | Jan 2026 | Smart router (/acos), auto-activation, hooks |\r\n| v5.0 | Jan 2026 | 7-pillar architecture, 62 skills, swarm topologies |\r\n| v4.0 | Jan 2026 | Initial release, 14 commands, basic skills |\r\n\r\n---\r\n\r\n## Credits \u0026 Attribution\r\n\r\nACOS builds on work from the open-source community:\r\n\r\n| Project | Author | What We Learned |\r\n|---------|--------|-----------------|\r\n| [claude-flow](https://github.com/ruvnet/claude-flow) | @ruvnet | Swarm orchestration, hierarchical topologies |\r\n| [wshobson/agents](https://github.com/wshobson/agents) | @wshobson | Plugin architecture, modular skills |\r\n| [obra/superpowers](https://github.com/obra/superpowers) | @obra | Progressive disclosure, token-efficient loading |\r\n| [diet103/claude-code-infrastructure-showcase](https://github.com/diet103/claude-code-infrastructure-showcase) | @diet103 | `skill-rules.json` auto-activation pattern |\r\n| [ChrisWiles/claude-code-showcase](https://github.com/ChrisWiles/claude-code-showcase) | @ChrisWiles | Hook automation patterns |\r\n| [Pimzino/claude-code-spec-workflow](https://github.com/Pimzino/claude-code-spec-workflow) | @Pimzino | Spec-driven development |\r\n| [github/github-mcp-server](https://github.com/github/github-mcp-server) | GitHub | Official GitHub MCP server |\r\n| [agentic-jujutsu](https://github.com/ruvnet/agentic-jujutsu) | @ruvnet | Self-learning trajectory patterns |\r\n\r\n**Built on:** [Claude Code](https://claude.ai/claude-code) by Anthropic, [Model Context Protocol](https://modelcontextprotocol.io/)\r\n\r\n---\r\n\r\n## Related Projects\r\n\r\n- **[agentic-creator-skills](https://github.com/frankxai/agentic-creator-skills)** — Plugin marketplace (8 domain plugins)\r\n- **[Starlight Intelligence System](https://github.com/frankxai/Starlight-Intelligence-System)** — The universal framework powering ACOS\r\n- **[Arcanea](https://github.com/frankxai/arcanea)** — AI-native creative platform built with ACOS\r\n\r\n---\r\n\r\n## License\r\n\r\nMIT — Use it, fork it, build your own OS with it.\r\n\r\n---\r\n\r\n\u003cdiv align=\"center\"\u003e\r\n\r\n**Agentic Creator OS v11.0** — The Operating System for AI-Powered Creators\r\n\r\n*90+ Skills | 65+ Commands | 38 Agents | 8 Plugins | Multi-Platform | Self-Learning*\r\n\r\nBuilt by [FrankX](https://frankx.ai) — AI Architect \u0026 Creator\r\n\r\n[GitHub](https://github.com/frankxai/agentic-creator-os) | [Website](https://frankx.ai/acos) | [Issues](https://github.com/frankxai/agentic-creator-os/issues)\r\n\r\n\u003c/div\u003e\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrankxai%2Fagentic-creator-os","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffrankxai%2Fagentic-creator-os","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffrankxai%2Fagentic-creator-os/lists"}