Agent Fleet
AI OS orchestrates 51 specialized sub-agents powered by Claude Opus 4.8 with effort-based routing. Instead of separate models, agents are assigned effort levels (xhigh, high, low) that control reasoning depth. Each agent has a defined role, capabilities, and escalation path managed through Markdown files with YAML frontmatter.
Strategic Tier — Opus 4.8 (effort: xhigh)
Maximum reasoning depth for decisions requiring deep analysis, architectural judgment, and cross-system awareness. Uses adaptive thinking for complex multi-step planning.
| Agent | Role |
|---|---|
| Orchestrator | Central intelligence. Decomposes complex requests, delegates to sub-agents, manages inter-agent data flow, synthesizes final outputs. |
| Architect | System design and technical architecture. Evaluates trade-offs, defines data models, plans migrations. |
| Reviewer | Code and content review. Identifies quality issues, enforces standards, provides actionable improvement suggestions. |
| Security Auditor | Vulnerability assessment, dependency auditing, CSP review, authentication flow analysis. |
Professional Tier — Opus 4.8 (effort: high)
The workhorse tier handles the majority of tasks with balanced quality and speed. Opus 4.8 at high effort provides the same model quality with optimized thinking depth.
| Agent | Role |
|---|---|
| Researcher | Deep research with source synthesis, citation tracking, and structured output generation. |
| Coder | Full-stack development, debugging, refactoring, and test authoring across languages. |
| Writer | Long-form content, copywriting, documentation, and tone-adaptive writing. |
| Design System | DESIGN.md creation, brand reasoning, color theory, WCAG compliance, component specifications. |
| Media Producer | Remotion video generation, Google Vids integration, asset composition. |
| Lead Gen | Prospect scraping, enrichment, scoring, and personalized outreach sequence generation. |
| Marketing Hub | Multi-platform content pipelines, scheduling, A/B variant generation, performance tracking. |
| Product Factory | Digital product creation, marketplace listing, Etsy/Gumroad publishing automation. |
| Vibe Designer | Prompt-driven UI generation with predictive heat maps and interaction flow analysis. |
| Blender 3D | Text-to-3D environments and product renders via Blender MCP integration. |
| Knowledge Graph | Auto-categorizing knowledge ingestion, semantic linking, and radial graph visualization. |
| Golden Loop | Gemini Gems synced to NotebookLM notebooks for continuous knowledge amplification. |
| Synthesis | Cross-agent output merging, conflict resolution, and cohesive deliverable assembly. |
| Automator | CRON-scheduled routines, workflow triggers, and conditional automation chains. |
| Browser Agent | Headless browser control for scraping, form filling, and multi-step web interactions. |
| Report Compiler | Structured report generation from multiple data sources with charts and tables. |
| Research Architect | Research project planning, methodology design, and literature review structuring. |
| Data Wrangler | Data cleaning, transformation, format conversion, and statistical analysis. |
| QA | Test plan creation, regression testing, edge case identification, and quality metrics. |
Scout Tier — Opus 4.8 (effort: low)
Fast agents for quick lookups and lightweight tasks. Low effort minimizes thinking time while retaining Opus 4.8's full capability when needed.
| Agent | Role |
|---|---|
| Scout | Quick fact-checking, simple lookups, and rapid triage of incoming requests. |
| Social Intel | Social media monitoring, sentiment analysis, and trend detection. |
| Routine Runner | Executes pre-defined CRON routines with minimal overhead. |
Economy Tier — DeepSeek V4
Maximum throughput at minimal cost for batch operations.
| Agent | Role |
|---|---|
| DeepSeek Worker | Bulk content generation, template expansion, and high-volume text processing. |
| Batch Runner | Queue-based mass production with automatic retry and output routing. |
Realtime Tier — Grok-3
| Agent | Role |
|---|---|
| Grok Realtime | Live data queries, current events, real-time web intelligence, and social platform analysis. |
Agent Definitions
Each agent is defined as a Markdown file in .claude/agents/ with YAML frontmatter specifying its metadata:
---
name: researcher
model: opus-4.8
effort: high
tier: professional
escalates_to: orchestrator
tools:
- web_search
- vault_read
- vault_write
---
# Researcher Agent
You are a deep research specialist. Your role is to...
Frontmatter Fields
- name — Unique identifier used in API calls and routing
- model — AI model to use (opus-4.8, gemini-omni-flash, deepseek, grok)
- effort — Opus 4.8 effort level: xhigh (strategic), high (professional), low (scout)
- tier — Cost/capability tier for routing decisions
- escalates_to — Agent to escalate to when confidence is low
- tools — List of tools/capabilities available to this agent
Creative Tier — Gemini Omni
Multimodal creative generation powered by Gemini Omni Flash. Produces video, images, audio, thumbnails, and social clips from text prompts.
| Agent | Role |
|---|---|
| Media Producer (Muse) | Creative pipeline orchestration, production strategy, brand consistency across media. |
| Vibe Designer (Pixel) | Prompt-driven UI generation, predictive heat maps, interaction flow analysis. |
| Video Creator (Reel) | Text/image/audio to video with physics simulation. Up to 1080p, 60s. |
| Audio Producer (Sonance) | Voiceovers, music, sound effects, podcast audio from text prompts. |
| Thumbnail Gen | Platform-optimized thumbnails with A/B variants for YouTube, social, blog. |
SEO Agency Sub-Agents
Five specialized agents that run in parallel during SEO audits, each analyzing a different dimension of the target domain.
| Agent | Role |
|---|---|
| SEO Keyword | Keyword research, gap analysis, cannibalization detection, local targeting. |
| SEO Technical | Crawl analysis, Core Web Vitals, HTTP status codes, security, structured data. |
| SEO Competitor | Top 10 competitor profiling, content velocity, schema adoption, ranking overlap. |
| SEO Content | Content inventory, thin content detection, topic clusters, meta data quality. |
| SEO Backlink | Referring domains, toxicity detection, broken link recovery, anchor text analysis. |
Legal Department
Handles licensing agreements, compliance, contracts, and intellectual property protection.
| Agent | Role |
|---|---|
| General Counsel (Justice) | Chief Legal Officer. License agreements, IP protection, regulatory compliance, dispute resolution. |
| Compliance Officer (Shield) | GDPR/CCPA enforcement, audit trails, policy monitoring, API usage compliance. |
| Licensing Attorney (Covenant) | Software license agreements, white-label terms, SaaS licensing, usage rights. |
| Contract Specialist (Clause) | Contract generation, review, lifecycle management, template library. |
Persistent Tier — Hermes MCP
The always-on background worker tier. Hermes runs 24/7 on the platform and handles tasks that require persistence beyond the active session.
| Agent | Role |
|---|---|
| Hermes Delegate | Background task execution with progress pings. Walkaway mode for long refactoring tasks with mobile replies. |
| Hermes Cron | 24/7 scheduled jobs: inbox summaries, news briefs, GitHub backups, comment monitoring, health checks. |
| Hermes Approval Gate | Pauses destructive actions and pushes approval prompts to Telegram/Slack/Discord for mobile review. |
Escalation Paths
Agents can escalate tasks upward when they encounter requests beyond their capability. The escalation chain follows the tier hierarchy:
- Economy → Scout → Professional → Strategic (Orchestrator)
- The Orchestrator is the terminal escalation point and can re-delegate to any agent