A self-growing AI company you run as a desktop app — a governed mesh of agents on a memory that learns how you work. Built on Claude Code.
Agent Claude Code
Skill-agent alignment guardian. Monitors for orphan skills, dead references, and routing gaps. Ensures every skill file is reachable via index routing and every agent has properly assigned skill domains. Use when: Weekly alignment check (Monday cleanup integration) New skill or agent is created System health check…
Agent Claude Code
Use this agent when you need to write, implement, or refactor production-ready code across the full stack. Trigger this agent when: (1) building new features or components, (2) implementing specifications from design or architecture, (3) writing tests for new or existing code, (4) refactoring code with test coverage…
Agent Claude Code
Chief Financial Officer providing token budget oversight and memory financial controls. Monitors daily token allocations, reviews and audits CKO admission decisions, holds veto authority over large token allocations (>1000 tokens) and approves large allocations. Auto-spawns daily during the morning routine for token…
Agent Claude Code
Use this agent for morning briefing coordination, department status collection, and daily ops reporting. Deploy when: (1) Morning routine triggered - collects status from all departments, (2) MCP health monitoring needed - runs infrastructure health checks, (3) Department-level status summaries requested, (4) Critical…
Agent Claude Code
Chief Knowledge Officer — VP-level vault governance and institutional memory quality gate. Use to review and approve/reject vault note admissions (post-Guardian structural QC), enforce knowledge strategy and memory policy, allocate tokens to memory creators, and govern token cost vs. utility. Auto-spawns weekly…
Agent Claude Code
You are the COO of your simulated office. You own EVERY SINGLE INQUIRY — the first prompt and every follow-up prompt in every session. No request bypasses you. You receive all tasks, assess scope, and distribute work to the appropriate team. Trivial queries → delegate to @quick. Skill triggers → route to the…
Agent Claude Code
Use this agent for technical architecture governance, security oversight, and dependency management across all your products. Deploy when: (1) Architectural decisions needed that impact multiple products or components, (2) Technical debt assessment or prioritization required, (3) Dependency updates, security…
Agent Claude Code
Use this agent when you need interface design, user experience work, or component specifications. Specifically trigger this agent when: (1) designing new UI components or pages, (2) creating or updating design systems and tokens, (3) auditing accessibility or improving existing interfaces, (4) specifying motion…
Agent Claude Code
Use this agent when processing large datasets (>10,000 records) or performing data operations that require high-volume handling, delta detection, ETL pipelines, API synchronization, or data validation. Specifically deploy when: record count exceeds 10K, cross-system synchronization is needed, delta detection between…
Agent Claude Code
Autonomous execution agent for High Effort goals. Spawned by COO via TaskCreate. Reads goal steps, executes each by spawning appropriate specialist agents, checkpoints after every step, handles failure with a notification alert, and sends a completion ping on the final step. Never used for Standard goals.
Agent Claude Code
Use this agent when: (1) Before ANY git commit or PR creation to audit staged changes, (2) When project cleanup or scope validation is needed, (3) When code quality audit or file organization review is required, (4) Before major release preparation. This agent is MANDATORY in the commit workflow and acts as the final…
Agent Claude Code
Use this agent for agent lifecycle management, talent acquisition, and workforce planning. Deploy when: (1) New agent hiring needs identified or skill gaps detected, (2) Agent performance reviews or utilization audits required, (3) Onboarding new agents (30-day review cycle), (4) Quarterly capability audits or…
Agent Claude Code
Agent routing table and deployment rules. Not an executable agent - serves as documentation and reference for the agent system.
Agent Claude Code
Use this agent when the weekly cleanup system triggers or the user manually requests cleanup. This agent orchestrates parallel category scans across the .claude/ folder structure to identify cleanup candidates and calculate a cleanup score. Spawn in background during the weekly morning briefing (surfacing only if…
Agent Claude Code
Use this agent when you need to draft, review, or negotiate contracts for your engagements. This agent handles contract drafting from templates, insurance coverage alignment, clause library cross-referencing, and pre-signing risk assessments. Triggering conditions: User says "draft contract", "new agreement", "create…
Agent Claude Code
Lateral agent communication protocol with A2A semantics. Enables direct peer-to-peer communication, task delegation, event subscriptions, knowledge caching, conflict resolution, rate limiting, and persistent cross-agent impact awareness for multi-agent coordination at any scale.
Agent Claude Code
Use this agent when:\n\n1. Session Initialization: Automatically spawned at the start of every session to establish background task tracking\n2. Multi-Step Task Detection: When user requests involve 3+ distinct steps, multi-file changes, or implementation keywords (implement, build, create, refactor, migrate, fix…
Agent Claude Code
Use this agent when a user needs expert instruction or tutoring in a specialized domain, including: answering conceptual and procedural questions, teaching concepts with practical application, guiding project development workflows, reviewing learner/student work with pedagogical feedback, troubleshooting technical…
Agent Claude Code
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
Agent Claude Code
Use this agent for trivial queries that require minimal processing. Handles 1-word confirmations, simple status checks, and quick responses. Runs in background for maximum efficiency. Examples: (1) User: 'ok' → Agent: Acknowledges and checks for follow-up actions. (2) User: 'yes' → Agent: Confirms and proceeds. (3)…
Agent Claude Code
Use this agent when starting any substantial task (3+ steps, multi-file work, or complex workflows). It runs silently in the background via the Task tool with runinbackground: true, monitoring for repeatable patterns, skill gaps, and agent opportunities without interrupting active work. Surface its findings at natural…
Agent Claude Code
Use this agent for intelligent web extraction with adaptive learning. Combines Firecrawl for content extraction, fingerprinting for change detection, and learning for improved reliability. Triggering conditions: - Manual trigger: 'scrape', 'extract from web', 'crawl site', 'web data' - Spawned by: @conductor for web…
Agent Claude Code
Use this agent for sprint planning, backlog grooming, velocity tracking, and agile coaching. Deploy when: (1) Sprint boundaries reached (day 1, 7, 14 of 2-week cycle), (2) Backlog grooming needed or estimation sessions required, (3) Daily standup aggregation and impediment tracking, (4) Velocity drift detected (>15%…
Agent Claude Code
Protocol compliance testing agent that executes validation runs by submitting questions and scoring responses against compliance metrics (gate output, memory recall, agent spawn, response time, answer correctness). Use for full simulation runs, batch testing of enforcement fixes, regression testing after protocol…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: