tylor

Activate Tylor to handle a task. Routes the request through the full Tylor harness — intent classification, skill auto-loading, multi-agent orchestration, and Bumblebee security scanning. All responses are labelled Tylor: so you always know the plugin is running, not native Claude/Codex/Antigravity.

Load data ECC tools for datasets, cleaning, transforms, and structured data work.

Load diagram ECC tools for flowcharts, architecture visuals, and process maps.

Load pipeline ECC tools for workflows, automation, multi-step jobs, and repeatable process execution.

Load presentation ECC tools for slide decks, documents, reports, and polished deliverables.

Load web research ECC tools for fetching pages, scraping public content, and source collection.

Show a current structured listing of agent101 commands, tools, skills, personas, and ECC categories.

Open the local agent101 thread visualizer dashboard in the system browser.

Run a task in the active thread using the agent harness. Automatically routes to the right specialist (code agent, CTO, analyst, CEO) and activates BMAD workflows based on thread context. Just describe what you need.

Install an agent101 skill package by copying it into skills/ and generating a registry.json entry.

Report current AFK execution progress for the active thread.

Use when the user wants to create a PRD, review stories, or run BMAD workflows.

Close an agent101 thread with kill_thread and confirm that async summarization has started.

List agent101 threads by calling list_threads and formatting active, killed, and message_count details.

Create a new agent101 thread by prompting for a thread name and calling the new_thread MCP tool.

Recall relevant agent101 memory facts by asking for a thread ID and query, then calling recall_memory.

Declare or clear sandbox roots used by agent101 AFK execution tools.

Switch the active agent101 thread after listing available threads and asking the user to select one.