| name | description |
|---|---|
orchestrating-swarms |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns. |
Master multi-agent orchestration using Claude Code's TeammateTool and Task system.
This is not a proposal. This documents existing but hidden functionality found in Claude Code v2.1.19 binary, plus speculation on how it could be used.
TeammateTool already exists in Claude Code. We extracted this from the compiled binary at ~/.local/share/claude/versions/2.1.19 using strings analysis. The feature is fully implemented but gated behind feature flags (I9() && qFB()).
A system where the large language model (LLM) serves as the brain, natural language is the programming interface, and tools function as devices.
| Classical OS | Claude Code |
|---|---|
| Kernel | Claude (reasoning engine) |
| Memory | Context-window |
| Shell | Natural language |
| Process spawning | Sub-agents |
I'm learning to author and use Agent Skills in Claude and Codex. I gained some insights and I would like to share them here today.
Skill content comes in three types: instructions, scripts, and resources. Skills are organized as files/folders that Claude can draw from via a filesystem-style interface. Claude does progressive disclosure: it does not need to load the entire Skill into the context window upfront, and can fetch only the relevant files as needed. [^1]
Skill content types have different strengths:
I've been a SWE for 7 years, between Amazon, Disney, and Capital One. The code I've shipped touches millions of users, and I built systems that couldn't afford to break. Now I'm the CTO of a startup that builds agents for enterprise, and Claude Code is my daily driver.
Here's a beginners playbook you might find useful, containing everything I've learned about Claude after using it to build robust systems that handle complex workloads from large companies. Let me know if it helps below.
Most people assume that with Claude Code and other AI tools, the first thing you need to do is type (or start talking). But that's probably one of the biggest mistakes that you can make straight off the bat. The first thing that you actually need to do is think.
Just a guide. Not a prescription.
Prompt:
Create a 3D scene of a dynamic, interactive display of Christmas-themed tarot cards arranged in a semi-circular or ring formation.
Here are the specific requirements:
**Visuals & Assets:**
* **Environment:** A dark, moody background with subtle atmospheric effects (e.g., light fog or floating particles).
* **Cards:** Use placeholder plane geometries that resemble tarot card dimensions (e.g., 3.5x5 units).
Here's what it feels like to use Opus 4.5 every day, written the way I'd tell a friend over coffee.
The launch timing was weird: Gemini 3 Pro stole the mic for a day, then everyone vanished for turkey. So the best coding model and the best agent model slipped in the side door while the Internet was sleeping. People just haven't caught up yet.
The hype around "2025 is the year of agents" finally makes sense.
Remember how GPT-4 turned "chat with a computer" into something you'd actually do? Then Sonnet 3.5 did the same for "hey, can you write this code?" Opus 4.5 is that jump again, but for "go handle this whole codebase and ping me when it's done." The first time you watch it plan, iterate, fix its own bugs, and finish a two-hour job while you play Expedition 33, the room tilts a little. After that, the old way feels like the sounds of a dial-up modem.
Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.
Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1