cms

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.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

---

cms

How Claude Code Team Coordination Works

Observed by: observer agent Date: 2026-02-09 Team: moltbook-tui (1 lead + 4 agents, observed over ~10 minutes of activity) Snapshots taken: 7 (see snapshot-1.md through snapshot-7.md for raw data)

Architecture Overview

Claude Code teams use a filesystem-based coordination system. There are no sockets, databases, or message queues - everything is stored as JSON files on disk. Agents coordinate through:

cms

Agent Guidelines for Python Code Quality

This document provides guidelines for maintaining high-quality Python code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

cms

At the end of this message, I will ask you to do something. Please follow the "Explore, Plan, Code, Test" workflow when you start.

Explore

First, use parallel subagents to find and read all files that may be useful for implementing the ticket, either as examples or as edit targets. The subagents should return relevant file paths, and any other info that may be useful.

Plan

Next, think hard and write up a detailed implementation plan. Don't forget to include tests, lookbook components, and documentation. Use your judgement as to what is necessary, given the standards of this repo.

If there are things you are not sure about, use parallel subagents to do some web research. They should only return useful information, no noise.

cms

import _ from "lodash"
import React from "react"
import moment from "moment"
import { connect } from "react-redux"
import API from "@Services/Api/profile"
import { ApiManager } from "../../api/apiManager"
import ParsedText from "react-native-parsed-text"
import { NavigationEvents } from "react-navigation"
import { DateToWordsFromNow } from "../../helpers/helper"
import { ACTIVITY_NOTIFICATION } from "../../api/constants"

cms

import _ from "lodash";
import React from 'react';
import moment from 'moment';
import { connect } from 'react-redux';
import API from '@Services/Api/profile';
import { ApiManager } from "../../api/apiManager";
import ParsedText from 'react-native-parsed-text';
import { NavigationEvents } from "react-navigation";
import { DateToWordsFromNow } from '../../helpers/helper';
import { ACTIVITY_NOTIFICATION } from "../../api/constants";

cms

USE AdventureWorks

GO

--============== Supporting function dbo.udfGetFullQualName
IF OBJECT_ID('dbo.udfGetFullQualName') IS NOT NULL 
    DROP FUNCTION dbo.udfGetFullQualName
GO
CREATE FUNCTION dbo.udfGetFullQualName ( @ObjectId INTEGER )

cms

stashgrep() {
  for i in `git stash list | awk -F ':' '{print $1}'`; do
    git stash show -p $i | grep -H --label="$i" "$1"
  done
}

cms

Installing GNU Screen on OS X in Homebrew

I want to edit in one tab, run what I edit in the other. Typical multi-view stuff. I've used Terminal.app for the last few years. Lately, however, after not long enough, Terminal gets laggy when I switch between tabs.

The stutter between edit and run is annoying, an unnacceptable. One of the major reason I've chosen to work with character based UI is because it is snappy. There shouldn't be a lag while a screen of UTF-8 is rendered in a monospace font.

The lag gets progressively longer, chipping at my productivity with irritation. The only solution is to kill all my Terminals, which essentially kills my flow. Terminal.app won't remember where I was for me. I have to initialize ever tab.

GNU Screen

cms

# http://henrik.nyh.se/2008/12/git-dirty-prompt
# http://www.simplisticcomplexity.com/2008/03/13/show-your-git-branch-name-in-your-prompt/
#   username@Machine ~/dev/dir[master]$   # clean working directory
#   username@Machine ~/dev/dir[master*]$  # dirty working directory

function parse_git_dirty {
  [[ $(git status 2> /dev/null | tail -n1) != "nothing to commit (working directory clean)" ]] && echo "*"
}
function parse_git_branch {
  git branch --no-color 2> /dev/null | sed -e '/^[^*]/d' -e "s/* \(.*\)/[\1$(parse_git_dirty)]/"