ryanb

require "rubygems"
require "octokit" # gem install octokit

1.upto(5) do |page|
  Octokit.repositories("railscasts", page: page, per_page: 100).each do |repo|
    system "git clone git://github.com/railscasts/#{repo.name}"
  end
end

DavidToca

# Aliases
alias g='git'
compdef g=git
alias gst='git status'
compdef _git gst=git-status
alias gl='git pull'
compdef _git gl=git-pull
alias gup='git fetch && git rebase'
compdef _git gup=git-fetch
alias gp='git push'

aspyct

# Sample implementation of quicksort and mergesort in ruby
# Both algorithm sort in O(n * lg(n)) time
# Quicksort works inplace, where mergesort works in a new array

def quicksort(array, from=0, to=nil)
    if to == nil
        # Sort the whole array, by default
        to = array.count - 1
    end

kpym

Gist

Package

\usepackage{tkz-euclide} % checked for version 3.02c

Point definitions

achow101

#! /usr/bin/env python3

import json
import hashlib

with open('export.json') as f:
    pws = json.load(f)

def build_radix_index(i, offset, lchar):
    radix = {}

championswimmer

How Personal AI Agents and Agent Orchestrators like OpenClaw or GasTown are Made

Over the last few months, projects like Gas Town by Steve Yegge and OpenClaw by Peter Steinberger have made “AI agent orchestrators” feel suddenly mainstream. It is tempting to treat them as a new kind of intelligence, but under the hood they are still a small set of primitives wired together with discipline: an LLM API call, a state loop, tools, memory, and orchestration.

This raises a practical question: what is actually inside an “agent,” and how is it different from ChatGPT (a chat UI over a model) or coding tools like Claude Code (an agentic coding surface)? Gas Town’s README frames it as a “multi‑agent orchest

velvet-shark

OpenClaw after 50 days: all prompts

Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)

These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.

Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.

My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.

CodeLeom

## Workflow Orchestration

### 1. Plan Mode Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately 
- Don't keep pushing.
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity

### 2. Subagent Strategy