Skip to content

Instantly share code, notes, and snippets.

View romgenie's full-sized avatar

Timothy Gregg romgenie

View GitHub Profile
@romgenie
romgenie / 1778559130.run
Created May 12, 2026 11:10
STS2MCP Ironclad Ascension 1 clear run file
{
"acts": [
"ACT.OVERGROWTH",
"ACT.HIVE",
"ACT.GLORY"
],
"ascension": 1,
"build_id": "v0.103.2",
"game_mode": "standard",
"killed_by_encounter": "NONE.NONE",
@romgenie
romgenie / no-harness-tool-calls-real-weather-api.md
Created April 29, 2026 02:31
Tool Calls Without a Harness: Real Weather API

Tool Calls Without a Harness: From Mock Data to a Real Weather API

This is a slow walkthrough of OpenAI tool calling using only raw API calls and PowerShell.

The point:

  • No agent framework is required.
  • No harness is required.
  • The model does not execute your code.
  • The model asks for a tool call.
@romgenie
romgenie / bat_signal_curve.svg
Created April 13, 2026 12:16
Batman SVG curve files
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@romgenie
romgenie / .wezterm.lua
Last active April 13, 2026 14:10
WezTerm config — Claude Code color scheme, SSH launcher with per-host colors, Codex/Claude Code quick-launch, numbered launcher menu, custom keybindings
-- ~/.wezterm.lua
-- Cross-platform WezTerm config (Windows / macOS / Linux).
-- Gist: https://gist.github.com/romgenie/a6acd389dc53c78802b971058cd281f1
local wezterm = require 'wezterm'
local mux = wezterm.mux
local act = wezterm.action
local config = wezterm.config_builder()
-- ============================================================
@romgenie
romgenie / llm-wiki.md
Created April 6, 2026 18:14 — forked from karpathy/llm-wiki.md
llm-wiki

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@romgenie
romgenie / feature-development-workflow.md
Last active April 8, 2026 04:19
Feature Development Workflow with Mermaid diagram

Feature Development Workflow

Keep main stable. Treat feature branches as the default path for any meaningful change.

Core Rules

  1. Create a feature branch before starting implementation work.
  2. Use the codex/ prefix when it fits the task, such as codex/add-spectator-delay.
  3. Keep a todo.md updated while the work is in progress.
  4. Stay on the branch that matches the current task.
@romgenie
romgenie / example_coding_workflow.md
Last active March 29, 2026 16:53
Example coding workflow - STS2 MCP wrapper development flow

Development Workflow


Architecture

graph LR
    subgraph HOST ["Host (LIGHTHOUSE)"]
        W[sts2-mcp-wrapper/<br/>widgets + .env]