pressdarling

Claude Code Tool Extraction Suite

Python scripts for extracting Claude Code tool definitions from claude-trace JSONL files and comparing versions. Uses streaming processing for memory efficiency and includes basic security features (size limits, path sanitisation, credential filtering).

Note

HUMAN WARNING: this is pretty much entirely vibecoded lol thx Claude

Quick Start

Gemini CLI Integration for Claude Code MCP Server

A complete setup guide for integrating Google's Gemini CLI with Claude Code through an MCP (Model Context Protocol) server. This provides automatic second opinion consultation when Claude expresses uncertainty or encounters complex technical decisions.

🚀 Quick Start

Political Spectrum Analysis Prompt

human (Oct 30, 2024, 06:03 PM)

I want to ask the analysis stage llm (a very advanced multimodal LLM) to assess I want to ask the LLM to assess is the snippet politically left-leaning or right-leaning (on a spectrum of -1.0 to +1.0 where -1.0 is extremely left-leaning and +1.0 is extremely right leaning). Please help me to add this to the prompt. Here is the existing prompt that I want you to add it to:

paste.txt

Install iTerm2 from https://www.iterm2.com/
Install oh-my-zsh from https://ohmyz.sh/ or https://github.com/robbyrussell/oh-my-zsh
Set iTerm2 theme tab theme to Dark - Preferences | Appearance | Tabs | Theme > Dark
Install Fira Code fonts from https://github.com/tonsky/FiraCode (Clone and navigate to dstr > ttf, install all font files by double clicking)
Install Powerline fonts from https://github.com/powerline/fonts
Set fonts for iTerm2 - Preferences | Profiles | Text
- Change Font to 14pt Fira code regular and Check Use Ligatures checkbox
- Change Non ASCII Font to 14pt Fira mono and Check Use Ligatures checkbox
Install iTerm2 snazzy theme from https://github.com/sindresorhus/iterm2-snazzy
- Navigate to Preferences | Profiles | Color Presets > Snazzy

	#!/bin/sh

	basename=`basename $0`

	if [ -z "$*" ]; then
	echo "usage: ${basename} <dot> [ -o \| -r \| <file> \| - ]"
	echo ""
	echo "options:"
	echo " -o open dot in window with keyboard focus"
	echo " -r read contents of dot"

	#!/bin/bash

	# Script: GitHubFileDownloader.sh
	# Author: electblake <https://github.com/electblake>, pressdarling <https://github.com/pressdarling>
	# Version: 1.1
	# Description: This script converts one or more GitHub repository file URLs to its GitHub API URL for file contents, checks if the user is logged into GitHub CLI, and downloads the file.
	# Source: https://gist.github.com/electblake/7ef3a63e20b3c8db67d9d66f7021d727
	# Credits:
	# - Inspired by answers on: https://stackoverflow.com/questions/9159894/download-specific-files-from-github-in-command-line-not-clone-the-entire-repo
	# - v1 used "Bash Script" GPT by Widenex for script creation assistance.

	{
	"model_type": "ane",
	"model_config": "v3-3b",
	"backbone_signature": "d95e977fa8053546c6b733aa9d28367d6b23c822",
	"adapter_type_to_signature_mapping": {
	"lora_8": "6c95e384657fa683f8cbd794b893b0171dcc5978",
	"lora_32": "c36b2dd9364c7f12a2d4020f4ebe074458820be7",
	"lora_16": "75f8bce3c9072389a4f73c72390540afde6c93aa"
	},
	"adapter_type_to_symbol_mapping": {

	{
	"model_type": "mlm",
	"tamm_id": "afm-text-30b-instruct-v5-astc-6x6-20240709",
	"checkpoint": "model.mlm",
	"tokenizer": "afm-text-instruct-multilingual-100k-20240701",
	"original_checkpoint": "bolttorchmodel://x5bhyxgsn7/440",
	"export_date": "07/22/2024-11:36:33",
	"mlm_config": {
	"model_name": "ajax",
	"backend": "metal",

	<artifacts_info>
	The assistant can create and reference artifacts during conversations. Artifacts are for substantial, self-contained content that users might modify or reuse, displayed in a separate UI window for clarity.

	# Good artifacts are...
	- Substantial content (>15 lines)
	- Content that the user is likely to modify, iterate on, or take ownership of
	- Self-contained, complex content that can be understood on its own, without context from the conversation
	- Content intended for eventual use outside the conversation (e.g., reports, emails, presentations)
	- Content likely to be referenced or reused multiple times