Sam sammcj

Claude Code Mods: a field guide

How to build Claude Code mods: plugins that hook the engine, add commands and tools, and draw their own UI inside Claude Code, from status lines to animated panes.

By ruvnet. Written from building and shipping a real mod, with every pitfall we hit included.

Early access. Mods (function hooks) are an early-access Claude Code feature, and the API moves between releases. Your build writes its own type definitions next to every mod you load (see Setup), and those types are the authority. Grep them before you trust any guide, this one included.

Throughout this guide:

🧪 Field-tested means we did it in a shipped mod and saw it work (or break) for real.

name	explain-diff-html
description	Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.

Explain Diff

Please make me a rich, interactive explanation of the specified code change.

It should have these sections:

LLM Wiki V3: Segmentation

Karpathy gave us the foundation. Rohitg00 warned us what breaks. V3 is how you structure it to scale.

This is a concept document in the same spirit as V1 and V2.

V1 was intentionally vague. Build on it. V2 was intentionally open. Solve it.

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 20K+ Stars ⭐️, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

The Complete Guide to Building Skills for Claude

The Great Quant Wars of 2025

"All things leave behind them the Obscurity... and go forward to embrace the Brightness..." — Dao De Jing #42

tl;dr;

Q: Who provides the best GGUFs now?
A: They're all pretty good.

Skip down if you just want graphs and numbers comparing various Qwen3-30B-A3B GGUF quants.

	#!/usr/bin/env python3
	# Repack a split GGUF so one tensor (default: the qwen4exp engram table
	# per_layer_token_embd.weight) sits ALONE in the final shard, with no other tensors
	# sharing that file. Motivation: on Metal, llama.cpp wires the mmap'd regions that
	# back GPU tensors; a tensor interleaved with them in the same file gets wired along
	# for the ride (measured +24 GiB on Qwen3.8-Flash-Next). A file containing only
	# CPU-side tensors keeps its own mapping and stays pageable.
	#
	# Tensor bytes are copied verbatim (no requantization). Output layout for an N-file
	# input: shard 1 = byte-for-byte copy of input shard 1 (metadata-only; split.count and

	/**
	* Local Models Extension
	*
	* Manage self-hosted LLM endpoints entirely from the TUI.
	* Commands:
	* /local-models - Open the local models manager
	*
	* Config is persisted across sessions. Models show up in /model selector
	* automatically when their endpoint is reachable.
	*

	# Standard zshrc stuff like path, etc.
	# ...

	# Enable using the two files above:

	# Functions
	source venv-auto-activate.sh

	# Venv security whitelist/blocklist
	alias venv-security='uv run -q --no-project ~/scripts/venv-security.py'

	import requests
	import json
	import argparse
	from rich.console import Console
	from rich.table import Table
	from rich.live import Live
	from rich.spinner import Spinner

	def search_for_part(description, show_all, no_sort):
	"""