learnopengles

LLM Wiki: Mindmap Extension

Purpose. This is an extension of Karpathy's LLM Wiki pattern for a specific variant: a mindmap, where the subject of the wiki is your own thinking rather than a collection of external sources. Paste his gist first, then this, into a fresh LLM coding agent opened on an empty Obsidian vault. The agent asks you what the mindmap is for, writes the schema file and the scaffold, and the wiki grows from conversation.

What it does. Everything in the gist stays as-is: the three layers, the ingest / query / lint loop, index.md and log.md, the LLM as sole writer. This prompt changes the source layer to conversation, adds digital-garden conventions (leaves, maturity markers, red links, question pages), and fixes the agent's stance, the safety rules, and the file layout. It does not decide what the mindmap is for, who reads it, or what it sounds like. That is yours to answer in the first session. A mindmap ca

learnopengles

Agent Harness Seed

A single prompt that builds an agent harness for your repository. The agent scans the code, asks you a short series of questions, and writes a harness sized to your project rather than adapted from someone else's.

What this one gives you: rules that hold because a script checks them, with the reason for each written down; review by a second model family, briefed on what the product must do rather than how the code does it; plan files that make "done" binary and give executors the right to refuse a bad contract; handoffs so an unfinished session is resumable; routing

learnopengles

// Jack Compiler for nand2tetris project 11 -- written in Rust.
// License: CC BY-SA 4.0 -- https://creativecommons.org/licenses/by-sa/4.0/

use std::collections::HashMap;
use std::env;
use std::fs::File;
use std::io;
use std::io::{BufRead, BufReader, BufWriter, Read, Write};
use std::iter::Peekable;
use std::path::Path;

learnopengles

// Jack Analyzer for nand2tetris project 10 -- written in Rust.
// License: CC BY-SA 4.0 -- https://creativecommons.org/licenses/by-sa/4.0/

use std::env;
use std::fs::File;
use std::io;
use std::io::{BufRead, BufReader, BufWriter, Read, Write};
use std::iter::Peekable;
use std::path::Path;
use std::str::Chars;

learnopengles

// VM Translator for nand2tetris project 8 -- written in Rust by Kevin Brothaler.
// CC BY-SA 4.0 -- https://creativecommons.org/licenses/by-sa/4.0/
use std::env;
use std::fs::File;
use std::io;
use std::io::{BufRead, BufReader, BufWriter, Read, Write};
use std::path::Path;

fn main() {
    let args: Vec<String> = env::args().collect();

learnopengles

// Example output for VM Translator for nand2tetris project 7 -- written in Rust.
// CC BY-SA 4.0 -- https://creativecommons.org/licenses/by-sa/4.0/

// Initialize stack pointer
@256
D=A
@SP
M=D

// Push 10 onto the stack

learnopengles

Prerequisites:

- rustup target install x86_64-apple-ios

Steps:

DOCUMENTATION ON COMPILING FOR IOS SIMULATOR

1) Create a shim to the cross-compiling linker for the simulator:

learnopengles

// Assember for nand2tetris project 6 written in Rust.
// CC BY-SA 4.0 -- https://creativecommons.org/licenses/by-sa/4.0/
use std::collections::HashMap;
use std::env;
use std::fs::File;
use std::io;
use std::io::{BufRead, BufReader, BufWriter, Read, Seek, SeekFrom, Write};

fn main() {
    let args: Vec<String> = env::args().collect();

learnopengles

#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include <time.h>
#include "dsp.h"

using namespace std;

static const int LENGTH = 524288;