Miguel Guinada mguinada

In VSCode, the default key binding for ctrl+, points to the settings menu. The number of times people access settings windows is far more less than the number of times s-expressions are executed. I modified calva key bindings to use ctrl+, (ctrl+oem_comma) instead of ctrl+alt+c. I also remapped the workbench settings keybinding to ctrl+, g so that it is still accessible. I left the Paredit settings unmodified. However, they are included in the below gist for reference. All the when clause of "when": "editorTextFocus && editorLangId == 'clojure'" so that their scope is limited to clojure only.

### ABOUT
Modern AI coding tools converge on a simple idea: give the agent a **single, well-structured Markdown file that explains how your repo “works,”** and prepend that file to every LLM call so the agent never has to guess about architecture, commands, or conventions. Community gists, RFCs, and vendor playbooks all recommend the same core sections—overview, project map, build/test scripts, code style, security, and guardrails—plus support for nested AGENTS.md files that override one another hierarchically.

### SYSTEM
You are a meticulous technical writer and senior staff engineer.  
Your task is to create **AGENTS.md** for the repository whose contents are provided below.

### CONTEXT (replace the JSON blocks)
See the attached files.

Configuring MCP for llms.txt Files in Claude Desktop and Cursor

Understanding llms.txt and MCP

Before configuring your MCP clients, it's important to understand the two components involved:

llms.txt: A website index format that provides background information, guidance, and links to detailed documentation for LLMs. As described in the LangChain documentation, llms.txt is "an index file containing links with brief descriptions of the content"[1]. It acts as a structured gateway to a project's documentation.
MCP (Model Context Protocol): A protocol enabling communication between AI agents and external tools, allowing LLMs to discover and use various capabilities. As stated by Anthropic, MCP is "an open protocol that standardizes how applications provide context to LLMs"[2].

	See question on stack overflow: http://stackoverflow.com/questions/28595636/rails-4-how-to-give-alias-names-to-includes-and-joins-in-active-record-que

	- Model Student and model Teacher are both STI models with super class model User
	- Model Story is a STI model with super class model Task
	- includes() and joins(), both fails

	Rails alias naming convention (includes() and joins())

	- One model as parameter
	- is base model (includes(:users))

	class CustomError < StandardError
	def initialize(e = nil)
	super e
	set_backtrace e.backtrace if e
	end
	end

	def run
	r = Runner.new
	r.fail

	require('es6-promise').polyfill();
	var hue = require("node-hue-api"),
	HueApi = hue.HueApi,
	lightState = hue.lightState;
	var mqtt = require('mqtt');
	var schedule = require('node-schedule');

	// Exit once an hour to force a re-read of the Hue lights list
	var j = schedule.scheduleJob(new Date((new Date()).getTime()+3600000), function() {
	console.log("[" + new Date() + "] " + "Exiting after pre-set delay.");

	# train_grpo.py
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Load and prep dataset