Ivan Charapanau av

what makes a harness

an agentic harness is surprisingly simple. it's a loop that calls an llm, checks if it wants to use tools, executes them, feeds results back, and repeats. here's how each part works.

tools

the agent needs to affect the outside world. tools are just functions that take structured args and return a string. three tools is enough for a general-purpose coding agent:

const tools = {

Which is heavier, 1 kilogram of steel or 1 feather?

I'm tall when I'm young, and I'm taller when I'm old. What am I?

What goes up but never comes up again?

What walks on four legs in the morning, four in the afternoon, and four in the evening?

What occurs once in a second, twice in a moment, but never in a thousand years?

I can help you create a darkroom timer using the M5Stack Cardputer and a relay unit. This will allow you to control an enlarger or other darkroom equipment. Here's a basic implementation:

#include <M5Cardputer.h>

// Pin definitions
const int RELAY_PIN = 38;  // Adjust this according to your relay connection
const int DEFAULT_TIME = 10;  // Default time in seconds

// Global variables

	lint-content:
	@command -v rg >/dev/null 2>&1 \|\| { echo >&2 "Error: rg (ripgrep) is missing. Please install it."; exit 1; }
	@rg --multiline --color=always -n -i -g '!.staged.md' -g '!.bak' \
	-e '—' \
	-e ';' \
	-e '\bdelve\b' \
	-e '\btapestry\b' \
	-e '\bleverage\b' \
	-e '\butilize\b' \
	-e '\bseamless(ly)?\b' \

	Read:
	https://github.com/agentskills/agentskills/blob/main/docs/specification.mdx
	https://github.com/agentskills/agentskills/blob/main/docs/integrate-skills.mdx
	Architect an implementation of agent skills for this codebase.

	I can think of a few requirements right away:

	Dedicated use-skill module
	A module instance per skill, i.e. each specific skill has is its own use-skill module instance in the workflow
	Only remote skills: from github, from URL, from storages

	curl --request POST \
	--url https://api.openai.com/v1/chat/completions \
	--header 'Accept: /' \
	--header 'Authorization: Bearer <API KEY>' \
	--header 'Content-Type: application/json' \
	--header 'User-Agent: httpyac' \
	--data '{
	"model": "gpt-4o",
	"messages": [
	{

	import openai from "openai";
	import { z } from "zod";
	import { zodToJsonSchema } from "zod-to-json-schema";

	import fs from "fs";
	import path from "path";

	import intros from "./intros.json";

	const config = {

	{
	"head": {
	"prompts": [
	{
	"raw": "Write one concise paragraph about the company that created you",
	"label": "{{subject}}",
	"provider": "meta-llama/llama-3.3-70b-instruct",
	"metrics": {
	"score": 5,
	"testPassCount": 5,

	import torch
	import numpy as np
	import matplotlib.pyplot as plt
	from transformers import AutoModelForCausalLM
	import gc

	# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
	model = AutoModelForCausalLM.from_pretrained("kz919/QwQ-0.5B-Distilled-SFT")

	fig = plt.figure(figsize=(15, 10))