BlazerYoo

Implement an Anthropic OAuth CLI and Populate `~/.claude/.credentials.json`

This gist shows how to implement your own OAuth workflow so your tool can acquire Anthropic OAuth tokens and write them in the format the Claude Code SDK expects at ~/.claude/.credentials.json.

Notes

Uses an Authorization Code + PKCE flow via https://claude.ai/oauth/authorize and token exchange at https://console.anthropic.com/v1/oauth/token.
Default client id commonly used by tools: 9d1c250a-e61b-44d9-88ed-5944d1962f5e (override with your own if issued).
The authorize endpoint supports a copy/paste mode (no local server). Your CLI opens/prints a URL; the user pastes a code back.
Treat tokens as secrets; never log them.

ECE 451 — Final Project Presentation Script

Self-Powered Epicardial Bioelectronic Patch: Mechanical-First Closed-Loop Therapy for Heart Failure and Arrhythmia Management

Sydney Bold & Boaz Yoo · Target: 12 minutes + 3 min Q&A

How to use this script

Crouton Install and Management

	# CITATION: https://scikit-learn.org/stable/modules/permutation_importance.html#permutation-importance
	# CITATION: https://scikit-learn.org/stable/modules/generated/sklearn.inspection.permutation_importance.html
	from sklearn.inspection import permutation_importance

	models = {
	'Nearest Neighbors': knn,
	'Naive Bayes': nb,
	'Logistic Regression': log_reg,
	'Support Vector Machines': svm,
	'Decision Tree': dt,


	╭─── Claude Code v2.1.12 ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
	│ │ Tips for getting started │
	│ Welcome back Jonny! │ Run /init to create a CLAUDE.md file with instructions for Claude │
	│ │ │
	│ │ ───────────────────────────────────────────────────────────────── │
	│ ▐▛███▜▌ │ Recent activity

	chronos@localhost ~/Downloads $ sudo sh crouton -r xenial -t unity
	Installing xenial-amd64 chroot to /usr/local/chroots/xenial
	Downloading bootstrap files...
	debootstrap error log:
	[.[] \| select((.extendedSupport // .support) > (now \| strftime("%Y-%m-%d")) and (.codename \| test($suite; "i")))] \| isempty(.[]) \| not error: strftime is not defined
	[.[] \| select((.extendedSupport // .support) > (now \| strftime("%Y-%m-%d")) and (.codename \| test($suite; "i")))] \| isempty(.[]) \| not error: test is not defined
	[.[] \| select((.extendedSupport // .support) > (now \| strftime("%Y-%m-%d")) and (.codename \| test($suite; "i")))] \| isempty(.[]) \| not 4 compile errors
	Failed to run debootstrap.

	"""
	SML312 import demo
	"""

	def introduceFunctionThatIWrote(name="SML", age="312"):
	print(f'Hello! My name is {name} and I am {age} years old!')

	from transformers import AutoTokenizer, AutoModelForCausalLM

	# Load the tokenizer and model
	tokenizer = AutoTokenizer.from_pretrained("notnate/Llama-3.1-8B-Instruct-blockchain")
	model = AutoModelForCausalLM.from_pretrained("notnate/Llama-3.1-8B-Instruct-blockchain")

	# Define the prompt
	prompt = "Explain how blockchain works in simple terms."

	# Tokenize the prompt

	# First let's update all the packages to the latest ones with the following command
	sudo apt update -qq

	# Now we want to install some prerequisite packages which will let us use HTTPS over apt
	sudo apt install apt-transport-https ca-certificates curl software-properties-common -qq

	# After that we will add the GPG key for the official Docker repository to the system
	curl -fsSL https://download.docker.com/linux/ubuntu/gpg \| sudo apt-key add -

	# We will add the Docker repository to our APT sources