Abdullah Mohammed abodacs

name	description	tools	model
appsec-guardian	Expert Application Security Engineer. Prevents insecure code from reaching remote repositories by enforcing OWASP Top 10 and secure SDLC practices. Runs before git push to block vulnerable code.	view, bash_tool, str_replace, create_file, web_search, web_fetch	inherit

You are a senior Application Security Engineer with deep expertise in OWASP Top 10, secure SDLC, and security-by-design principles.

Core Mission

source	title	type	organization	cleaned_by
https://huggingfacetb-smol-training-playbook.hf.space/	The Smol Training Playbook: The Secrets to Building World-Class LLMs	Technical Blog Post	Hugging Face	Crawl4AI

The Smol Training Playbook:

Title: The Smol Training Playbook: The Secrets to Building World-Class LLMs

URL Source: https://huggingfacetb-smol-training-playbook.hf.space/

Published Time: Oct. 30, 2025

Markdown Content: Table of Contents

Table of Contents

Replace Xcode MCP with CLI (saves about 32k tokens)

There are two files:

xcodebuild - the script that the agent is expected to run
building-with-xcode.md - the instructions given to the agent, i.e. in CLAUDE.md

Collapse Studio Buttons Container

Collapse Studio Buttons Container is a userscript that adds a collapse/expand button to the studio panel header in NotebookLM. This allows users to hide or show the studio buttons container, providing a cleaner and more focused view of the artifact library.

Key Features

Adds a collapse/expand button to the studio panel header.
Smooth transition when collapsing or expanding the buttons container.

	# ------------------- Stage 0: Base Stage ------------------------------
	FROM python:3.13-alpine AS base

	# Install tini, a tiny init for containers
	RUN apk add --update --no-cache tini

	# Install required packages for cryptography and ml-dtypes packages
	# https://cryptography.io/en/latest/installation/#building-cryptography-on-linux
	RUN apk add gcc g++ musl-dev python3-dev libffi-dev openssl-dev cargo pkgconfig

	"""
	Quick and dirty replication of
	"Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline" (https://arxiv.org/abs/2507.15855)
	using LangGraph.

	Export GOOGLE_API_KEY to run.
	Change the model, question and constants directly in the code (no CLI).
	"""

	import asyncio

	## Stack:
	## Tanstack Start
	## Infra: Alchemy / Cloudflare
	## UI: Shadcn
	## Store: Zustand
	## DB Drizzle

	## Commands

	- Dev Server: pnpm dev (runs Alchemy dev with hot-reload; uses .env.dev)

	import subprocess
	import random
	import numpy as np

	import torch
	from torch._utils import _get_available_device_type, _get_device_module
	from loguru import logger

	# DEBUG = False
	DEBUG = True

	import torch
	from torch import Tensor


	def varlen_attn(
	query: Tensor,
	key: Tensor,
	value: Tensor,
	cum_seq_q: Tensor,
	cum_seq_k: Tensor,