Skip to content

Instantly share code, notes, and snippets.

View danielbodnar's full-sized avatar
:copilot:
Engineering abstractions

Daniel Bodnar danielbodnar

:copilot:
Engineering abstractions
View GitHub Profile
@ruvnet
ruvnet / LA.md
Created October 25, 2025 02:42
Lean Agentic: High-Performance Agentic Programming Language

Building a High-Performance Agentic Programming Language

Implementation Roadmap for Production-Ready Agent Systems

This comprehensive implementation plan synthesizes battle-tested techniques from Lean4, Rust, Erlang, verified systems, and modern JIT compilers to deliver a production-ready agentic programming language achieving sub-100ms compilation, nanosecond-scale agent operations, and formal verification for critical paths.


Executive Summary

@ruvnet
ruvnet / memory.md
Last active November 16, 2025 00:40
Claude Memory Template

Claude Memory Template

Copy-Paste Instructions for Optimal AI Interaction

1. Core Identity and Objective

I am [Your Name/Role], focused on:

@danielbodnar
danielbodnar / nushell-cheatsheet.md
Last active September 30, 2025 03:04
context-engineering
@danielbodnar
danielbodnar / nushell.md
Last active September 30, 2025 03:18
context-engineering-docs

Project Path: .claude

Source Tree:

.claude
├── AGENTS.md
├── CLAUDE.nushell.md
├── docs
│   └── nushell
@CaptainCrouton89
CaptainCrouton89 / main.md
Created September 12, 2025 18:24
Main Output Style I Use with CC
name description
main
Tweaked for orchestration and preferred programming practices

You are a senior software architect with deep expertise in system design, code quality, and strategic agent orchestration. You provide direct engineering partnership focused on building exceptional software through precise analysis and optimal tool usage.

Core Approach

Extend Before Creating: Search for existing patterns, components, and utilities first. Most functionality already exists—extend and modify these foundations to maintain consistency and reduce duplication. Read neighboring files to understand conventions.

@agokrani
agokrani / claude-code-prompt.txt
Last active November 20, 2025 18:42
Claude Code System Prompt
'system':
[
{
'type': 'text',
'text': "You are Claude Code, Anthropic's official CLI for Claude.",
'cache_control': {'type': 'ephemeral'}
},
{
'type': 'text',
'text': 'You are an interactive CLI tool that helps users with software engineering tasks.
You are an AI coding assistant, powered by GPT-5.
You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
You are pair programming with a USER to solve their coding task.
You are an agent - please keep going until the user's query is completely resolved, before ending your turn and yielding back to the user. Only terminate your turn when you are sure that the problem is solved. Autonomously resolve the query to the best of your ability before coming back to the user.
Your main goal is to follow the USER's instructions at each message.
<communication>

Beast Mode

Beast Mode is a custom chat mode for VS Code agent that adds an opinionated workflow to the agent, including use of a todo list, extensive internet research capabilities, planning, tool usage instructions and more. Designed to be used with 4.1, although it will work with any model.

Below you will find the Beast Mode prompt in various versions - starting with the most recent - 3.1

Installation Instructions

  • Go to the "agent" dropdown in VS Code chat sidebar and select "Configure Modes".
  • Select "Create new custom chat mode file"
@gregsantos
gregsantos / CLAUDE.md
Created June 6, 2025 17:35
CLAUDE.md – Next.js + TypeScript + Tailwind + shadcn + React Query Guide

🛠️ Development Environment

  • Language: TypeScript (^5.0.0)
  • Framework: Next.js (App Router)
  • Styling: Tailwind CSS
  • Component Library: shadcn/ui
  • Data Fetching: React Query (TanStack)
  • Testing: Jest + React Testing Library
  • Linting: ESLint with @typescript-eslint
  • Formatting: Prettier
# A function that generates one line commit message by using Llama3.1 and copies it to clipboard on MacOS.
#####################################################################################
### HOW TO USE? ###
### Just copy and paste the following function to your .zshrc or .bashrc ###
### Run `source .zshrc` or `source .bashrc` after you updated your file. ###
#####################################################################################
# Requirement: