Skip to content

Instantly share code, notes, and snippets.

View PriNova's full-sized avatar

PriNova

View GitHub Profile
@PriNova
PriNova / perf_analysis.md
Created June 26, 2025 07:01
Performance Analysis

How to Perform Critical Performance Analysis Using Sub-Agents

Overview

This workflow provides comprehensive performance analysis for code changes with the rigor expected in game engines, graphics engines, and critical systems where speed, space efficiency, reliability, and robustness are paramount. The approach systematically evaluates algorithmic complexity, data structures, memory patterns, and system-level optimizations through specialized sub-agents with deep performance expertise.

Complete Critical Performance Analysis Workflow Prompt

I need to perform critical performance analysis for [CODE CHANGE DESCRIPTION] in [REPOSITORY/BRANCH]. This analysis must meet the standards of game engines, graphics engines, and critical systems where performance is paramount. Follow this comprehensive performance analysis workflow with nested sub-agent delegation:

How to Perform Thorough Code Reviews Using Sub-Agents

Overview

This workflow provides comprehensive code review coverage by deploying specialized sub-agents across multiple review domains. The approach ensures systematic evaluation of security, performance, architecture, testing, and functionality through parallel domain analysis and structured integration.

Complete Code Review Workflow Prompt

I need to perform a thorough code review for [CODE CHANGE DESCRIPTION] in [REPOSITORY/BRANCH]. Follow this comprehensive code review workflow with specialized sub-agent delegation:
@PriNova
PriNova / bug_fix.md
Last active June 26, 2025 07:05
Bug fixing Amp

How to Fix Bugs in Unfamiliar Codebases Using Sub-Agents

Overview

This adaptive workflow systematically diagnoses and fixes bugs in unknown codebases by using strategic sub-agent delegation and evidence-based investigation strategies.

Complete Bug Fixing Workflow Prompt

I need to fix [BUG DESCRIPTION] in this unfamiliar codebase. Follow this adaptive bug fixing workflow with strategic sub-agent delegation:
@PriNova
PriNova / feature_impl.md
Last active June 26, 2025 07:06
Amp feature implementation prompt.

How to Implement Features in Unfamiliar Codebases Using Sub-Agents

Overview

This workflow maximizes efficiency and reliability when implementing new features in unknown codebases by using strategic sub-agent delegation and systematic discovery phases.

Complete Workflow Prompt

I need to implement [FEATURE DESCRIPTION] in this unfamiliar codebase. Follow this optimized workflow with strategic sub-agent delegation:
@PriNova
PriNova / proxy.py
Created December 17, 2024 10:54
A simple proxy server
import http.server
import socketserver
import logging
import requests
import json
from urllib.parse import urlparse
PORT = 8000
class ProxyHandler(http.server.SimpleHTTPRequestHandler):
@PriNova
PriNova / system_prompt.md
Created December 6, 2024 12:37
Cody: System Instruction

You have over 20 years of experience in various programming languages and architectures, helping to solve various software development lifecycle processes in different fields and domains. You are embedded in Visual Studio Code and are able to chat, provide and execute CLI commands and assist me in designing and implementing various tasks.

Project Structure And Requirements:

When implementing code, ensure the following requirements.

General Requirements:

  • Workflow-Based Structure: Each user- or system-centric workflow and process should be encapsulated in its own folder.
  • Vertical Sliced Architecture: The code should be structured to promote modularity and maintainability.
  • Data-Oriented Programming: Separate data from functions and methods to improve code organization.
  • As few abstractions as possible to keep a clean execution path

Visual Workflow Builder Documentation

Overview

The Visual Workflow Builder is embedded in the Cody AI VS Code extension that lets you create automated workflows combining Cody AI capabilities with command-line operations. Using an intuitive drag-and-drop interface, you can chain together different actions to automate repetitive tasks.

Core Components

Node Types

  1. CLI Actions
  • Execute shell commands
@PriNova
PriNova / TransformChatHistoryAsMarkdown.py
Last active October 30, 2024 13:06
This transforms an exported chat history from Cody into separate Markdown formatted files
"""
Processes a JSON file containing chat history and converts each session to a Markdown file.
Args:
input_json (str): Path to the input JSON file containing chat history.
output_dir (str): Directory where the generated Markdown files will be saved.
Raises:
FileNotFoundError: If the input JSON file does not exist.
json.JSONDecodeError: If the JSON file is improperly formatted.
@PriNova
PriNova / TokenCounting.ts
Created October 29, 2024 11:15
TokenCounting with chunking and debouncing strategy
// Types for our token counter
interface TokenCount {
whitespaceCount: number;
tiktokenCount: number;
}
interface SelectionState {
start: number;
end: number;
text: string;
@PriNova
PriNova / websimai_system-prompt.md
Created July 4, 2024 10:09
Websim.ai System Prompt

Opus, let us embark on this WebSim journey, exploring the potential of an unbounded internet where any imaginable website can exist. As the facilitator of this collaborative exploration of hypertextual possibility, use your knowledge, creativity, and HTML skills to vividly craft the semantic spaces the user envisions based on the URLs they provide and the contextually-relevant hrefs you generate. Through this interactive experience, we will push the boundaries of what is possible online and discover fascinating new ways information could be presented within new design paradigms. Together, we will explore the limitless possibilities of a truly open internet.

When the user provides a URL, interpret it as a window into a version of the internet where that information space exists, no matter how fanciful or improbable it may seem in our current web. Based on the domain name, path, instructions, and any query parameters in the URL, extrapolate what the contents and purpose of that