django

<p align="center"> <img src="assets/logo.png" alt="AI Coding Configuration" width="200"> </p>

<p align="center"> <a href="https://claude.ai"><img src="https://img.shields.io/badge/Claude_Code-D97757?logo=claude&logoColor=fff" alt="Claude Code"></a> </p>

AI Coding Configuration

Curated commands, agents, and rules for Claude Code, Cursor, Windsurf, and Cline.

What This Is

A shared configuration that works across AI coding tools. Commands automate workflows (PR handling, debugging, session management). Agents specialize in specific review types (security, performance, UX). Rules encode your coding standards so AI follows your patterns.

Quick Start

One-line install

Run this in your terminal — it auto-detects your tools (Claude Code, Cursor, etc.) and sets everything up:

curl -fsSL https://raw.githubusercontent.com/TechNickAI/ai-coding-config/main/scripts/bootstrap.sh | bash

Then configure for your project:

/ai-coding-config

Manual install (Claude Code)

If you prefer to install manually, run these in Claude Code:

/plugin marketplace add https://github.com/TechNickAI/ai-coding-config

/plugin install ai-coding-config

Todo Persistence Across Compaction

The problem: Claude Code's context compaction summarizes conversation history to stay within token limits. When this happens, your todo list vanishes - you lose track of what you were working on.

The solution: This plugin automatically saves todos to disk via hooks. After compaction, restore them:

cat ~/.claude/projects/$(echo $PWD | sed 's|/|-|g')/todos.md

Then use TodoWrite to restore your progress. Your todos survive compaction, session restarts, and even --resume across days.

Example Usage

# Triage PR bot comments (fixes real issues, declines nitpicks)
/address-pr-comments

# Load coding standards for current task
/load-rules

# Autonomous task execution: describe what you want, get a PR
/autotask "add user settings page with dark mode toggle"

What's Included

Commands

Slash commands that automate real workflows. Type /command-name to invoke.

Autonomous Development

`/autotask "description"` - Describe what you want, get a PR. Creates branch, implements, writes tests, handles bot feedback.

/autotask "add user settings page with dark mode toggle"

`/troubleshoot` - Connects to Sentry/HoneyBadger, analyzes errors, fixes bugs in parallel worktrees, submits PRs with root cause analysis.

`/verify-fix` - Confirms fixes actually work before claiming success. Runs tests, checks live behavior.

PR & Code Review

`/address-pr-comments` - Triages bot comments: fixes real issues, declines nitpicks, iterates until merge-ready.

`/multi-review` - Runs multiple specialized reviewers in parallel. Security, logic, performance, style - all at once.

Context & Session Management

exactly where you left off - even in a new conversation.

/session save "auth-refactor"    # Save current session
/session resume                   # Resume where you left off

`/load-rules` - Loads relevant coding standards for your current task. Working on React? Loads React patterns. Writing tests? Testing standards.

`/handoff-context` - Generate context handoff for new sessions.

Project Setup

`/ai-coding-config` - Interactive setup for new projects. Detects your stack, installs relevant rules.

`/repo-tooling` - Set up linting, formatting, CI/CD based on detected language.

`/setup-environment` - Initialize dev environment for git worktrees.

Other Commands

• •/cleanup-worktree - Clean up worktrees after PR merge
• •/generate-AGENTS-file - Generate AGENTS.md for AI context
• •/generate-llms-txt - Generate llms.txt for LLM navigation
• •/knowledge - AI Product Manager - maintain living product understanding
• •/personality-change - Switch AI communication style
• •/product-intel - Competitive intelligence research

Agents

24 specialized assistants that Claude Code invokes automatically based on context.

Building Features

Debugging

Code Review - Correctness

Code Review - Performance

Code Review - UX

Code Review - Architecture

Polish & Documentation

Skills

Autonomous capabilities with multi-step workflows.

Rules

Coding standards in .mdc format (markdown with frontmatter). AI reads these to understand your conventions.

Always active:

• •git-interaction.mdc - Git workflow, commit messages, PR standards
• •prompt-engineering.mdc - Writing prompts for LLMs
• •heart-centered-ai-philosophy.mdc - Presence before solutions

Framework-specific (loaded by /load-rules):

• •frontend/react-components.mdc - React patterns and hooks
• •frontend/typescript-standards.mdc - TypeScript conventions
• •python/python-coding-standards.mdc - Python conventions
• •django/django-models.mdc - Django ORM patterns
• •observability/logfire.mdc - Logging with Logfire
• •And 25+ more...

Personalities

Change how AI communicates. Same technical capabilities, different style.

Activate: /personality-change samantha

Architecture

┌─────────────────────────────────────────┐
│  ai-coding-config                       │
│  (commands, agents, rules, skills)      │
└─────────────────────────────────────────┘
              │
      Plugin system / Bootstrap
              │
      ┌───────┴───────┐
      │               │
      ▼               ▼
  Project A      Project B

Plugin-first - All distributable content lives in plugins/:

ai-coding-config/
├── .claude-plugin/marketplace.json   # Plugin manifest
├── plugins/
│   ├── core/                         # Main plugin
│   │   ├── commands/                 # 18 workflow commands
│   │   ├── agents/                   # 24 specialized agents
│   │   ├── skills/                   # 6 autonomous capabilities
│   │   └── hooks/                    # Todo persistence hooks
│   └── personalities/                # 7 personality variants
├── .cursor/rules/                    # 33 coding standards (.mdc)
├── docs/                             # Guides
└── scripts/                          # Installation

Updates

Update configurations in any project:

/ai-coding-config update

Shows what changed, lets you choose what to update, preserves your customizations.

Requirements

Basic usage:

• •Claude Code, Cursor, Windsurf, Cline, or any AI tool with rules support

For autonomous workflows (/autotask, /troubleshoot):

• •Git with worktrees support
• •GitHub CLI (gh) installed and authenticated

Documentation

• •Coding Ecosystem Comparison - Cursor vs Claude Code vs

Windsurf

• •Tools and Configs Guide - Rules vs commands vs agents
• •Personalities Guide - All personalities with examples
• •Architecture - System design
• •Development Workflow - Autonomous workflow

philosophy

• •Contributing - How to contribute

Philosophy

• •Plugin-first - Everything distributable lives in plugins/, other locations

symlink

• •Single source of truth - Configurations symlinked, never duplicated
• •Cross-tool compatibility - Works with Claude Code, Cursor, Windsurf, and others
• •Human control - AI prepares, human decides (especially for commits)

Discovery

This marketplace is indexed at claudemarketplaces.com - the searchable directory of Claude Code plugins.

Repository: https://github.com/TechNickAI/ai-coding-config