ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RT

Shob – an AI agent that delivers high-quality coding & automation work

My awesome dotfiles :rocket:

OhMyPi (OMP) Agent Framework Spec-Driven Development infrastructure for Oh My Pi. Skills transform artifacts through a deterministic engineering workflow.

Governed AI workflow orchestration for complex software development, coordinating specialist skills, validation, security review, human gates, and execution continuity.

One reliable canonical source for AI coding agent rules, commands, skills, MCP, hooks, and permissions — synced across AI coding assistants.

macos/linux: terminal, editors, shell, AI harness

:feet: All of my configuration files for all the things

A simple repo that elegantly manages my configs and scripts.

Arch Linux dotfiles and opt-in workstation automation with Ansible, go-task, uv, and Neovim

Cross-device sync for Claude Code, Codex, OpenCode configs

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

A personal, evidence-based reference for how Claude Code is used day-to-day: real skills, workflow habits, and global config, organized by Laravel, Angular, React, and Java/Spring Boot. No generic advice—every entry traces to a real skill f

My Claude Code configuration: 29 agents, 60 commands, 60 skills, 65 rules. Built on everything-claude-code + obra/superpowers.

Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.

Turn a ticket into a reviewed pull request, under gates that stop work which drifted out of scope or weakened tests. Compiles one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions.

Web-based mission control for running multiple AI coding agents (Claude Code, Codex, Gemini CLI, Aider) simultaneously — live dashboard, auto-approval rules, structured review queue

A personal Claude Code setup script.

Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.

Claude Code project template: five agent roles with tool-level permission boundaries, four workflow commands, and a permission baseline that keeps secrets and build noise out of context. Built on native worktrees and subagents — no third-pa

My dotfiles for my little linux. I use the beautiful and majestic Arch Linux. Not Arch anymore, now I'm a Fedora Chad.

—

My agent setup for Claude Code, Codex, Cursor, Grok and opencode: shared rules, six subagents, a git guard hook and 14 skills, with an installer that copies files and merges settings.

One canonical AI agent config (rules, skills, MCP servers) rendered into Claude Code, Codex, Copilot CLI and Antigravity by acsync

One source of truth for MCP servers, skills and slash commands across Claude Code, OpenCode, Codex, Zed and more — plus classic dotfiles.

macOS dotfiles as a start-here template: stow-style symlinks + idempotent installer, shared multi-profile Homebrew, tmux/Ghostty with OSC 52 clipboard and ssh-nested prefixes. Fork, personalize, clone, install.

—

Shared configs and workflows for AI coding agents (Claude Code, OpenCode, Codex). Includes custom commands, subagents, and MCP server integrations.

—