github-copilot

wshobson/agents

One plugin catalog, seven AI coding harnesses — A single Markdown-based source of 202 agents, 185 skills, 105 commands and 94 plugins installs across Claude Code, Codex CLI, Cursor, OpenCode, Antigravity, GitHub Copilot and Pi. Useful for developers juggling multiple AI coding tools who want shared agents and skills instead of maintaining separate configs per harness.

github/awesome-copilot

A curated hub of community add-ons for GitHub Copilot — This repo collects community-made agents, instructions, skills, plugins, and cookbook recipes for customizing GitHub Copilot. It now ships a searchable website, a Learning Hub with guides, and a machine-readable llms.txt for AI agents—useful for developers and tool builders extending Copilot workflows.

OthmanAdi/planning-with-files

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

jlcodes99/cockpit-tools

One cockpit for juggling every AI coding IDE account — A Rust-built desktop tool for managing accounts across 15+ AI IDEs and CLIs (Cursor, Copilot, Windsurf, Kiro, Codex, Trae, Zed and more). It adds one-click account switching, multi-instance running, quota monitoring, wake-up automation, and ships in 18 languages for macOS, Windows and Linux.

gamedev-skills/awesome-gamedev-agent-skills

74 engine-specific Agent Skills that teach AI coders game dev — A collection of 74 SKILL.md files covering Godot, Unity, Unreal, Phaser, PixiJS, three.js, Bevy, pygame, LÖVE and Roblox, installed via one CLI command. A router auto-detects your engine and task so the agent loads only relevant skills, plus a deterministic asset-production workflow for consistent art direction across Claude Code, Cursor, Kiro, Codex, Copilot and more.

microsoft/TokenEconomizer

Experience-Driven Black-Box Cost Control for Coding Agents

microsoft/apm

A package manager that makes AI agent setups portable — APM lets teams declare agent context, skills, prompts and MCP servers in one apm.yml manifest, then reproduce the full setup across tools like Copilot, Claude Code, Cursor and Codex with a single command. It supports transitive dependency resolution and plugin authoring, aimed at developers tired of manually configuring agent context per project.

vshulcz/deja-vu

A local memory layer that mines your coding agents' own session logs — Deja-vu indexes months of session history already saved on disk by Claude Code, Codex, Cursor and 39 other agents, then surfaces the relevant fix to whichever agent runs next. It works via local search, MCP and hooks with no LLM calls, shipped as a single Go binary, and reports 97.2% R@5 on LongMemEval-S.

kdlbs/kandev

A kanban-style control room for orchestrating coding agents — Kandev lets you organize parallel tasks across kanban/pipeline views and assign AI agents from multiple providers, with an integrated workspace (editor, terminal, browser preview, git diff) for reviewing their output. It ships as a self-hostable Go binary with no telemetry, aimed at power users who want fine-grained control over agent workflows and review gates rather than juggling separate terminal TUIs.

ericrisco/rsc-harness

A reviewable plan for setting up your coding agent's memory and skills — rsc-harness reads your project, asks about your goal and which assistants you use (18 targets including Claude Code, Codex, Cursor), then proposes a plan of skills, rules and MCP connections you approve before anything is written. It aims to avoid ad-hoc 'Frankenstein' agent setups by keeping project knowledge consistent across tools, installed via npx.

Entelligence-AI/agentplay

Replay your coding agent sessions as a map and a timeline

dembrandt/dembrandt-skills

Senior-level UX and design-system knowledge, packaged so your AI agent applies it automatically.