Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use.
Inventory the AI-agent skills and instruction files installed on this machine. Scans where Claude Code, Codex, Cursor, Copilot, Windsurf, and other agents store skills and standing instructions, then reports what is actually there.
★not rated 14 1mo agoA
tokens not measured
originalApache-2.0
A project-aware full-stack specialist team. Every agent reads the project's .claude/agent-hub/profile.yml before acting, so the same team behaves differently per project.
★not rated 14 2mo agoA
tokens not measured
originalMIT
DPF-native agent skills for both Claude Code contributors (plugin namespace dpf-platform:) and in-portal coworkers (seeded as SkillDefinition rows by the extended seed-skills.ts loader). Single-source-of-truth contract: superset SKILL.md frontmatter feeds both surfaces from one file per skill. See README.md.
★not rated 14 yesterdayA
tokens not measured
originalApache-2.0
Create virtual workspaces that unify AI coding assistant configs (agents, commands, skills, hooks) across multiple sibling git repos. Works with Claude Code and Codex. Supports worktrees for synchronized multi-repo feature development.
★not rated 14 3mo agoA
tokens not measured
originalMIT
A plugin for coordinating several command-line AI agents through one interface, including Claude Code, Codex, Gemini CLI, and Copilot CLI. Its description is provided in Korean, and the excerpt does not list individual tools.
★not rated 14 6mo agoA
tokens not measured
originalMITarchived
New in 2.0.1: harness-doctor cadence promoted from prose to a SessionStart hook (30-day overdue check no longer silent); portability lint (BSD/GNU, zsh/bash pattern denylist) wired into pre-commit as the shell-layer sibling of the existing lints; branchclaim.sh gains an explicit warning that live-claim count is not a.
★not rated 14
changed 2d agoA
tokens not measured
originalMIT
Wire AnyRouter into Claude Code, Codex, Cursor, and other coding agents. Universal OpenAI-compatible router for 150+ models, with migration recipes from Anthropic, OpenAI, and OpenRouter, plus a remote MCP server for key and credit management.
NodeBench MCP — 244-tool development methodology server with context sandbox, progressive discovery, agent-as-a-graph embeddings, and toolset gating presets.
★not rated 14 yesterdayA
tokens not measured
originalMIT
The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent.
★not rated 13
changed todayA
tokens not measured
originalMIT
Turn a folder into a collaboration knowledge base for you, your AI, and your humans. Builds a SmartFolder: a tiered navigation-and-knowledge layer (root CLAUDE.md, per-folder guides, syntheses, sidecar summaries, and status surfaces) over your existing files, so knowledge lives in the folder instead of in an ephemeral.
★not rated 13
changed 6d agoA
tokens not measured
CC-BY-4.0
Your AI argues before it answers. Five-step decision loop for builders — GATE, LOOK, RESHAPE, ATTACK, CARD — built from Bezos's letters, Musk's algorithm, and Farnam Street's mental models. No more "you're absolutely right!".
Juni Skills Suite - Feature development workflows and context safety tools.
★not rated 13 7mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: