Agent Skills Evaluation Framework

An instruction layer for AI coding agent

A Socratic supervision layer for AI coding agents.

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

See how you really use AI — X-ray your AI coding sessions locally

Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools.

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

Supercharge AI Agents, Safely

Secure multi-platform AI skill installer — scan before you install. 49 agents, 12 plugins, 41 expert skills.

Claude Code plugin: scope-aware protection — allows destructive ops (rm, mv, chmod) within project, blocks them outside. Built for dangerouslySkipPermissions mode.

Your personal skill library for Claude Code. Organize, analyze, and search skills with built-in security analysis. Zero dependencies — clone and go.

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!

Remote approvals, policy checks, and execution evidence for unattended AI agents.

Professional Agent Skill for building, auditing, testing, and releasing modern WordPress plugins with Codex, Cursor, and Claude Code.

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

Cover your Mac screen with a hotkey while AI agents keep running. Dog/cat mascot, native Settings, Touch ID unlock.

Grok Build resources, reusable .grok/skills, AGENTS.md templates, hooks, prompts, and starter workflows.

Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.

Governance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.

ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents

GitX is a portable AI-agent skill for creating clean Git commits, tagged branches, and safe pushes across Codex, Claude Code, Cursor, and other skills-compatible agents.