Open-source adversary emulation for AI agents and MCP servers.
577
netresearch/
security-audit-skill
Agent Skill for PHP security audits - OWASP patterns, vulnerability detection | Claude Code compatible
41
Evol-ai/
SkillCompass
Evol-ai/SkillCompassTools
Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.
216
wshobson/
agents
wshobson/agentsCollections
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity
40k
agentrhq/
authsome
agentrhq/authsomeConnectors
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
88
netresearch/
claude-code-marketplace
netresearch/claude-code-marketplaceCollections
Curated Agent Skills collection for AI-assisted development. Open standard — agentskills.io. Portable across Claude Code, Cursor, Copilot, Codex, Gemini CLI, and 30+ more agents. By Netresearch.
56
CodeAlive-AI/
ai-driven-development
Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.
132
ruvnet/
metaharness
ruvnet/metaharnessHarnesses
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).
645
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
1.5k