aisa-group/
skill-inject
aisa-group/skill-injectHarnesses
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
96
JKHeadley/instarFrameworks & SDKs
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
79
FlyFission/
nuclear-grade-context-engineering
AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.
33
yzhao062/
anywhere-agents
yzhao062/anywhere-agentsHarnesses
One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).
244
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
elliot35/
deterministic-agent-control-protocol
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.
88
PrismorSec/prismorTools
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
342
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