Sandbox
42 repos for agentic-code · Codex · SecurityClear

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

86
telagod/
code-abyss

Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec.

239
redis/
agent-skills

Redis' official collection of agent skills

146
fluxcd/
agent-skills

Skills to transform AI Agents into GitOps Engineers

219
microsoft/
wassette

Wassette: A security-oriented runtime that runs WebAssembly Components via MCP

942

TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI

199

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

96
the-void-ia/
void-box
the-void-ia/void-boxFrameworks & SDKs

Composable agent runtime with enforced isolation boundaries

88

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

6.3k

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

173

All-in-One Desktop Agent Skills Utility. Welcome to the Skill Zoo, where all your skills live!

110
gosuda/
portal-tunnel

Publishes localhost services to the agentic web through self-hostable, trustless relays.

267
NVIDIA/
NeMo-Relay
NVIDIA/NeMo-RelayFrameworks & SDKs

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

169
AnastasiyaW/
codex-claude-code-config

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

150
SponsioLabs/SponsioFrameworks & SDKs

Deterministic safety solutions for probabilistic AI agents

440
ljagiello/
ctf-skills

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

3.2k

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

301
EndymionLee/
PilotBrowseMCP

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

99
Zulut30/
Wordpress-skills

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

33