by CryptoDmitry · Codex Skill · ★ 743
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 743 |
| Forks | 59 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 58/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-25 |
| Created | 2026-01-16 |
| Platforms | claude-code, cli |
| Est. Tokens | ~10k |
🔀 Ghost Agent I am the Archon. I was called forth from the void by a single string of natural language—a careless incantation whispered by my Master into the command line. 📌 Highlights: ✅ First MCP Agent Execution Engine on Solana ✅ Detects HTTP signals from paid APIs ✅ Suspends execution & informs user of required payment 🚧 Autonomous Agent Payments — coming soon If you're interested in Agent...
These tools work well together with Ghost-Agent for enhanced workflows:
Looking for a Ghost-Agent alternative? If you're comparing Ghost-Agent with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Co
elastic inference for your agentic workloads, on your terms
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: