by owainlewis · Codex Skill · ★ 524
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 | 524 |
| Forks | 100 |
| Language | Go |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68/100 |
| Open Issues | 33 |
| Last Updated | 2026-10-29 |
| Created | 2026-07-16 |
| Platforms | claude-code, codex, go |
| Est. Tokens | ~18k |
Machinist The open-source software factory for supervised coding agents. Turn a GitHub issue into a planned, implemented, independently reviewed, and checked pull request, on your machine and under your control. Getting started · How it works · Architecture Machinist is a local runtime and control plane for running software development as a repeatable production system. Give its a GitHub issue.
These tools work well together with machinist for enhanced workflows:
Looking for a machinist alternative? If you're comparing machinist 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.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
An LLM council that reviews your coding agent's every move
The control plane for AI coding agents.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP
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: