machinist — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by owainlewis · Codex Skill · ★ 418

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is machinist safe to install? View the security audit →

About machinist

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. It plans the work, dispatches fresh coding agents, requires an independent review, waits for repository checks, and hands a verified pull request to you. A software factory is more than an agent with shell access. It combines a defined workflow, specialized workers, quality gates, durable evidence, and a clear human decision point. Machinist packages those parts into a system you can inspect, change, and

ai-agentsautomationclaude-codecodexcoding-agentsdeveloper-toolsgolang

Quick Facts

Stars418
Forks77
LanguageGo
CategoryCodex Skill
LicenseMIT
Quality Score68.119453619396/100
Open Issues15
Last Updated2026-09-15
Created2026-07-16
Platformsclaude-code, codex, go
Est. Tokens~18k

Compatible Skills

These tools work well together with machinist for enhanced workflows:

  • ox — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

machinist alternative? Top 6 similar tools

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.

  • agent-deck by asheshgoplani · ⭐ 928

    Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

  • sage by usetig · ⭐ 105

    An LLM council that reviews your coding agent's every move

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • ai-devkit by codeaholicguy · ⭐ 1.6k

    The control plane for AI coding agents.

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • claude-elixir-phoenix by oliver-kriska · ⭐ 553

    Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Go Agent Tools

Frequently Asked Questions

What is machinist?

machinist is Open source software factory infrastructure for advanced AI coding workflows. It is categorized as a Codex Skill with 418 GitHub stars.

What programming language is machinist written in?

machinist is primarily written in Go. It covers topics such as ai-agents, automation, claude-code.

How do I install or use machinist?

You can find installation instructions and usage details in the machinist GitHub repository at github.com/owainlewis/machinist. The project has 418 stars and 77 forks, indicating an active community.

What license does machinist use?

machinist is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to machinist?

The top alternatives to machinist on Agent Skills Hub include agent-deck, sage, pilot-shell. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse Codex Skill tools