by autonomous-ai · Codex Skill · ★ 78
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Agents that build things, in one window: code with Claude Code, Codex and 12 more, PCBs with Copper, 3D parts with Solid, keynotes with Marp. Persistent terminals on every machine you own, end-to-end encrypted, no SSH. Desktop app, daemon, relay, USB device.
| Stars | 78 |
| Forks | 13 |
| Language | C |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 54.6029118118812/100 |
| Open Issues | 18 |
| Last Updated | 2026-09-17 |
| Created | 2026-08-04 |
| Platforms | browser, claude-code, codex |
| Est. Tokens | ~14k |
These tools work well together with autonomous-harness for enhanced workflows:
Looking for a autonomous-harness alternative? If you're comparing autonomous-harness 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.
Close the lid and walk away — every window, desktop and terminal on your machines, live in any browser. E2E-en
Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes codi
Self-hosted browser workspace to run coding agents in parallel, steer work as it runs, review diffs, and ship.
An LLM council that reviews your coding agent's every move
Code from anywhere — Telegram bridge for AI coding agents (Claude Code, Codex, OpenCode, Pi, Gemini CLI, Amp).
A remote, phone-first console for your tmux — agent-agnostic, no database. Spawn and watch coding agents in pa
Explore other popular codex skill tools:
autonomous-harness is Agents that build things, in one window: code with Claude Code, Codex and 12 more, PCBs with Copper, 3D parts with Solid, keynotes with Marp. Persistent terminals on every machine you own, end-to-end . It is categorized as a Codex Skill with 78 GitHub stars.
autonomous-harness is primarily written in C. It covers topics such as agent-harness, ai-agents, cad.
You can find installation instructions and usage details in the autonomous-harness GitHub repository at github.com/autonomous-ai/autonomous-harness. The project has 78 stars and 13 forks, indicating an active community.
autonomous-harness is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to autonomous-harness on Agent Skills Hub include Reminal, sesori_apps_monorepo, garcon. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: