A safety-focused plugin for AI coding agents that keeps them running, protects data, and improves planning.
autorun is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add ahundt/autorunRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
12 GitHub stars indicate community interest.
2 open issues signal maintenance load.
NOASSERTION license detected.
3 security/trust notes recorded.
Setup difficulty is 3/5.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.
A multimodal toolset for AI agents to generate, edit, and display images, videos, and audio via CLI.
This tool adds safety features to AI coding assistants like Claude Code and Codex. It can stop dangerous commands, control file creation, and help the AI plan better. It also lets the AI resume tasks after interruptions.
autorun is a plugin and extension for AI coding agents, including Claude Code, Codex, Gemini CLI, and others. It focuses on safety, reliability, and planning. Key features include native safety hooks that intercept tool calls, file policies to control file creation, command guards that redirect dangerous commands (like 'rm' to 'trash' guidance), and stop hooks that resume incomplete tasks. It also offers optional planning capabilities with stages for implementation, evaluation, and verification. The tool provides a set of slash commands for tasks, plans, and safety, and integrates with tmux for session management. It supports multiple AI harnesses and can be installed via UV.
12
Stars
2
Forks
2
Issues
NOASSERTION
License
A safety-focused plugin for AI coding agents that keeps them running, protects data, and improves planning.
Developers using Claude Code or Codex who want safer AI interactions., Teams that need to enforce file management policies with AI agents., Power users who want to automate complex tasks with AI and need reliability.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The tool can execute commands on your system; ensure you trust the AI agent and review its actions. File policies may be bypassed if the agent finds a workaround; use with caution.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, hyperframes.
Aug 20, 2026