← Browse
ar
ahundt ★ 13
autorun adds safety hooks and autonomous execution guards to AI coding assistants, preventing unintended operations like destructive shell commands and ensuring agents complete tasks rather than stopping prematurely. It installs hooks, commands, and skills across Claude Code, Codex, Qwen Code, Pi, and five other agent platforms with customized interfaces for each.
Install
> /plugin marketplace add ahundt/autorun/tree/HEAD/plugins/autorun
> /plugin install ar
Source: https://github.com/ahundt/autorun/tree/HEAD/plugins/autorun
What it's made of
51 commands · 2 agents · 17 skills · 7 hooks
- Commands
- 51
- Agents
- 2
- Skills
- 17
- MCP servers
- 0
- Hooks
- 7 · PostToolUse, PreCompact, PreToolUse, SessionStart, Stop, SubagentStop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (ahundt).