stop-that-shit

stop-that-shit

Prevent unwanted hashes, checksums, and scope creep from AI coding agents.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 1.1k
Source
skill-github

Overview

Stop That Shit is a multi-platform Hook + Skill Guard designed for Codex/GPT scenarios, blocking unnecessary hashes, checksums, and preventing task scope expansion generated by AI coding agents. It enforces strict task boundary checks to ensure AI agents perform only the actions explicitly requested. Supports various coding agents including Codex, Claude Code, OpenCode, and more. Ideal for developers requiring tight control over AI agent behavior.

Capabilities

  • Block unwanted hashes and checksums
  • Prevent task scope creep
  • Enforce clear task boundary checks
  • Support multiple coding agents

Use cases

Prevent AI agents from generating unnecessary filesLimit AI agents' modification permissionsEnsure AI agents act only when neededImprove code review efficiency

Setup

Requires: Node.js 18+API Key
Install the plugin using the appropriate command based on your coding agent. For example:
- Claude Code: `claude plugin validate .` and `claude plugin install stop-that-shit@stop-that-shit`
- Codex: `codex plugin marketplace add lennney/stop-that-shit --ref 0.2.0` and `codex plugin add stop-that-shit@stop-that-shit`

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which coding agents does Stop That Shit support?

Supports Codex, Claude Code, OpenCode, Hermes Agent CLI, and Pi Coding Agent.

Related skills