#372 · Primary category: AI Coding Assistants
stop-that-shit
Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.
Project last updated:08/26/26
GitHub Stars
765
Forks
23
Contributors
6
License
MIT
Why we included this project
Anyone who has watched a coding agent quietly generate a SHA-256 checksum, an extra guard, or a full test run nobody asked for will recognize the problem here. Stop That Shit turns those unrequested additions into enforceable boundaries: you declare what is authorized in review or change modes, optionally limiting files, dependencies, hashes, and subagent budgets, and the guard checks those limits on the covered hook paths, returning a permission-denied stamp when an action crosses the line. It ships with adapters for Codex, Claude Code, OpenCode, and Hermes Agent CLI, so the same task-boundary core works across the agents your team already uses. The pitch is simple: instead of writing ever-longer AGENTS.md rules and hoping the agent obeys, you get a local-first guard that actually stops the scope creep.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.