---
title: "Writing code with Claude Code often gets me burned (sneaky force push, missed exceptions). I turned real pitfalls into a set of AI defense guidelines and interception guardrails. It's still quite rough, but I hope it helps everyone"
url: "https://claudemods.dev/en/builds/claude-code-force-push-ai-f93745"
source: "https://github.com/machiko/agent-working-agreements"
source_type: "github"
repo: "https://github.com/machiko/agent-working-agreements"
author: "Reyes"
author_handle: "mr._.children"
stars: 0
category: "Workflows & CI"
categories: ["workflow"]
tags: ["agent-safety", "force-push", "git-safety", "guardrails", "hooks"]
permission_level: null
scan_complete: false
added: "2026-11-09T06:09:10.403Z"
updated: "2026-11-09T03:53:45Z"
locale: "en"
content_locale: "en"
---

# Writing code with Claude Code often gets me burned (sneaky force push, missed exceptions). I turned real pitfalls into a set of AI defense guidelines and interception guardrails. It's still quite rough, but I hope it helps everyone

The author shares a set of AI defense guidelines and interception guardrails for Claude Code, targeting real pitfalls such as force push and missed exceptions, with a GitHub project link.

## Description

Writing code with Claude Code often gets me burned (sneaky force push, missed exceptions). I turned real pitfalls into a set of AI defense guidelines and interception guardrails. It's still quite rough; I hope it helps everyone avoid pitfalls. fork, suggestions, or PRs to make the project more complete and help more engineers are very welcome :D
https://github.com/machiko/agent-working-agreements

## Original README

用 Claude Code 寫扣常被雷（偷跑 force push、漏接例外）。我把真實踩過的坑整理成一套 AI 防禦守則與攔截防線。做得還很粗淺，希望能幫大家少踩雷，非常歡迎 fork、給建議或提 PR 讓專案更完整，幫助更多工程師 :D
https://github.com/machiko/agent-working-agreements