Make coding agents ask before they delete, push, deploy or migrate
A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check.
Source
@404kidwiz2 on X · 2026-10-20
Written in our own words. Credit to the original author. Link checked 2026-10-20.
What they did
A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check.
Result (as claimed)
Free public beta.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo; Cursor: free plan, paid from $8/mo.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude Code, OpenAI Codex, Cursor. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Make coding agents ask before they delete, push, deploy or migrate What the original author did: A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check. Reported result (as claimed by the author): Free public beta. Source: https://x.com/404kidwiz2/status/2112348037221581010 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Make coding agents ask before they delete, push, deploy or migrate What the original author did: A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check. Reported result (as claimed by the author): Free public beta. Source: https://x.com/404kidwiz2/status/2112348037221581010 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Make coding agents ask before they delete, push, deploy or migrate What the original author did: A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check. Reported result (as claimed by the author): Free public beta. Source: https://x.com/404kidwiz2/status/2112348037221581010 Tools they used: Claude Code, OpenAI Codex, Cursor Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to run multiple coding agents together · How to vibe code an app with Claude Code · How to make AI agents ask for approval before they act · How to use Claude Code skills and plugins
Related use cases
Clean up the disk space your coding agents leave behind
Every coding agent task can leave a full copy of a repo on disk. The builder checked his machine and found 40 branches safe to delete and 15.1 GB of old node_modules and build folders across 62 repos, so he built Lopper to find and clear them.
Run coding agents side by side with shared memory, undo and phone access
Pando runs Claude Code, Codex, Grok and Cursor side by side with one shared memory, undo for any task, tests after every change and vibe coding from your phone.
Give coding agents a local code graph and project memory with cited excerpts
Graphicle maps your repo into a code graph, remembers docs, decisions and past agent sessions, and hands Claude Code, Cursor or Codex the exact files and lines. It runs locally with no API key, account or telemetry.
Watch all your coding agents in a calm pixel room on your Mac
Shrine shows what your Claude Code, Codex, OpenCode, Cursor and Grok Bot sessions are doing on your Mac; pushes and merged PRs furnish a small pixel room.