Your agent was asked to export a file. It also wrote a checksum nobody uses.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Your agent was asked to export a file. It also wrote a checksum nobody uses. Stop That Shit is a Skill + Guard for people using AI coding agents in Codex, Claude Code, OpenCode, Hermes Agent CLI, and Pi. It helps you keep an agent focused on the requested delivery by setting boundaries around scope, authorization, defensive work, and repeat verification. Key features: • Four failure modes – names scope creep, needless hashing or hypothetical hardening, intent violations, and task thrashing • Task modes – review, answer, monitor, change, and watch separate reporting, modifying, and observin
Posted by Dan Kornas (99.3k followers) 1 days ago · 6 likes · 724 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- AI copy can sound polished and still feel predictable. This skill file helps catch the… — @DanKornas
- 🔥🔥🔥 Claude 限时优惠，可以直接领取 $250 云端会话额度 — @kafkaup
- This inspired us! — @heyaskr
- The agent answered correctly. Then it tried to send the email. — @AiswaryaVenkit1
- Product work gets messy when every AI prompt starts from zero. — @DanKornas
- 两个视频让你直观看到 Opus 5.5 和 6 SOL 的差距有多大。 — @0xLogicrw
- mizchi/vlmkit が破綻なくUIを実装できるデモの一つ、 excalidraw クローンが作れる — @mizchi
- Lovable’s agent infrastructure records ~500M events on a typical weekday. — @FabianHedin
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23.4k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 10:22 UTC. Full method.