Last commit on September 24, 2026·Created on August 11, 2026
lennney/stop-that-shit
“Prevents task-scope creep and speculative overengineering in AI coding agents”
Combined rank
#168
across all skills
Stars
2.4k
+8.5% in last 7d
Forks
51
+2.0% in last 7d
Watchers
3
0.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR
This skill acts as a guard for Codex and GPT workflows, ensuring AI agents adhere to explicit task boundaries. It is designed for automation builders who need to intercept unrequested hashes, checksums, and repetitive verification loops that deviate from the original request.
By identifying when an agent is introducing unnecessary hardening or speculative defenses, the skill helps maintain a lean development process and prevents the AI from expanding the project scope without authorization.
WHO IT'S FOR
AI agent / automation builders
preventing task-scope creep in AI coding agents
Technical leads / architects
reducing overengineering and speculative defenses in AI work
Platform / DevEx teams
enforcing machine-bound boundaries on AI action paths
Technical writers / researchers
removing defensive hedging from decision-facing writing
Claude
Codex
OpenCode
Hermes
PiWant to install it?
Claude Plugin · Clone to Claude · Manual Copy · NPX Skills AddRepository instructions