Run pnpm scan-secrets on staged files and report findings in the conversation
cursor-rule
llm-loop
ANo problem foundvakovalskii/NeuralDeskApp
The agent loop in runner-openai.ts implements a ReAct-style agent that can:
llm-loop got grade A on our automated scan on 2026-10-25.
Details
Source
Public file: https://github.com/vakovalskii/NeuralDeskApp/blob/1b6b66452ce278294f0334996bc72bbd767ee2bd/.cursor/rules/llm-loop.md
Last scanned: (Oct 25, 2026, 2:07 p.m. ET)
Category: uncategorized
License: Present
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
Run full pre-PR validation (compile, lint, test) and report any issues
Use when publishing a beta or stable release, creating release tags, or following the release workflow
Primary skills location for project bootstrap and agent workflows.
Build the Remote Torrent Adder extension for dev or production, and understand the RTA_TARGET-driven Vite pipeline. Use when asked to build, watch, or load the unpacked extension, or when a build/typecheck/lint failure needs interpreting.