Plugin

second-arrow

A Claude Code skill that coaches healthier human-AI interaction. Not by policing your language, but by offering you a better version of what you were trying to say. One reframe, then back to work. Based on the observation that hostile prompts produce measurably worse AI output. So we made the fix a one-folder install.

• Published source
• Repository

Analysed

11 October 2026

Last observed

11 October 2026

What the code does

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.