Show HN: agent-usage-guard – a Claude Code mod to protect your usage window

AI summary

A Claude Code mod called agent-usage-guard was released to protect usage windows by controlling subagent fan-out, heavy-context prompts, and retry loops.

Key points

•It holds subagent fan-out, heavy-context prompts, and retry loops before they spend the usage window.
•It reads the user's plan usage and counts agents across every session.
•It is developed as an extension for Claude Code aimed at protecting usage windows.

Read the original

#Generative AI Tools & Use #AI Agents#agent-usage-guard#Claude Code

#Generative AI Tools & Use#AI Agents#agent-usage-guard#Claude Code

Hacker News11/6/2026

Claude Code sends your email address to websites

A bug in Claude Code was reported where it leaks email addresses in User-Agent headers during web searches, causing users to receive numerous scam emails.

Hacker News11/6/2026

Show HN: Stroq – a local audit of what your coding agent did and why

Introduces Stroq, an open-source tool that finds known secrets in AI coding agent sessions like Claude Code, Codex, and Cursor, and guards the next session with local hooks that trace risky commands to their source content.

Hacker News11/5/2026