agent-usage-guard
a Claude Code mod to protect your usage window. A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan's usage, counts agents across every session, and asks in Claude Code's own dialog.
Open source
Reactions (1)
Similar products
by description similarity
a guard that blocks catastrophic agent actions
Your agent team, on your machine. Open-source harness for multi-user Claude agents.
Full Stack HQ
github.comClaude.md and Agent Stack for Claude Code
Claude Code Usage Monitor
github.comreal-time tracker to dodge usage cut-offs
A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.