Allow Claude Code to self-monitor token usage and auto-resume after rate limit reset

Preflight Checklist

• [x] I have searched existing requests and this feature hasn't been requested yet
• [x] This is a single feature request (not multiple features)

Problem Statement

Currently, when Claude Code hits a usage/rate limit during a long task, the session is blocked and the user must manually resume after the limit resets. Claude has no visibility into its own token consumption or remaining quota.

Proposed Solution

Expose token usage / remaining quota info within the session (e.g., percentage used, reset timestamp)
When approaching the limit (e.g., 95%), Claude could proactively pause, read the reset time, and use ScheduleWakeup to automatically resume at the exact reset moment
This would enable fully unattended long-running tasks without manual intervention
Why this is currently impossible:
This is a catch-22: Claude can't set a timer because it's already blocked when the limit hits, and it can't preemptively pause because it has no visibility into usage. Solving either side would unlock the other.

Alternative Solutions

_No response_

Priority

Critical - Blocking my work

Feature Category

CLI commands and flags

Use Case Example

Users running complex multi-step tasks (e.g., batch data entry, large refactors) that exceed a single rate limit window.

Additional Context

_No response_