Add context usage information to statusline JSON input

Resolved 💬 2 comments Opened Oct 30, 2025 by swirltoenail Closed Oct 30, 2025

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

Summary

The statusline script currently receives JSON input from Claude Code but doesn't include information about the current context window usage. This makes it impossible to accurately display context percentage in custom statuslines.

## Current Behavior
The JSON passed to statusline scripts includes:

  • session_id
  • transcript_path
  • exceeds_200k_tokens (boolean)
  • cost information

However, it doesn't include:

  • Current total tokens in context
  • Maximum context window size for the model

The /context command shows accurate context usage (e.g., "94k/200k tokens (47%)"), but this information isn't available to statusline scripts.

Proposed Solution

Please add the following fields to the statusline JSON input:

```json
{
"context": {
"current_tokens": 94000,
"max_tokens": 200000,
"percentage": 47
}
}

Alternative Solutions

Currently, there's no reliable workaround since the transcript only stores per-message usage, not cumulative context size.

Priority

Medium - Would be very helpful

Feature Category

CLI commands and flags

Use Case Example

This would enable custom statuslines to display real-time context usage, helping users:

  • Monitor conversation length at a glance
  • Know when they're approaching context limits
  • Match the information shown in /context in their terminal prompt

Additional Context

_No response_

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗