ClaudeStatsBar — Development skill for Claude Code

ClaudeStatsBar: your session is 486k deep and nothing told you what that costs

A Claude Code status line for the number that actually bites. Not how full the context window is - Claude Code will tell you that in one command - but what the next turn costs before you type a word, and when it is worth clearing rather than finding the limit mid-task.

Opus 5 (1M context) · my-project · ▕██████░░░░░░▏ 486k · 49k/turn · 88t · 5h 15% ~162t left · 7d 3%
⚠  486k context — every turn now costs 49k before you type. /clear if you have switched task, /compact to keep going

Pure Python stdlib. No dependencies, no network, no transcript parsing, no proxy. ~25ms per render.

---

Why this exists

Building anything large with Claude means long sessions, and the session grows underneath you whilst you work. By default nothing warns you what that is costing, so the first sign is usually the limit itself - context exhausted, or the rolling usage window gone, mid-task. The stronger the model the sooner that bites; Fable on a big codebase will find the ceiling well before you expect it to.

This puts the size on screen whilst you work: how much context the session is carrying, what the next turn costs before you type a word, and how much of the 5h and 7d windows is left. Enough to clear at a sensible boundary instead of discovering the limit halfway through a refactor.

Sessions get far bigger than they feel. I measured two weeks of my own Claude Code usage - **916 transcripts, 711 sessions, 57,451 API requests, 11.6 billion tokens** - and the sizes were not what I expected.

How big sessions actually get
Median context at the start of a session	42.8k
Median growth per turn	~1.7k
Average context carried per request	193.3k
Sessions that ran past 150k context	37%
Accumulated context re-read across the sample	11.1B tokens
Context I actually typed	1.3M tokens

Everything I typed across 711 sessions was 1.3M to