Claude Statusline Plus — Development skill for Claude Code
Claude Code status line segments: whether your prompt cache is still warm and what a cold start costs, and whether your 5-hour and weekly usage limits will last until they reset at the current pace, w.
How to install Claude Statusline Plus
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jimmc414/claude_statusline_plus and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Statusline Plus does
Claude Code status line segments: whether your prompt cache is still warm and what a cold start costs, and whether your 5-hour and weekly usage limits will last until they reset at the current pace, with the session doing the burning named.
Alternatives in Development
- Market Segments — Identify 3-5 customer segments with JTBD and product fit 7.8k ★
- Claude Usage Monitor — Claude Code statusline plugin for 5-hour/7-day quota, context usage, tokens, and reset countdowns in your term 51 ★
- Brow — Claude Code usage and rate limits in the MacBook notch 50 ★
README
claude_statusline_plus
Claude Code status line segments that show what the CLI knows but does not display: whether your prompt cache is still warm, and whether your usage limits will last until they reset.

cache warm 31m · 5h 12% (resets in 3h00m) · 7d 41% · Fable 50%
cache warm 31m · 5h 53% 3.9× cap 15:36 (resets in 4h20m) · 7d 38% · Fable 50% · top: refactor auth 57%
| Segment | The question it answers |
|---|---|
cache_warm.sh |
Is the prompt cache still warm, and what will a cold start cost? |
usage_forecast.sh |
At this pace, will my 5-hour, weekly and Fable limits last until they reset, and which session is burning them? |
statusline_plus.sh |
Runs both and joins what they print. The installer uses it when you have no status line of your own. |
Each segment is a standalone script with the same contract: status line JSON on stdin, one line on stdout, nothing at all when there is nothing to report, and always exit 0.
Problem
**The prompt cache.** Every request Claude Code sends includes the entire conversation so far. Prompt caching makes that affordable: a cached prefix is read at a fraction of the normal input price. But the cache expires after a period of inactivity, and nothing in the terminal tells you when. So you step away from a 300k-token session, come back 65 minutes later, type "ok, continue", and that one short message re-processes all 300k tokens at full price. On a subscription that is a visible bite out of your usage window. The expiry is invisible, and the cost lands on whichever message happens to come next.
**The usage limits.** A Claude subscription meters usage in a rolling 5-hour window and a weekly one. Claude Code hands the status line both percentages, but a percentage alone does not say whether you will make it. 53% is comfortable three hours into a window and a lockout forty minutes i
Related Skills
Token Hamster
🐹 Claude Code mod & plugin: usage monitor, token tracker & statusline. Live token usage, 5-hour session and w
Tokenite
A slim band above the Claude Code prompt: usage left and when it runs out, a warm or cold prompt cache, and wh
Ribbon
A slim band above your Claude Code prompt: usage left, reset times, and whether the prompt cache is warm or co
Zapara
Keep your head cold. How hard was today? zapara scores every hour you spent driving Claude Code, 0 to 100, fro
Clodfarm
clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open
Claude Prompt Cache Keepalive
Agent skill for Claude Code: keep the 1-hour prompt cache warm while you are away, with a ladder of background
Related Agents
Worker Apply Opus
Resumable implementation worker for non-SDD work units. Applies multi-file changes from a handoff, absorbs fol
Cost Estimator
Estimates Cloudflare Workers costs before deploying. Reads wrangler.toml, counts D1 tables/rows, estimates KV/
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break