Opus 4.8 ▓▓░░░░░░░░ 22%Model plus a 10-block context-usage bar. Example statusline inspired by the Claude Code docs (code.claude.com/docs/en/statusline).
Claude Code status lines and mods that show token usage
12 status lines and 15 mods. These show how much of your context window is used. Pick one that shows a percentage for the exact figure, or a bar you can read at a glance.
Status lines and mods
Opus 4.8 high ✦ │ ctx 22% │ app (main) │ PR #1287 ● │ $0.41 · 10m +128 -34
Session ● ● ● ● ● ● ● ● ○ ○ ○ 74% left Resets in 2h 6m
Weekly ● ● ● ● ● ● ● ● ● ● ○ 93% left Resets in 2d 0h
Feature-rich bash status line with model, context bar, session cost (read live from Claude Code, so it stays correct on any model), rate-limit bars, and live tool/agent activity that adapts to terminal width. Source: github.com/JungHoonGhae/claude-statusline
✧ ███████████▋ 73% 🗝 Ultima Weapon ✦ app ∙ main
♥ ████████████████████████ 100% 「SAVE POINT」 ✶ Limit Form ◉ 41
Claude Code plan-usage HP bar that reads the Claude auth token to show remaining usage.
Opus 4.8 │ main │ app │ ▓▓░░░░░░░░ 44k/200k │ $0.41
Catppuccin Frappé–themed status line with model, git branch and dirty flag, folder, a block context bar, and session cost. Source: github.com/danjdewhurst/cc-status-line
app · main · Opus-4.8 · effort high · ctx 22% · 5h 26% ↻2h6m · 7d 7% ↻2d0hFolder, git branch, model (color-coded by family), effort, context usage, and 5h/7d rate-limit usage with reset countdowns — all on one line, each percentage going green → yellow → red as it climbs. Needs jq.
Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it.
🤖 Opus 4.8 [200K] │ 🎯 high │ 📁 app │ 🌿 main
📅 07/07/26 Tue │ ⏰ 22:59:15 │ ₿$63k │ ☀️ +90°F
Ctx: ● ▓▓░░░░ 33% [66K/200K] │ ⏱ 10m │ 🔧 2.1.155
A three-line bar that mixes coding metrics with ambient real-world data: model, context and git on top; date, time, live weather from wttr.in and the Bitcoin price from Coinbase in the middle; a context bar with real token counts, session cost and Claude Code version below.
5h ▓░░░░ 🟢
A minimal 5-slot block bar showing context-window usage with a green/yellow/red status dot. Source: github.com/gwiener/claude-burn-bars
[Opus 4.8] | ━━━━━━ 22% (44K/200K) | app | git:(main) | ⏱ 10m
Single-line status with a context bar, H/W usage limits, project, git branch, MCP server count, and a session timer, with cross-platform credential lookup. Source: github.com/AndyShaman/claude-statusline
Opus 4.8 │ ✍️ 78% │ app (main) │ +128/-34
Cost $0.4100
Tokens in 44.0k │ cache write 5000 │ cache read 2000 │ out 1.4k
Compact status line showing model, context remaining %, directory/git, session time and lines changed, with rate-limit bars or a cost/token breakdown. Source: github.com/susomejias/claude-statusline
◆ Opus 4.8 │ ▪ app │ ⎇ main │ ◷ 13:32 │ ██▄░░░░░░░ 26% (44K/167K) │ 26% ↻2h6m │ 7% ⟳2d0hNode status line with an autocompact-aware context bar (subtracts the compaction buffer), project, branch, last-activity time, and 5h/7d rate-limit segments. Source: github.com/philipshurpik/claude-code-status-line
Opus 4.8 │ ✍️ 22% │ app (main) │ ● high
current ●●○○○○○○○○ 26% ⟳ 3:35pm
weekly ○○○○○○○○○○ 7% ⟳ oct 20, 2:28pmTwo-block bash status line: model, context %, directory/git and session time up top, with 5h/weekly rate-limit bars below. Source: github.com/nilbuild/claude-statusline
Opus 4.8 main 22% $0.41Color-coded model, branch, context %, and session cost. Example statusline inspired by the Claude Code docs (code.claude.com/docs/en/statusline).
⎿ cache-tax: keepwarm on for 6h00m, a ping 50m after each idle stretch keeps the cache read, not
re-written
⎿ cache-tax: claude-opus-5-5
state warm, 1h00m left
context 44,000 tokens
cold cost $0.35 to re-write it (warm turn $0.01)
keepwarm on, 6h00m left · ping in 50m
break-even up to 40 pings at the read rate cost one cold write, about 33h20m of idle at one
ping per 50m
guard ask first (/cache-tax guard warn to only show the price)
session 0 cold writes paid, $0.00
[>] cache-tax · warm · keepwarm 6h00m left · ping in 50m [-]A Claude Code mod that keeps the one-hour prompt cache warm during breaks and asks before a cold send, showing its estimated rewrite cost. Warming uses model requests and costs tokens. Requires Claude Code 2.1.287+.
⎿ context-inspector: Context Inspector pane opened (shown in the terminal and the desktop app).
╭────────────────────────────────────────────────────────────────────────────────────────────────✕─╮
│ Context Inspector — main context │
│ Live ≈3.0k tokens in 12 items · 1 turn(s) · 0 compaction(s) · waste ≈0 │
│ ≈ = estimate (chars/4 × k=1.00, 0 calibration segment(s)); figures without ≈ are measured or en… │
│ │
│ Top occupants (live, by category) │
│ attachment:skill_listing ≈1.5k 50% █████░░░░░ 1 item(s) │
│ attachment:agent_listing_de… ≈685 23% ██░░░░░░░░ 1 item(s) │
│ attachment:environment ≈180 6% █░░░░░░░░░ 1 item(s) │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
⚠ context-inspector: ctx 22% · waste≈0Context waste analyzer for Claude Code: what fills the window, re-reads, near-duplicate outputs, what compaction kept, advice
The session's context window fill, right above the prompt: gray while there is room, yellow when it is time to /compact, red when a new session is better.
A cockpit for Claude Code: plan bars and subagent strips, context, usage limits with reset countdowns and burn rates, spend, the model route and a pet. Six bar styles, three collapsed looks. CLI and Desktop.
Flightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session events
A control room above your prompt: background agents and shells, disk space and context at a glance. Two themes, loud and quiet. /stand toggles the list.
▀▄ ▄▀ [-]
▀▀▀▀▀▀▀▀▀
▀▀▀▀▀▀▀▀▀
▀▄ ▄▀▀▀▀▀▀▀ ▀▀▀▄▄▄
▀▀▀▀▀▀▀▀ ▀▀▀▀▀▀▀▀
ctx 22% [ Pet ♥ ] [ ⚙ ] [ ↻ Adventurer ] [ Hide ]A little pixel cat that wanders above the Claude Code prompt, watches your usage limits and announces when work finishes; or switch packs for an adventurer who mines, chops trees and fights zombies
An animated pixel-art companion above your prompt that reacts to your session and your typing, with a live context meter.
Band above the prompt: turn number, output speed, turn and session cost, prompt cache countdown and context fill; notifies before the cache expires.
Shows branch safety, context headroom, and account usage in a compact session telemetry strip
· ↑ 37.0k ↓ 1.4k cache 7.0k · session ↑ 111.0k ↓ 4.2kEach turn's tokens and the session's running total, in color at the end of the hint line under the prompt.
A live forecast of the context window, drawn above the prompt: a weather icon, the fill percentage, and a chart of the last turns.
One line above the prompt: context tokens with their weather, a bar per recent prompt, your 5-hour and 7-day limits against the time elapsed, the prompt cache with its time left, the session cost with the last prompt's share in dollars and in points of the 5-hour limit, the subagents running, and a one-click pill for the GOs Claude proposes. Labels in English, French or Russian. After Token Weather (Anthropic, Apache-2.0) and the ideas of usage-meter (HolyGrail) and prompt-cache-control (Daniel San).
A band above the prompt showing your 5-hour and 7-day limits, context window and prompt-cache hit rate, styled for the terminal and the desktop app
Updated 2026-10-09
Common questions
How does a status line read token usage?
Claude Code pipes a JSON payload to your status line script on stdin each time the line refreshes. Token usage is under context_window. Read context_window.used_percentage for a percentage, or total_input_tokens and context_window_size for raw counts. used_percentage is null in a fresh session, so default it to 0 in jq with // 0. Every field Claude Code sends is in the status line guide.
How do I show a context bar instead of a number?
Take context_window.used_percentage, scale it to the bar width, and print that many filled blocks followed by empty ones. The bar-style ones above work this way.
Does the context window size change with the model?
It can. context_window.context_window_size carries the window for the current session, such as 200000 or 1000000. Divide by it instead of hardcoding 200k.