SLOPSHOPPER

token-weather

A live forecast of the context window, drawn above the prompt: a traffic light, the fill percentage, and a chart of the last turns.

newband
v0.2.1Apache-2.0updated 2026-10-12akaz01/claude-mods/plugins/token-weather
A shopper browsing a rack in a slop shop
Preview · a replayed session in a sandbox
claude · ~/work/app · token-weather
› fix the failing auth test and add an audit log call ⏺ Read(src/auth.ts) ⎿ Read 6 lines ⏺ Update(src/auth.ts) ⎿ Added 2 lines, removed 1 line ⏺ Bash(bun test) ⎿ 3 pass, 1 fail ● Done. refresh now rejects expired claims and logs an audit event. ✻ Worked for 42s · done 4:20 PM ● Go 49% of context 97.4k / 200k last turns █ ⟨Claude Code's own drawing⟩ ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── › ? for shortcuts

Draws

Band
● Go 49% of context 97.4k / 200k last turns █ ⟨Claude Code's own drawing⟩
README

Token Weather

A Claude Code mod that draws a live forecast of your context window in the band above the prompt. We're sharing it as the smallest of the three mods here: one hooks module that reads real usage figures and draws one line of UI.

What this shows

 ☂  Showers  67% of context  134.4k / 200k   last turns ▁▂█  ▲ +98.3k last turn

After each turn, the band shows:

  • a weather icon and word for how full the window is,
  • the percentage used, and the tokens used out of the window,
  • a chart of the last 12 turns, drawn with block characters, and
  • how much the last turn added.
UsedForecast
under 25%☀ Clear
25–49%☁ Cloudy
50–74%☂ Showers
75–89%☇ Storm
90% up↯ Compact soon

The numbers are real, not estimated. After each main-loop turn, the mod calls $.session.usage() and reads context:

  • tokens: the input tokens the last response was answered over (uncached, cache-written and cache-read together),
  • window: the context window of the session's model, and
  • percent: tokens over window.

These are the same figures the status line shows (total_input_tokens, context_window_size, used_percentage). The call is free, because the mod doesn't ask for a breakdown, so it sends no token-count request.

HookWhat it does
session.startTakes a first reading, so the band shows before the first turn.
turn.completeTakes a reading after each main-loop turn. Subagent turns are skipped.
ui.render with {component: "AbovePrompt"}Draws the band as one line.

Demo

After the first turn, 18% full:

Token Weather reading Clear at 18% of context

After reading four large files, 67% full:

Token Weather reading Showers at 67% of context

After one more file, 81% full. Claude Code's own notice reads 90%, because it counts toward the auto-compact point (see the limitations):

Token Weather reading Storm at 81% of context

How it was built

  • Model: built with Claude in Claude Code. The test runs and screenshots used Claude Haiku 4.5, because its 200k window shows the forecast change within a few turns. The mod itself doesn't call a model.
  • Prompt(s): the mod started as one of ten ideas Claude wrote for mods. This is the idea as written:

Token Weather. A live forecast of your context window. A band above the prompt draws a small chart of context use for each turn, as weather icons. It's clear when the window is mostly empty, and stormy when it's nearly full. It uses ui.render on the AbovePrompt component, with the Svg element, and it updates on turn.complete. I haven't confirmed which event or call gives the token counts, so that needs a check. Developers would share it because it looks good in a screenshot, and it answers "why did Claude forget that?" at a glance. The status line only shows text. A weekend build.

The build prompt, which picked this idea and two others by number:

implement 1,2,7. give me zips for them. test them in claude code and get me screenshots of what they look like when used.

  • Transcript: not shared. The build ran in an internal workspace.
  • Iterations:
  • The idea left open where the token counts come from. The build found $.session.usage(), which returns the same figures as the status line, so the mod shows real numbers rather than an estimate.
  • The idea drew the chart with the Svg element. The terminal can't draw Svg, so the chart is a row of block characters.
  • The first icons were emoji, which weren't in the test terminal's font. The mod uses single-width text symbols instead, which line up in any terminal font.
  • Tested in Claude Code on a test repo of five 42 KB source files: three turns, each reading more files, moved the band from ☀ 18%, to ☂ 67%, to ☇ 81%.

Run it

Requirements:

  • Claude Code 2.1.287 or later, where mods load by default. The mod was built and tested on 2.1.280, and claude plugin validate passes on 2.1.285.
  • A terminal. AbovePrompt is drawn on the terminal surface only.

No environment variables or configuration.

Steps:

  1. Clone this repository and go to this folder's parent:
   git clone https://github.com/anthropics/claude-code-playground.git
   cd claude-code-playground/claude-code/mods
  1. Check the plugin:
   claude plugin validate ./token-weather
  1. Try it for one session:
   claude --plugin-dir ./token-weather

Or install it, with the other mods here, from the local marketplace in this folder (see the mods README):

   claude plugin marketplace add ./
   claude plugin install token-weather@claude-code-playground-mods --scope user
  1. Work as normal. The band updates after each turn.

Notes / limitations

  • The percentage is of the full window. Claude Code's own "context used" notice counts against the auto-compact point, which is lower, so the two can differ. In testing, the band read 81% when the notice read 90%.
  • The band updates once per turn, not during a turn.
  • The chart's bars are relative to the fullest turn shown, so growth shows even at low fill. The percentage is the absolute figure.
  • The history resets when the session starts, or when the plugin reloads.
  • On a 1M-token window, ordinary work stays at ☀ for a long time. That's accurate.
  • One band per session. Another plugin that draws AbovePrompt competes for the same band.
  • Before the first response, the band reads 0%, because no response has reported usage yet.

Dependencies

NameVersionLicense (SPDX)Source
None

Third-party notices

None.


Shared as-is as part of claude-code-playground. Not an official Anthropic product; no support or maintenance is implied. See the root README and LICENSE.

공통 context 신호등 0.2.0

Codex CLI 대시보드와 같은 50/75/90% 기준을 사용합니다. session.measure에서도 읽고, 같은 수치의 중복 기록은 합칩니다. 갱신 실패는 STALE, 미제공 수치는 0으로 꾸미지 않습니다. 긴 표시는 한 줄로 자릅니다. 5h/7d 계정 한도와 현재 context 사용률은 서로 다른 값입니다.

출처

anthropics/claude-code-playground의 claude-code/mods/token-weather를 수정한 버전입니다. Copyright 2026 Anthropic PBC, Apache License 2.0. 변경 내역은 저장소 루트의 NOTICE를 참고하세요. Anthropic 공식 배포물이 아닙니다.

Source 1 files
hooks/token-weather.mjs 143 lines
1// Copyright 2026 Anthropic PBC
2// SPDX-License-Identifier: Apache-2.0
3// Modified 2026 by suhoon (Windows port / display changes). Original: https://github.com/anthropics/claude-code-playground — see NOTICE.
4//
5// Token Weather: a live traffic light for the context window, above the prompt.
6//
7// turn.complete: after each main-loop turn, read the context window's fill
8// from $.session.usage() (the same figures the status line shows) and keep
9// the last HISTORY readings.
10// session.start: take a first reading, so the band shows before any turn.
11// ui.render (AbovePrompt): one line: traffic light, signal word, percent, tokens
12// used of the window, and a block-character chart of the recent turns.
13//
14// The host reads on(...) and $.noun.method(...) from source, so they are
15// spelled literally, and helpers that take $ are top-level functions.
16
17const HISTORY = 12;
18const BARS = "▁▂▃▄▅▆▇█";
19
20// Traffic-light bands, by percent of the window used. One lamp (a single-width
21// ●, not an emoji) that changes color.
22const LAMP = "●";
23const SIGNAL = [
24  { upTo: 50, word: "Go", color: "green" },
25  { upTo: 75, word: "Caution", color: "yellow" },
26  { upTo: 90, word: "Stop", color: "red" },
27  { upTo: Infinity, word: "Compact soon", color: "red" },
28];
29
30// Readings: { tokens, window, percent }, oldest first.
31let readings = [];
32let stale = false;
33
34export function register(on) {
35  on("session.start", async ($, e, next) => {
36    const result = await next(e);
37    readings = [];
38    stale = false;
39    await takeReading($);
40    return result;
41  });
42
43  on("turn.complete", async ($, e, next) => {
44    const result = await next(e);
45    if (e.agentId) {
46      return result;
47    }
48    await takeReading($);
49    return result;
50  });
51
52  on("session.measure", async ($, e, next) => {
53    const result = await next(e);
54    await takeReading($);
55    return result;
56  });
57
58  // Stack the light over whatever the plugins beneath draw, so another mod's
59  // band (replay-theater's hint) never hides it and it never hides theirs.
60  on("ui.render", { component: "AbovePrompt" }, async ($, e, next) => {
61    if (e.hasSurvey || readings.length === 0) {
62      return next(e);
63    }
64    const { Box, Text } = $.ui.resolve(e);
65    const below = await next(e);
66    const light = band(Box, Text, e.bodyColumns ?? 80);
67    return below ? Box({ flexDirection: "column", children: [light, below] }) : light;
68  });
69}
70
71async function takeReading($) {
72  try {
73    const { context } = await $.session.usage();
74    if (!context || !Number.isFinite(context.window) || context.window <= 0 || !Number.isFinite(context.tokens) || context.tokens < 0) {
75      stale = true;
76      return;
77    }
78    const tokens = context.tokens;
79    const percent = Math.round(context.percent ?? (tokens / context.window) * 100);
80    // The session.start reading is 0 before any response; drop it once real readings arrive.
81    readings = readings.filter((r) => r.tokens > 0);
82    const last = readings[readings.length - 1];
83    if (!last || last.tokens !== tokens || last.window !== context.window || last.percent !== percent) {
84      readings.push({ tokens, window: context.window, percent });
85    }
86    stale = false;
87    if (readings.length > HISTORY) {
88      readings = readings.slice(-HISTORY);
89    }
90    $.ui.invalidate("ui.render");
91  } catch {
92    // No reading this turn; the band keeps the last one.
93    stale = true;
94  }
95}
96
97function band(Box, Text, columns) {
98  const now = readings[readings.length - 1];
99  const f = signalFor(now.percent);
100  const trend = trendWord();
101  const parts = [
102    Text({ wrap: "truncate-end", color: stale ? 'gray' : f.color, bold: true, children: `${LAMP}  ${f.word}` }),
103    Text({ wrap: "truncate-end", children: `  ${now.percent}% of context` }),
104    Text({ wrap: "truncate-end", dimColor: true, children: `  ${short(now.tokens)} / ${short(now.window)}` }),
105  ];
106  if (stale) parts.push(Text({ wrap: "truncate-end", dimColor: true, children: '  STALE' }));
107  if (columns >= 60) {
108    parts.push(Text({ wrap: "truncate-end", dimColor: true, children: "   last turns " }));
109    parts.push(Text({ wrap: "truncate-end", color: f.color, children: chart() }));
110    if (trend) {
111      parts.push(Text({ wrap: "truncate-end", dimColor: true, children: `  ${trend}` }));
112    }
113  }
114  return Box({ flexDirection: "row", paddingX: 1, children: parts });
115}
116
117export function signalFor(percent) {
118  return SIGNAL.find((band) => percent < band.upTo) ?? SIGNAL[SIGNAL.length - 1];
119}
120
121// Bars scale to the busiest reading shown, so growth shows at any fill level.
122function chart() {
123  const top = Math.max(...readings.map((r) => r.tokens), 1);
124  const bars = readings.map((r) => BARS[Math.min(BARS.length - 1, Math.floor((r.tokens / top) * (BARS.length - 1)))]);
125  return bars.join("");
126}
127
128function trendWord() {
129  if (readings.length < 2) {
130    return "";
131  }
132  const delta = readings[readings.length - 1].tokens - readings[readings.length - 2].tokens;
133  if (delta > 0) return `▲ +${short(delta)} last turn`;
134  if (delta < 0) return `▼ ${short(-delta)} last turn`;
135  return "steady";
136}
137
138function short(n) {
139  if (n >= 1_000_000) return `${(n / 1_000_000).toFixed(n % 1_000_000 === 0 ? 0 : 1)}M`;
140  if (n >= 1_000) return `${(n / 1_000).toFixed(n % 1_000 === 0 ? 0 : 1)}k`;
141  return String(n);
142}
143