Claude Mods
Claude Code mod: context in tokens, 5-hour and weekly limits vs. the clock, prompt cache countdown, session cost and running agents, in one band above the prompt.
Install
/plugin marketplace add augiefra/claude-modsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →claude-mods
Claude Code mods by Eric Cologni.
token-weather-usage
Stop hitting your Claude limit by surprise. One band above the prompt shows how big your context is, your 5-hour and weekly limits against the clock (with a warning when the week's pace would run out before the reset), whether the prompt cache is still warm, what the session and the last prompt cost, and which agents are running.
Four situations
All clear. Small context, both limits behind the clock, the cache warm for almost an hour.
Agents at work. Three subagents running (hover their pill for their tasks); the 5-hour limit runs a little ahead of time, so its gauge turns yellow.
Cache about to lapse. Seven minutes left: send the next message now, or the whole 604k context gets written again at full price.
Slow down. Context near full, the 5-hour limit far ahead of time, the cache expired: /compact before going on.
What each pill says
- Context: tokens in the context, with a weather icon from Clear to "Compact soon" (hover the pill for the weather and the share of the window). Then one bar per prompt for the last 5, as tall as the tokens it added, the current one in color, and the last prompt's change.
- 5h / 7d: the share of your account's limits already used. The gap with the time elapsed is hatched: grey after the bar while you have margin, in the bar's color when you use faster than time passes. Green while usage does not run ahead of time; yellow beyond; red when more than 15 points ahead or past 90%. Then the time left; for the 5-hour limit, the reset time (machine's time zone) sits in the pill's hover card in the app and is left out in the terminal. A window that already reset is hidden until the next reading; the latest reading is shared across the sessions open on the machine.
- Cache: the time before the prompt cache lapses, behind a bolt in the app and the word "cache" in the terminal. When the last message read less than 90% of its prompt from the cache, that share comes first ("cache 64% · 52 min"). Each message restarts the clock: 1 hour on a Claude subscription, 5 minutes on an API key. Mods get the token counts but not the lifetime, so it follows Claude Code's rules and corrects itself from what the traffic shows. Yellow under 10 minutes, with what is at stake in dollars ("$2.32 at stake": the whole context written again if the cache lapses); "missed" with its cause (model changed, lapsed, start changed) when a message had to write the cache again, and what that cost above a message served by the cache ("+$2.10"); red "expired" once it lapsed, with what the next message writes again and its cost ("741k to rewrite ≈ $5.93"). From 100k tokens comes the way out:
/compactup to 300k, a new thread beyond, since the next message would rewrite the whole context at full price, which a new thread avoids and a compaction would only read again. The terminal keeps that advice on the line ("· /compact", "· new thread"); the app puts it in the pill's hover card. In the app, hover the cache pill for the expiry time, the share of the last message read from the cache, what the context costs a message read from the cache against writing it again, and what the cache saved in this thread. The dollars come from Anthropic's list prices, dated 2026-10-08 (input, cache read, and cache writes at 1.25× input for 5 minutes or 2× for 1 hour); on a subscription the
Similar plugs
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro,…
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini…