Cache Ttl Timer — AI skill for Claude Code

Cache TTL Timer

A Claude Code mod that shows how long the prompt cache of your conversation stays warm, right in the prompt footer beside the model and effort:

+ 🎙 ⌄ Auto        ● 47m  Opus 5.5  High  ◔

Claude caches the conversation's prompt for a time to live (TTL) of 5 minutes or 1 hour after each request. While the cache is warm, your next message is read from it cheaply. Once it lapses, the next message writes the whole conversation to the cache again, which costs more and counts more against your usage. The timer tells you which of the two your next message will be, before you send it.

What it shows

Footer	Meaning
● 60m → ◕ → ◑ → ◔	The cache is warm. The ring empties as the TTL runs down, and the time counts down in minutes.
◔ 9m in the warning color	Less than a fifth of the TTL is left.
○ 0:42	The last minute, counted in seconds.
◌ Cold	The cache has lapsed. Your next message re-caches the conversation.

Nothing shows before the first request of a session. The label uses the footer's own dim color until the last fifth of the TTL, so it stays quiet until it matters.

How it works

• When the countdown starts: each time the main conversation sends a request to the model, which is when the cache is read or written. A turn with tool calls sends several requests, and each one restarts the countdown. Requests from subagents are left out, because they cache their own prompts.
• Which TTL applies: read from the session's transcript, where the API reports how many tokens each request wrote to the cache at the 5-minute and 1-hour TTL. Until a write is seen, the timer assumes 1 hour, the TTL Claude Code uses on the main conversation of a subscription.
• After a restart or a resume: the countdown picks up from the last request in the transcript, so a session you come back to shows whether its cache is still warm before you type.

The timer is an estimate from the client's side.