Who it is forA developer who runs several long Claude Code sessions over a workday and does not want to arm keepwarm in each one.
The problemSetting keepwarm by hand in every session is easy to forget, and an unwarmed session costs a full rewrite on the next message after a break.
The outcomeEach session that reaches the cache keeps a warm window of at least six hours from its last turn, and the setting persists across sessions.
What you need first
- Claude Code 2.1.287 or later
- A one-hour cache (included subscription usage defaults to one hour; API-key, usage-credit and cloud-provider sessions default to five minutes and need promptCacheTtl set to "1h")
- Claude Code left running during the break
Steps
- Install the plugin and confirm the cache lifetime setting as described in the first use case.
- In a warm session, run
/keepwarm alwaysto keep every session warm until six hours after its last turn. - Run
/keepwarm statusin a session to confirm the window and next ping. - When you no longer want warming, run
/keepwarm off, which stops every session from its next turn and turns always off.
Prompt for your agent
In the karanb192/cache-tax repo, with the plugin installed, run /keepwarm always in a Claude Code session and then /keepwarm status. Report the warming window and next ping. Verify that the window reaches at least six hours after the last turn.
Caveat. Always mode keeps pinging across sessions, so it spends tokens even on sessions you no longer use, and the README says pings cost tokens including uncapped output.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page