DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to keep Claude Code's cache warm during a break with Cache Tax

Arm a timed keepwarm window before stepping away so the next message does not pay a full cache rewrite.

Who it is forA developer deep in a large Claude Code session who needs to step away for a meeting, lunch or a short break and return to the same context.

The problemWhen the prompt cache expires, even a short message can trigger a rewrite of the old context, which costs tokens on the next send.

The outcomeThe session stays warm for the chosen window, and the user knows the next ping time and the last receipt when they return.

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

  1. Run claude plugin marketplace add karanb192/claude-code-mods in a terminal.
  2. Run claude plugin install cache-tax@claude-code-mods, then restart Claude Code or run /reload-plugins in an open session.
  3. If you use API-key, usage-credit or cloud-provider billing, set promptCacheTtl to "1h" so the main cache lasts an hour.
  4. In a warm session, run /keepwarm 90m before your break, or /keepwarm for the six-hour default.
  5. On return, run /keepwarm status to see the warming window, next ping and last receipt.

Prompt for your agent

In the karanb192/cache-tax repo, install the cache-tax plugin, then in a warm Claude Code session run /keepwarm 90m. Report the output of /keepwarm status, including the warming window and next ping time. Verify that the window shown matches the 90 minutes you requested.

Caveat. Pings cost tokens, and the mod reads every prompt you type, so choose a window you expect to return within.

Share: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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