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

How to keep a long chat's cache warm while you step away with CTX Handoff Mod

Send small keep-alive requests during idle time, then resume the saved handoff or the same chat on return.

Who it is forA developer who leaves a large Claude Code conversation for an hour or more and dreads the full-price reread on return.

The problemAfter an idle break, the next message rereads the whole conversation at full price because the cache has expired.

The outcomeThe cache is kept warm for up to about 4 hours, and on return you choose to start fresh from the saved summary or stay where you were.

What you need first

  • Claude Code 2.1.287 or later (the README says it is tested up to 2.1.302)
  • A Claude subscription sign-in, or an API key, Bedrock or Vertex setup with the cache refresh turned off
  • Access to the Claude Code plugin commands in a terminal

Steps

  1. Run claude plugin install ctx-handoff@ctx-handoff-mod if it is not installed yet
  2. Type /handoff in the session to confirm that cache refresh is on
  3. Before leaving a conversation you do not want refreshed, run /handoff away pause
  4. On return, run /handoff resume to start fresh from the saved summary, or type continue to stay where you were
  5. Run /handoff resume again later and restart the timer with resume if you paused it

Prompt for your agent

In Claude Code with ctx-handoff-mod installed, check the cache refresh status for <conversation> using `/handoff`. Expected output: a line reporting how many refreshes were used this idle period. Verify the status line before stepping away.

Caveat. On an API key, Bedrock or Vertex the cache lasts only 5 minutes, so the README says to run `/handoff refresh off` in those setups.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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