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

How to keep the prompt cache warm during breaks with Awesome Claude Code Mods

Install cache-tax to keep the prompt cache warm and see the estimated cost of a cold send.

Authorization notice. Awesome Claude Code Mods is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Remote script. The mod runs inside Claude Code and warming sends requests that use tokens, so review its access details first.

Who it is forA Claude Code user who pauses between prompts and notices slower or costlier replies after a break.

The problemThe prompt cache expires during breaks, so the next send is cold and costs more.

The outcomeThe cache stays warm during breaks, and you see one estimated cost warning when a cold send happens.

What you need first

  • Claude Code 2.1.287 or later
  • Node 18 or later for mod-finder
  • A Claude Code terminal session
  • Access details reviewed for any mod before you install it

Steps

  1. Run /plugin install mod-finder --marketplace karanb192/awesome-claude-code-mods and complete the installation prompts.
  2. Run /reload-plugins.
  3. Ask Claude: Find a mod that keeps the prompt cache warm.
  4. Check cache-tax's access details and its one-hour cache requirement, then follow its installation instructions.
  5. Keep the warming setting in mind, since warming uses tokens.

Prompt for your agent

Using the karanb192/awesome-claude-code-mods repo, find the cache-tax mod and confirm it is listed as a prompt cache warmer. Expected output: its install path, access details and the note that warming uses tokens and needs a one-hour cache. Verify the one-hour cache requirement before recommending installation.

Caveat. Warming uses tokens and needs a one-hour cache, so it may not suit every plan or workflow.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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