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

How to shortlist the files that handle a concern before Claude reads them with Quicksilver

Ask Jev which files in a big repo match a condition, then give Claude only those paths.

Credentials. The skill never sends .env files, private keys, certificates, or credentials files, but any other file it reads goes to TypeSafe's API, so keep sensitive source out of the target folder.

Who it is forA developer or security reviewer working in a large repo who needs every file that touches auth, sessions, or another concern.

The problemClaude reads every candidate file to decide which ones matter, which fills its context with noise and costs many tokens.

The outcomeClaude gets a short list of matching file paths with borderline items marked, and the benchmark's codebase discovery task reached 100% F1 with 91% fewer Claude tokens.

What you need first

  • Claude Code installed
  • Node 18 or later
  • A Jev key from console.typesafe.ai
  • Content you are allowed to send to TypeSafe's API

Steps

  1. Get a Jev key at console.typesafe.ai.
  2. Run npx github:UditAkhourii/quicksilver and enter your key when asked.
  3. Restart Claude Code. Claude uses the skill on its own for this kind of task.
  4. Run qs filter "Does this file handle user sessions?" src and replace the question and the folder with your own. (inferred, check the README)
  5. Read the returned paths and check every line marked with ? yourself.

Prompt for your agent

Using the repo UditAkhourii/quicksilver, run qs filter with a yes/no question about <concern> against <target-directory>. Return the matching file paths and list any borderline items marked with ?. Verify that the output ends with a receipt line showing files scanned and the Jev cost.

Caveat. Look-alike code can produce borderline matches, so Claude or you should review the items marked with ? before acting on them.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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