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

How to count and export your repeated prompts with CLI Faq Shortcuts

Run the extractor alone to list, count or export your prompts with no agent involved.

Credentials. The exported JSONL contains raw prompts that may include tokens or personal data, so do not share or commit the output file.

Who it is forA developer or team lead who wants to see how much time goes into repeated requests before picking shortcuts.

The problemWithout a count, it is hard to tell which requests are worth turning into shortcuts.

The outcomeA list of your matching prompts, a count since a chosen date, and JSONL records you can load into your own scripts.

What you need first

  • git and Python 3.9+ installed (macOS, Linux, or Windows with the PowerShell steps)
  • Claude Code, Codex or Cursor installed, with existing prompt history on the machine
  • A project folder you have already worked in with one of those agents

Steps

  1. Run E=~/.agents/skills/faq-shortcuts/scripts/extract_asks.py after the clone step in the Quick start.
  2. Run python3 "$E" . | head to see the matching prompts in your project folder. (inferred, check the README)
  3. Run python3 "$E" . --since 2026-09-01 | wc -l to count prompts since a date.
  4. Run python3 "$E" . --format jsonl to get one JSON record per prompt with date, source and prompt fields.

Prompt for your agent

Using the cli-faq-shortcuts extractor at ~/.agents/skills/faq-shortcuts/scripts/extract_asks.py, run it on <project_path> with --format jsonl and write the records to a file. Expected output: one JSON object per line with date, source and prompt fields. Verify the file line count matches the count from the default tsv output.

Caveat. Prompts longer than 400 characters are filtered by default, so raise --max-len if your usual requests are longer.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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