npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

prompt-crimes

v0.1.4

Published

Generate a funny local Prompt Crimes report from AI chat histories

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

sangwandeveshsangwandevesh

Keywords

cliaicodexclaudecursorprompt-engineeringroastdeveloper-tools

Readme

Prompt Crimes

Generate a funny local "Prompt Crimes" report from your AI chat history.

prompt-crimes scans local AI chat/session storage and roasts common prompting habits: vague asks, context dumps, validation seeking, decision outsourcing, error dumps without context, and tiny retry prompts like again or still broken.

Everything runs locally. No chat content is uploaded anywhere.

Quick Start

Run without installing:

npx prompt-crimes

Or install globally:

npm install -g prompt-crimes
prompt-crimes

Usage

prompt-crimes
prompt-crimes scan
prompt-crimes scan --agent codex
prompt-crimes scan --since 2026-01-01
prompt-crimes scan --show-snippets

By default, snippets are hidden so the report is safer to share. Use --show-snippets to include short sanitized excerpts for the top evidence.

Example Output

  PROMPT CRIMES REPORT
  --------------------

  messages scanned     489
  agents found          3
  sessions found        134
  date range            2025-10-12 -> 2026-06-08
  charges filed         23
  crime rate            4.7%

  Crime Index          ████░░░░░░░░░░░░░░░░  18/100
  verdict               Mostly Harmless Prompt Tourist
  case summary          Context Dumping made a cameo, then politely returned to misdemeanor court.

  top crimes
    MAJOR   Context Dumping                 9 (144 pts)
    NOTABLE Context Without Question        8 (88 pts)
    MINOR   Vague Prompting                 3 (23 pts)
    MINOR   Validation Seeking              2 (20 pts)
    MINOR   Error Dump Without Context      1 (15 pts)

  by agent
    cursor       13 charges in   352 messages (3.7%) most charges
    codex         5 charges in    93 messages (5.4%)
    opencode      5 charges in    44 messages (11.4%) highest rate

  charges
    - Context Dumping x9: Releasing a context avalanche and asking for a snow cone.
    - Context Without Question x8: Dropping a full case file with the final page missing.
    - Vague Prompting x3: Filing tickets with the acceptance criteria of a shrug.
    - Validation Seeking x2: Asking the model to stamp APPROVED on vibes.
    - Error Dump Without Context x1: Mailing a stack trace with no return address.

Supported Agents

Reads local session storage for:

  • Claude Code
  • Codex
  • Cursor
  • OpenCode
  • Amp
  • Cline / Roo Code
  • Zed

Privacy

prompt-crimes is local-only. It reads chat history from local app storage, analyzes it with deterministic heuristics, and prints a terminal report. It does not call an LLM or send chat content to a server.

Credits

Inspired by DevLove and DevRage. The adapter shape follows DevLove's useful local-only chat reader architecture, with a new analyzer and report layer built for Prompt Crimes.