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

How to flag AI provenance marks in files Claude Code writes with Watermarks Remover

Get a PostToolUse hook that checks each file your agent writes for AI provenance marks.

  • Top pick
  • Content
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code

Authorization notice. Watermarks Remover is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Reverse engineering. Check mode only reports marks, but clean mode strips them in place, so only use it on content you own.

Who it is forA developer using Claude Code who wants every file the agent writes checked before it reaches git.

The problemAgent-written files can carry provenance marks, and a skill alone depends on the model choosing to run it.

The outcomeEach file the agent writes is scanned by a harness-run hook in check mode, and any findings are reported to the model.

What you need first

  • Python 3.10+ to run the installer (stdlib only, no dependencies)
  • A clone of the watermarks-remover repository
  • A supported agent host such as Claude Code, Codex, or Cursor
  • The local service running with make serve for remove-ai-marks

Steps

  1. From the repository checkout, run python3 install_skill.py --skill remove-ai-marks --target claude-code.
  2. Start the service with make serve.
  3. Install the plugin in Claude Code with /plugin marketplace add guillaumemeyer/watermarks-remover and then /plugin install watermarks-remover@watermarks-remover.
  4. Confirm Hook mode is set to check in /plugin manage, or add the PostToolUse hook from the README to ~/.claude/settings.json with --mode check.
  5. Ask the agent to write a test file, then confirm the hook reports findings without changing the file.

Prompt for your agent

In the watermarks-remover repo, use the remove-ai-marks skill in Claude Code to write <file path> with <test content>. Report whether the PostToolUse hook in check mode flagged any provenance marks, and leave the file unchanged unless I ask you to clean it.

Caveat. The hook covers files the agent writes, not the chat messages themselves, which the README says no hook can rewrite.

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