Who it is forA developer who wants to stop using the pet integration, or who sees missing hooks after installing and needs to recover the earlier settings.
The problemManually editing ~/.claude/settings.json risks deleting hooks that are not from this repo, and a failed change can leave the session without its original setup.
The outcomeThe repo's entries are removed and other hooks stay in place, or the most recent backup is restored.
What you need first
- A Mac running macOS
- Clawd on Desk installed from https://github.com/rullerzhou-afk/clawd-on-desk/releases
- Claude Code installed
- git, python3, and node available on the machine
Steps
- Open a terminal in the Clawd Conduit folder
- Run
bash uninstall.sh(inferred from the repo's file list) (inferred, check the README) - Run
python3 -c "import json;json.load(open('$HOME/.claude/settings.json'))"to confirm the file still parses (inferred, check the README) - If hooks are missing, run
ls -t ~/.claude/settings.json.bak.* | head -1to find the most recent backup - Start a new Claude Code session to load the changed settings
Prompt for your agent
In the clawd-conduit repo, run `bash uninstall.sh` and then parse ~/.claude/settings.json with python3 to confirm it is valid JSON. Report whether any non-repo hooks remain and which backup file was used if one was restored.
Caveat. Hooks are read at session start, so you must open a new Claude Code session after uninstalling or restoring for the change to take effect.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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