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

How to watch Claude Code session state on a desktop pet with Clawd Conduit

See on the desktop when Claude Code is thinking, running tools, failing, compacting, or finished.

Who it is forA developer who runs several tool-heavy Claude Code sessions and wants a glance at progress without reading the terminal.

The problemWith few hook events a status tool only shows busy or idle, so it is hard to tell a failed tool, parallel subagents, or context compaction apart.

The outcomeThe pet changes state for each lifecycle event, such as juggling for subagents, sweeping during compaction, and error after a tool failure.

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

  1. Run bash install.sh from the cloned Clawd Conduit folder
  2. Run lsof -nP -iTCP:23333 -sTCP:LISTEN to confirm Clawd's local service is listening
  3. Start a new Claude Code session and send any message
  4. Watch the pet move from idle to thinking, then working during tool calls
  5. Look for juggling during subagent runs and sweeping during context compaction

Prompt for your agent

In the clawd-conduit repo, run `lsof -nP -iTCP:23333 -sTCP:LISTEN` after `bash install.sh` and report whether Clawd on Desk is listening. Then count the events wired by the python3 check in the README and confirm the result is 15 events.

Caveat. Some builds report subagent launches only as a Task or Agent tool call, so juggling depends on Clawd's fallback, and the error state is brief enough that you may need to be watching.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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