Who it is forA developer who lets Claude Code work in the background and needs to know when it is waiting for a permission answer.
The problemA permission prompt can sit unanswered for a long time while you are away from the screen, which stalls the whole task.
The outcomeA repeating three-pulse pattern plays on the device while a permission prompt waits, and stops when the tool finishes, fails, or you reject it.
What you need first
- Claude Code with function-hooks plugin support (the README says it is an early-access API, built against 2.1.291)
- Node.js 22+ available as node on your PATH
- Intiface Central installed, with its WebSocket server running at ws://127.0.0.1:12345
- A vibration-capable controller paired in Intiface Central
- A private setting where you are comfortable using the device
Steps
- Complete the plugin install with
git clone https://github.com/transkatgirl/vibeclaude.git ~/.claude/vibeclaudeandcd ~/.claude/vibeclaude && npm install. - Start Intiface Central, press the server start button, then run
claude --plugin-dir ~/.claude/vibeclaude. - In Claude Code run
/intifaceand select your device. - Start a task that uses tools that need permission, and step away from the screen.
- When the prompt appears, feel for the three 90ms pulses and return to approve or reject the call.
Prompt for your agent
Use the transkatgirl/vibeclaude plugin in Claude Code with <device name> selected in Intiface Central. Start a task that needs a permission prompt and confirm that the device pulses three times at a steady pause until the prompt is answered. Report which tool asked for permission and whether the pattern stopped when the tool finished.
Caveat. Claude Code does not report when you answer a prompt, so the pattern can keep going until the tool that asked finishes or fails.
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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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