Get a one-time bypass so the next Write/Edit is not blocked by strict mode (for probing)
Scanned 8/31/2026
Install to Claude Code
Skills Directorynpx -y skills add LarryStanley/pi-delegate --skill probe --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Probe?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/larrystanley-probe)More formats (shields.io, HTML) on the badges page.
---
description: Get a one-time bypass so the next Write/Edit is not blocked by strict mode (for probing)
disable-model-invocation: true
---
The user wants to run a probe — make **one** minimal viable change by hand and verify it works,
then write the recipe into a task book afterward.
Create the one-time bypass flag:
```bash
node "${CLAUDE_PLUGIN_ROOT}/bin/pi-probe"
```
Then tell the user: **this flag is good for one use only** — it turns itself off automatically after
the next Write/Edit goes through. Once the probe is done, immediately write the verified recipe into
a task book, and dispatch everything else to pi as usual.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
