Request a read-only adversarial review from Claude Code through the sandbox-external bridge.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add Borda/AI-Rig --skill review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/borda-review-ai-rig)More formats (shields.io, HTML) on the badges page.
---
name: review
description: Request a read-only adversarial review from Claude Code through the sandbox-external bridge.
---
# Ask Claude Code to Review
Call `bridge_review` with required `task`; preserve caller-supplied `model`, `effort`, `timeout_seconds`, `depth`, and `run_id`. If effort is absent, select and pass it: `low` for narrow mechanical or settled factual work; `medium` for bounded implementation, diagnosis, or review; `high` for cross-file, adversarial, architectural, or security judgment; `xhigh` for unusually broad consequential work; `max` only on explicit request. Never replace supplied effort.
The MCP host binds its launch workspace. Return only the compact envelope; retain workspace-relative transcript and `incident` references for detail, never inline peer `details`.
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!
