- Home
- Skills
- Code Quality & Review
- Multi-Lens Code Review
Multi-Lens Code Review
Four specialist review passes and one ship / no-ship verdict.
$19
Works with the AI Agents you already use
About this skill
A reviewer asked to look at everything finds a little of everything and misses the thing that matters. This skill makes your agent run four narrow passes that are not allowed to overlap (architecture, security, performance, maintainability), each limited to three findings with line references, then one synthesis with strict rules: an issue is must-fix only when two passes raised it or one pass blocked on it, and disagreements are kept, not smoothed over.
You get a consensus verdict (ship, ship-with-changes or block), a must-fix list, a should-fix list and the four reports underneath.
It is the review format we run in production at Grupr. Works with any agent that reads SKILL.md; uses subagents and different models per pass when your setup has them, and runs the passes in sequence when it does not. No scripts, no network calls.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 7 days ago