Summary
This is a quality gate system that scores your code and agent outputs on a 0.0 to 1.0 scale, with automatic rollback if anything falls below 0.95. It integrates with Claude Flow to give you real-time truth metrics across your codebase, broken down by agent, task, or file. The dashboard view is nice for spotting trends, and the watch mode catches regressions as they happen. You can export to JSON or CSV for CI/CD pipelines. It's honestly more aggressive than most linting setups, the default 0.95 threshold is strict, but that's the point if you're running autonomous agents that can silently introduce bugs. The auto-fix flag on verification checks is a thoughtful touch for common issues.
Install to Claude Code
npx -y skills add spencermarx/open-code-review --skill "Verification & Quality Assurance" --agent claude-codeInstalls into .claude/skills of the current project.
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Files
SKILL.md
Select a file.
Featured
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 11, 2026
