trackbed:code:outside-view

Rate a codebase with unprimed raters to surface unknown-unknown quality problems, especially in AI-engineered code.

/trackbed:code:outside-view [--subagent-model <model>] [--raters N] [--output <path>] [--compare <report-path>] [--cross-model]

• Invocation: User
• Hosts: Claude Code, Codex ($trackbed:code:outside-view in Codex)
• Category: Audits
• Source: trackbed/skills/code:outside-view/SKILL.md

Description

Rate a codebase with unprimed raters; cluster complaints, compare with CODEBASE_WEAKNESS_REPORT.md, and track gestalt in OUTSIDE_VIEW_REPORT.md. Cross-model is opt-in and isolated. Use for unknown-unknown quality issues, especially in AI-engineered code. Not for evidence-ranked findings (trackbed:code:refactor-opportunities --ranked), PR review, or implementation.

Guides

• Review Workflows

Related

• Refers to: trackbed:code:refactor-opportunities, trackbed:workflow:cleanup-artifacts