trackbed:code:refactor-opportunities

Find refactoring candidates, tech debt, and implicit state machines in a repo, PR, path, or feature, or before a change (--for); --ranked ranks weaknesses.

/trackbed:code:refactor-opportunities [--subagent-model <model>] [full | pr | path <file-or-folder> | feature <name>] [--for <spec-file | description>] [--ranked [--solo] [--output <path>] [--max-findings N] [--base <ref>]]

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

Description

Scan the full codebase, current PR, a path, or a feature for refactoring candidates and implicit state machines. Use when the user asks to find refactor opportunities, audit code quality, identify tech debt, wants a codebase health check, or asks what to refactor before a planned change (--for). Flags themes whose fix edits over 500 lines as automation candidates. User-only --ranked ranks the biggest maintainability, readability, and correctness weaknesses into CODEBASE_WEAKNESS_REPORT.md.

Guides

• Review Workflows

Related

• Refers to: trackbed:code:api-design, trackbed:code:breakdown-findings, trackbed:code:refactor-pass, trackbed:discovery:interview, trackbed:docs:adr, trackbed:docs:track-rejected-enhancements, trackbed:linear:breakdown-findings, trackbed:pr:code-review, trackbed:pr:review-convergence
• Referred to by: trackbed:code:agent-readiness, trackbed:code:api-design, trackbed:code:audit-agent-config, trackbed:code:audit-practice, trackbed:code:deprecate, trackbed:code:encode-constraint, trackbed:code:outside-view, trackbed:code:refactor-pass, trackbed:debug:find-sibling-bugs, trackbed:discovery:strategic-inquiry, trackbed:docs:update-agents-md, trackbed:linear:issue-to-pr, trackbed:pr:review-convergence