review-duplicates

SkillDev tools

Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the review-duplicates skill

What this skill tells your AI

The instructions your AI receives, as published by nwiizo/ccswarm in .agents/skills/review-duplicates/SKILL.md and read by ahel’s review.

When subagents are enabled in Codex, prefer delegating this workflow to the code-refactor-agent custom agent.

Detect duplicate code in the ccswarm codebase using similarity-rs.

similarity-rs crates/ --threshold 0.80

For Rust code, also consult cargo coupling so duplicate cleanup is prioritized by architectural impact, not only by textual similarity.

cargo coupling . --summary --exclude-tests
cargo coupling . --hotspots=12 --exclude-tests

If a duplicate cluster is located in a coupling hotspot, high-risk boundary, or cycle-related module, raise its refactoring priority accordingly.

Classify results by priority:

Priority	Condition	Action
High	95%+ similarity, 10+ lines	Extract to common function
Medium	90-95% similarity, 5+ lines	Consider trait or macro
Low	85-90% similarity	Evaluate structural similarity
Skip	Test code, config structs	Allow intentional duplication

Output a JSON report with high_priority, medium_priority, low_priority, and ignored sections.

Advanced