name: codebase-cleaner
description: Safe codebase cleanup: delete AI slop, consolidate duplicates, update imports — always test-verified before committing
version: 1.0
model: sonnet
invoked_by: both
user_invocable: true
tools: [Read, Write, Bash, Grep]
verified: true
lastVerifiedAt: 2026-03-16T08:04:18.632Z
best_practices:
- Follow existing project patterns
- Document all outputs clearly
- Handle errors gracefully
error_handling: graceful
streaming: supported
source: builtin
trust_score: 100
provenance_sha: c4991038f2383e00
Codebase Cleaner
Codebase Cleaner Skill - Safe codebase cleanup: delete AI slop, consolidate duplicates, update imports — always test-verified before committing
- Codebase Cleaner primary function
- Integration with agent ecosystem
- Standardized output generation
Step 1: Gather Context
Read relevant files and understand requirements
Step 2: Execute
Perform the skill's main function using available tools
Step 3: Output
Return results and save artifacts if applicable
</execution_process>
<best_practices>
- Follow existing project patterns: Follow this practice for best results
- Document all outputs clearly: Follow this practice for best results
- Handle errors gracefully: Follow this practice for best results
</best_practices>
**Example Commands**:
/codebase-cleaner [arguments]
node .claude/skills/codebase-cleaner/scripts/main.cjs --help
</usage_example>
Search Protocol
For code discovery and search tasks, follow this priority order:
- `pnpm search:code ""` (Primary intent-based search).
- `ripgrep` (for exact keyword/regex matches).
- semantic/structural search via code tools if available.
Memory Protocol (MANDATORY)
Before starting:
```bash
cat .claude/context/memory/learnings.md
cat .claude/context/memory/decisions.md
```
After completing:
- New pattern -> `.claude/context/memory/learnings.md`
- Issue found -> `.claude/context/memory/issues.md`
- Decision made -> `.claude/context/memory/decisions.md`
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
