Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From sc-refactor
Detects post-AI session artifacts like debug statements, duplicate code, naming inconsistencies, and test issues in target directory, producing prioritized cleanup report.
npx claudepluginhub kylesnowschwartz/simpleclaude --plugin sc-refactorHow this command is triggered — by the user, by Claude, or both
Slash command
/sc-refactor:sc-cleanup [target-directory]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Clean up the codebase at $ARGUMENTS (or current directory if not specified) after an AI coding session. ## Purpose AI coding sessions often leave behind artifacts: - Debug statements (`console.log`, `print()`, `debugger`, `binding.pry`) - Duplicate implementations (AI wrote new code instead of finding existing) - Inconsistent naming (AI used different conventions than the codebase) - Orphaned tests or missing test coverage - TODO/FIXME comments that should be resolved This command finds these issues so you can clean them up before committing. ## Phase 1: Launch Analysis Agents Launch 4...
/ai-hygiene-auditAudits codebase for AI-generated code issues: git patterns, duplication bloat, test deficits, doc slop. Outputs hygiene score and report; supports focus areas, thresholds, JSON.
/cleanAnalyzes recent changes in commit range, unstaged files, or context for dead code, orphaned artifacts from failed branches; generates validated cleanup tasks and reports.
/reviewAnalyzes and fixes code using parallel subagents in review (changes), audit (path/codebase), or fix modes. Effort scales to input size.
/alRuns AgentLint diagnostics across all projects with default core checks for findability, instruction quality, workability, continuity, safety, and harness. Optional deep/session analysis. Initializes config on first run.
/code-reviewRuns enabled review agents on target files or git changes after lint/type-check/semgrep gates, producing a structured summary or JSON.
/sc-cleanupCleans up specified target: removes dead code, optimizes imports/structure. Supports --type code|imports|files|all, --safe|--aggressive|--interactive flags, produces summary report.
Share bugs, ideas, or general feedback.
Clean up the codebase at $ARGUMENTS (or current directory if not specified) after an AI coding session.
AI coding sessions often leave behind artifacts:
console.log, print(), debugger, binding.pry)This command finds these issues so you can clean them up before committing.
Launch 4 agents in parallel with run_in_background: true:
Task(subagent_type: "sc-refactor:sc-dead-code-detector", run_in_background: true,
prompt: "Analyze [target] for dead code and debug artifacts. Focus on:
- Debug statements (console.log, print, debugger, binding.pry, byebug)
- Stale TODO/FIXME/HACK/XXX comments
- Commented-out code blocks
- Unused imports")
Task(subagent_type: "sc-refactor:sc-duplication-hunter", run_in_background: true,
prompt: "Analyze [target] for code duplication. Focus on:
- Duplicate function implementations
- Copy-pasted code blocks
- Reimplemented utility functions")
Task(subagent_type: "sc-refactor:sc-naming-auditor", run_in_background: true,
prompt: "Analyze [target] for naming inconsistencies. Focus on:
- Convention violations vs established patterns
- Inconsistent casing or prefixes
- Names that don't match the domain language")
Task(subagent_type: "sc-refactor:sc-test-organizer", run_in_background: true,
prompt: "Analyze [target] test organization. Focus on:
- Missing tests for new code
- Orphaned test files
- Test/implementation file mismatches")
Wait for all agents to complete via task-notification messages. You MUST use the results delivered in task-notifications directly — do NOT call TaskOutput on completed background agents, as the task registry purges completed entries and TaskOutput will fail with "No task found".
Categorize findings:
# Post-Session Cleanup Report
## Immediate Fixes (before committing)
[Debug statements, obvious duplicates, broken tests]
## Should Address
[Naming inconsistencies, missing tests]
## Consider Later
[Minor duplication, stylistic issues]
## Findings Summary
- Dead code/debug: [count] issues
- Duplication: [count] issues
- Naming: [count] issues
- Test organization: [count] issues
Use AskUserQuestion:
| Option | Label | Description |
|---|---|---|
| auto-fix | Auto-fix immediate issues | Remove debug statements, delete dead code (max 15 changes) |
| fix-plan | Generate fix plan | Step-by-step instructions for each issue |
| report-only | Just the report | Output report and stop |
For each issue: File, Problem, Fix steps, Verification.
Output the report. Done.