Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/SuperClaude-Org/SuperClaude_PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/superclaude-org/superclaude_plugin/sc-cleanup)<a href="https://agentmods.dev/commands/superclaude-org/superclaude_plugin/sc-cleanup"><img src="https://agentmods.dev/badge/commands/superclaude-org/superclaude_plugin/sc-cleanup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/superclaude-org/superclaude_plugin/sc-cleanup"><img src="https://agentmods.dev/badge/commands/superclaude-org/superclaude_plugin/sc-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.00891 |
| Opus 5.5 | $0.00006 | $0.00356 |
| Sonnet 5.5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
91% identical to cleanup — 31 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sc:sc:sc:cleanup - Code and Project Cleanup
Triggers
- Code maintenance and technical debt reduction requests
- Dead code removal and import optimization needs
- Project structure improvement and organization requirements
- Codebase hygiene and quality improvement initiatives
Usage
/sc:sc:cleanup [target] [--type code|imports|files|all] [--safe|--aggressive] [--interactive]
Behavioral Flow
- Analyze: Assess cleanup opportunities and safety considerations across target scope
- Plan: Choose cleanup approach and activate relevant personas for domain expertise
- Execute: Apply systematic cleanup with intelligent dead code detection and removal
- Validate: Ensure no functionality loss through testing and safety verification
- Report: Generate cleanup summary with recommendations for ongoing maintenance
Key behaviors:
- Multi-persona coordination (architect, quality, security) based on cleanup type
- Framework-specific cleanup patterns via Context7 MCP integration
- Systematic analysis via Sequential MCP for complex cleanup operations
- Safety-first approach with backup and rollback capabilities
MCP Integration
- Sequential MCP: Auto-activated for complex multi-step cleanup analysis and planning
- Context7 MCP: Framework-specific cleanup patterns and best practices
- Persona Coordination: Architect (structure), Quality (debt), Security (credentials)
- Availability fallback: The MCP servers named here are preferred tooling, not hard requirements — when one is not installed, degrade gracefully (native reasoning in place of Sequential, official docs via web lookup in place of Context7, native tools otherwise) instead of routing work to absent servers.
Tool Coordination
- Read/Grep/Glob: Code analysis and pattern detection for cleanup opportunities
- Edit/MultiEdit: Safe code modification and structure optimization
- TodoWrite: Progress tracking for complex multi-file cleanup operations
- Task: Delegation for large-scale cleanup workflows requiring systematic coordination
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +2 lines e699396ab06b
- 1mo ago First seen · 112 lines · 16 tokens per session scan A fc570ff621de
cleanup is a command published in the GitHub repository SuperClaude-Org/SuperClaude_Plugin (55 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 891 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to cleanup, differing in 31 lines, and is treated as a copy.
Other commands, from other repositories
cleanup
Systematically clean up code, remove dead code, and optimize project structure.
debug
Systematic debug loop: root cause before any fix. Four phases, an evidence ledger, the 3-fix architecture wall. Use for any bug, defect, regression, test failure, or unexpected behavior before proposing a fix: 'fix this bug', 'why does X fail', 'the test is failing', 'it broke after Y', 'debug X', 'bị lỗi', 'sửa bug'…
fix-ci
Start an iterative CI fix session — resolve the input (build / PR / branch / cwd), then run the fixing-ci skill loop until CI is green or you've hit the iteration cap.
fact-check-code
Verify claims about the codebase by searching code and optionally the web.
troubleshoot
Diagnose root cause of a bug/issue (investigation only, no code changes).
null-as-error
Invoke the null-as-error skill to audit the current project for silent error swallowing in Effect code.