automagik-cli: Command for Claude Code

.claude/commands/clean.md

clean is a command for Claude Code from namastexlabs/automagik-cli. It costs 0 tokens per session (2,619 once invoked), scanned A, original, MIT.

A code-cleanup command that finds dead code, unused files, and obsolete project artifacts, then asks for confirmation before deleting them.

In plain words
What is it for?
Use it to clean a whole codebase or a selected directory, including old migrations, backups, and unused TypeScript types.
Why use it?
It reduces clutter while lowering the risk of deleting something still needed through repeated checks and user confirmation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md.

This is namastexlabs/automagik-cli's own configuration. It tells Claude Code how to work on automagik-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything automagik-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to namastexlabs/automagik-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/namastexlabs/automagik-cli/main/.claude/commands/clean.md
Clone the repo
git clone --depth 1 https://github.com/namastexlabs/automagik-cli

Made for: Claude Code.

Wrote 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.

agentmods badge for clean

README.md
[![agentmods](https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/clean.svg)](https://agentmods.dev/commands/namastexlabs/automagik-cli/clean)
Your own site
<a href="https://agentmods.dev/commands/namastexlabs/automagik-cli/clean"><img src="https://agentmods.dev/badge/commands/namastexlabs/automagik-cli/clean.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02619
Opus 5 $0.00000 $0.01309
Sonnet 5 $0.00000 $0.00524
Haiku 4.5 $0.00000 $0.00262

Measured 3d ago against content hash d7b7b850981c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

clean 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 3d 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.

.claude/commands/clean.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/clean


allowed-tools: Task(), Read(), Bash(), Glob(), Grep(), mcp__zen__, mcp__search-repo-docs__, mcp__ask-repo-agent__, mcp__genie_memory__, mcp__send_whatsapp_message__, mcp__wait__* description: Safely identify and remove dead code, unused files, and obsolete artifacts

Comprehensive dead code detection with triple-verification safety system using multiple expert agents and LLM consultation.

Auto-Loaded Project Context:

@/CLAUDE.md @/docs/ai-context/project-structure.md @/docs/ai-context/docs-overview.md

Usage

# Full codebase cleanup
/clean "Find all dead code and unused files"

# Specific directory cleanup
/clean "Clean unused files in agents/ directory"

# Target specific patterns
/clean "Remove old migration files and backups"

# Focus on specific file types
/clean "Find unused TypeScript interfaces and types"

⚠️ CRITICAL SAFETY NOTICE

This command can permanently delete files. It employs:

  • Triple-verification system with independent agents
  • Multi-LLM consensus via Gemini consultation
  • Memory-based pattern validation
  • WhatsApp notifications before any deletion
  • Mandatory user confirmation for all deletions

Intelligent Cleanup Strategy

Step 1: Scope Analysis

Parse user request: "$ARGUMENTS"

Cleanup Categories:

  • Unused Code → Functions, classes, variables never referenced
  • Orphan Files → Files not imported/required anywhere
  • Old Artifacts → Backups, migrations, temporary files
  • Dead Dependencies → Unused npm packages, imports
  • Obsolete Tests → Tests for deleted code
  • Stale Documentation → Docs for removed features

Step 2: Parallel Detection Phase

Deploy 8-10 specialized detection agents in parallel:

Wave 1: Discovery Agents (Parallel)

Task: "As [Agent_Role], identify potential dead code in [assigned_area] for request '$ARGUMENTS'"

Agent 1: Import_Analyzer
- Trace all import/export relationships
- Build dependency graph
- Identify orphan files with no imports
- Find circular dependencies

Agent 2: Reference_Hunter  
- Search for function/class/variable usage
- Track method calls across codebase
- Identify unreferenced exports
- Find dead event handlers

Agent 3: Pattern_Detective
- Identify naming patterns (*.old, *.backup, *.tmp)
- Find commented-out code blocks
- Detect TODO/FIXME markers for removed features
- Locate deprecated API usage

Agent 4: Test_Validator
- Map tests to implementation files
- Find tests for non-existent code
- Identify outdated test fixtures
- Check test coverage gaps

Agent 5: Documentation_Auditor
- Cross-reference docs with code
- Find documentation for deleted features
- Identify broken links and references
- Check API doc accuracy

Agent 6: Build_Artifact_Scanner
- Check build outputs and dist folders
- Find generated files without sources
- Identify stale build configurations
- Detect unused webpack chunks

Agent 7: Git_History_Analyst
- Analyze file modification patterns
- Find files unchanged for >6 months
- Identify abandoned feature branches
- Track file deletion patterns

Agent 8: Configuration_Inspector
- Check for unused config files
- Find environment variables never read
- Identify obsolete feature flags
- Detect dead deployment configs

CRITICAL: Each agent must return:
1. List of deletion candidates with confidence scores
2. Evidence for why each file/code is dead
3. Potential risks if deleted
4. Dependencies that might break

Read the full file on GitHub · 365 lines

Changes

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.

  1. 3d ago First seen · 365 lines · 0 tokens per session scan A d7b7b850981c

Subscribe to this mod's changes

clean is a command published in the GitHub repository namastexlabs/automagik-cli (6 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,619 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.