clean-repo

clean-repo is a command for Claude Code from davistroy/claude-marketplace. It costs 10 tokens per session (3,477 once invoked), scanned A, original, MIT.

A repository cleanup and documentation-refresh command. It first analyzes the repository, then can propose or perform organization, cleanup, and documentation updates.

In plain words
What is it for?
Auditing a repository, previewing or applying file cleanup, synchronizing documentation, recording actions in a JSON audit log, and producing structured JSON output for automated pipelines.
Why use it?
It helps identify obsolete files, misplaced artifacts, and documentation that no longer matches the repository. A dry-run can show proposed changes before anything is changed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Auditing a repository, previewing or applying file cleanup, synchronizing documentation, recording actions in a JSON audit log, and producing structured JSON output for automated pipelines.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/clean-repo
Install

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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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-repo

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/clean-repo/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/clean-repo)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/clean-repo"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/clean-repo/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.

agentmods 80×15 button for clean-repo

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/clean-repo"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/clean-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,477 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 $0.00010 $0.03477
Opus 5 $0.00005 $0.01739
Sonnet 5 $0.00002 $0.00695
Haiku 4.5 $0.00001 $0.00348

Measured 12d ago against content hash 3baf1ee63143, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clean-repo 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 12d 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.

plugins/personal-plugin/commands/clean-repo.md · 450 lines

How it starts

The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Cleanup and Organization

Perform a thorough cleanup and organization pass on this repository. This command requires deep analysis of the codebase before any cleanup actions.

Input Validation

Optional Arguments:

  • --dry-run - Preview all changes without executing them
  • --audit - Log all actions to .claude-plugin/audit.log
  • --docs-only - Skip artifact cleanup, focus only on documentation sync
  • --json - Output results as structured JSON instead of text. Enables CI/CD pipeline integration and programmatic consumption.

Dry-Run Mode: When --dry-run is specified:

  • Perform all analysis phases normally
  • Show what files would be deleted, moved, or modified
  • Show what documentation updates would be made
  • Prefix all proposed actions with [DRY-RUN]
  • Do NOT execute any file deletions, moves, or modifications

Audit Mode: When --audit is specified:

  • Log every action to .claude-plugin/audit.log
  • Each log entry is a JSON line with: timestamp, command, action, path, success

Phase 0: Deep Repository Analysis (REQUIRED)

CRITICAL: This phase must be completed thoroughly before any cleanup.

Before cleaning or updating anything, you MUST understand what this repository actually contains and does. Use the available tools to build a complete mental model.

0.1 Project Discovery

Execute these analysis steps:

1. Read the root README.md completely
2. Read CLAUDE.md if present
3. Examine the directory structure (use Glob to map all directories)
4. Identify the project type(s): library, CLI tool, plugin, monorepo, etc.
5. Find all package manifests (package.json, pyproject.toml, plugin.json, etc.)

0.2 Feature Inventory

Build a complete list of what this project provides:

For plugins/tools:

  • List all commands/skills with their actual functionality
  • Read command/skill files to understand what each does
  • Note any bundled tools or utilities

For libraries:

  • List all exported functions/classes
  • Identify the public API surface
  • Note major features and capabilities

Read the full file on GitHub · 450 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. 12d ago First seen · 450 lines · 10 tokens per session scan A 3baf1ee63143

Subscribe to this mod's changes

clean-repo is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 3,477 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.