spring-clean

A two-pass repository cleanup process that measures the project against a declared scoreboard and records the work in a numbered plan. It can organize development files, split oversized files, define package boundaries, and add rules for future checks.

In plain words
What is it for?
It helps clean or ignore misplaced files, move development material to a workspace repository, divide large files, establish package boundaries, and document enforceable project rules.
Why use it?
It helps distinguish project files from temporary notes, clones, dumps, and development material while leaving a plan that can survive an interrupted session.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add smk-labs/claude-plugins
agentmods
npx agentmods add plugins/smk-labs/claude-plugins/spring-clean
Clone the repo
git clone --depth 1 https://github.com/smk-labs/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

spring-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 2d 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.

spring-clean/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "spring-clean",
  "description": "Two passes over a repo. spring-clean measures against a declared scoreboard, deletes or gitignores what does not belong, relocates dev docs, notes, clones and dumps to a <project>-workspace repo, splits oversized files, draws package boundaries and writes its plan to a numbered unit list that survives a dead context. workspace-rules then gives that repo its rules at both layers, sorting each by what it hands the model: information it cannot infer is told where a session starts, anything a script could count is counted as a linter setting, an architecture test or a hook proved red by name and green on an untouched tree, and the cap, the displacement clause and the dated judged-out list go inside the check file itself.",
  "version": "3.0.0",
  "author": {
    "name": "Seyed M. Keramati",
    "url": "https://github.com/SMKeramati"
  }
}
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. 2d ago First seen · 10 lines scan A 55802c8f309f

Subscribe to this mod's changes

spring-clean is a plugin published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.