spring-clean

spring-clean is a skill for Claude Code, Codex from smk-labs/claude-plugins. It costs 226 tokens per session (2,067 once invoked), scanned A, original, MIT.

A repository clean-up process that simplifies a codebase while preserving its behaviour. A repository is the project's tracked files and history.

In plain words
What is it for?
Use it to find dead files, oversized code, duplicated logic, misplaced documentation, build artifacts, and missing tests across a whole project.
Why use it?
It helps remove unused code and clutter, reduce duplication, and leave rules that make the project easier to maintain.

Skill for Claude CodeCodex

Part of the spring-clean plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/smk-labs/claude-plugins/spring-clean
Any agent
npx skills add smk-labs/claude-plugins --skill spring-clean
Clone the repo
git clone --depth 1 https://github.com/smk-labs/claude-plugins

Made for: Claude Code, Codex.

Or install spring-clean, the plugin that ships this one along with the rest of its 2 skills.

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 spring-clean

README.md
[![agentmods](https://agentmods.dev/badge/skills/smk-labs/claude-plugins/spring-clean.svg)](https://agentmods.dev/skills/smk-labs/claude-plugins/spring-clean)
Your own site
<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/spring-clean"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/spring-clean.svg" alt="Measured on agentmods" height="20"></a>
Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,067 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00226 $0.02067
Opus 5 $0.00113 $0.01033
Sonnet 5 $0.00045 $0.00413
Haiku 4.5 $0.00023 $0.00207

Measured 5d ago against content hash 9fb168fd6608, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

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 5d 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/skills/spring-clean/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spring-clean a repository the way خونه تکونی cleans a house before the new year: everything comes out, only what belongs goes back, and the house gets rules that keep it clean. The pass is behaviour-preserving, and it is not a deletion contest. The one real pass on record was net +5,185 lines, and its single most valuable outcome was writing the first tests a security file ever had.

Phase 0: frame it, before any edit

Declare the scoreboard. Pick the numbers this pass will be judged on, measure them now, re-measure at the end. A worked set: files over the cap, worst complexity ceiling, linter warnings, test count, architecture test files, root non-code files. Each metric ships the command that produces it, or it is not re-measurable: scope and off-by-one will differ, and the second measurement quietly answers a different question. Two scoreboards, not one. What got cleaner in the code repo is the score. What got relocated (workspace file counts, disk freed) is reported separately and is not cleaning, because a score that rewards moving files is gameable by shuffling.

Write the red lines, now, not when you hit them. What must not change, each with its reason: vendored slices that stay diffable against upstream, guards whose branches only run under attack, a public surface that is a contract, byte budgets you must measure rather than quote, anything the repo declares law. Also: behaviour does not change, so a change that reddens an existing test is wrong and the test is right.

Name the gate and the other writers. Write the exact command, and read each exit code separately, never through a pipe: a pipe throws the code away and && hides every failure but the last. Assume a second writer in the tree: scope every commit to its own paths, stage and commit in one step, take a second reading before believing work is lost, and commit a green change immediately.

Phase 1: survey once, then write the plan down

Read-only, wide, one agent per slice, and never repeated. Look for: top files by line count and functions past ~40 lines; checked-in build artifacts (if a pipeline builds it, git must not hold it); dead surfaces including CI jobs whose only trigger was removed; companion material in the code tree; the untracked tree, because gitignored is not clean (reference clones, data dumps, scratch folders); duplicated tables; import-graph smells; clean-code offenders in the worst files.

Read the full file on GitHub · 75 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. 5d ago First seen · 75 lines · 226 tokens per session scan A 9fb168fd6608

Subscribe to this mod's changes

spring-clean is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It adds 226 tokens to every session and 2,067 once invoked, about $0.0011 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 2026-08-30.

Related

Other skills, from other repositories

brainstorm-okrs

Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

phuryn/pm-skills · 49 tokens

ab-test-analysis

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.

phuryn/pm-skills · 54 tokens

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens

outcome-roadmap

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.

phuryn/pm-skills · 53 tokens

pre-mortem

Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…

phuryn/pm-skills · 79 tokens

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens