spring-cleaning

spring-cleaning is a skill for Codex from ohong/agent-skills. It costs 119 tokens per session (2,552 once invoked), scanned C, original, MIT.

A guided cleanup process for freeing storage space on a Mac. It first uses a storage report to identify what is taking up room and checks backups, cloud syncing, and external storage before suggesting removal or relocation.

In plain words
What is it for?
Use it when a Mac is nearly full, to inspect disk usage and create a safe, prioritized cleanup plan using tools such as DaisyDisk, ncdu, dust, fdupes, or Homebrew.
Why use it?
It helps find large or unnecessary files while reducing the risk of deleting something that is not backed up or still needed.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it when a Mac is nearly full, to inspect disk usage and create a safe, prioritized cleanup plan using tools such as DaisyDisk, ncdu, dust, fdupes, or Homebrew.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ohong/agent-skills/spring-cleaning
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.

Any agent
npx skills add ohong/agent-skills --skill spring-cleaning
Clone the repo
git clone --depth 1 https://github.com/ohong/agent-skills

Made for: Codex.

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-cleaning

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohong/agent-skills/spring-cleaning.svg)](https://agentmods.dev/skills/ohong/agent-skills/spring-cleaning)
Your own site
<a href="https://agentmods.dev/skills/ohong/agent-skills/spring-cleaning"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/spring-cleaning.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00119 $0.02552
Opus 5 $0.00060 $0.01276
Sonnet 5 $0.00024 $0.00510
Haiku 4.5 $0.00012 $0.00255

Measured 7d ago against content hash c237efc912b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

spring-cleaning scanned grade C with 1 finding 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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.Trash/*
spring-cleaning/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spring Cleaning — Mac Disk Space Cleanup

A skill for generating a safe, prioritized, step-by-step runbook to free up local disk space on a Mac. Before recommending offloading or deletion, confirm the user's backup, cloud-sync, and external-storage setup. Useful optional tools include DaisyDisk, ncdu, dust, fdupes, and brew.


Step 1 — Get a Storage Snapshot

Before generating the runbook, the agent needs a storage report. Accept any of the following (in order of detail/usefulness):

Report Type How to Get It Detail Level
dust output dust -d 4 /Users/<name> 2>/dev/null ✅ Good
DaisyDisk screenshot Scan Macintosh HD, share screenshot ✅ Good
ncdu filtered output See command below ✅✅ Best
System Settings > Storage screenshot Built-in macOS storage view ⚠️ Low (ask for more)

ncdu filtered command (recommend this if user hasn't run anything yet):

ncdu / -o /tmp/ncdu_out.json 2>/dev/null && python3 << 'EOF'
import json
with open('/tmp/ncdu_out.json') as f:
    data = json.load(f)
def walk(node, path='', threshold=200*1024*1024):
    if isinstance(node, list):
        info = node[0]
        name = info.get('name', '')
        full = f"{path}/{name}".replace('//', '/')
        size = info.get('asize', 0)
        if size > threshold:
            print(f"{size // 1024 // 1024}MB\t{full}")
        for child in node[1:]:
            walk(child, full, threshold)
    elif isinstance(node, dict):
        name = node.get('name', '')
        full = f"{path}/{name}".replace('//', '/')
        size = node.get('asize', 0)
        if size > threshold:
            print(f"{size // 1024 // 1024}MB\t{full}")
root = data[2]
walk(root, threshold=200*1024*1024)
EOF

If the user only provides a high-level screenshot (e.g. macOS Storage view showing category totals), ask for a DaisyDisk scan or dust output before generating the runbook — the category-level view isn't granular enough to write safe, targeted commands.

Read the full file on GitHub · 315 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 315 lines · 119 tokens per session scan C c237efc912b6

Subscribe to this mod's changes

spring-cleaning is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 2,552 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.