digitalocean-registry-cleanup

digitalocean-registry-cleanup is a skill for Claude Code from Goodsmileduck/claude-registry. It costs 81 tokens per session (398 once invoked), scanned A, original, MIT.

A tool for analyzing and cleaning Docker images stored in DigitalOcean Container Registry, a service that stores container images. It can inspect repositories, remove older tags, find inactive repositories, and start storage cleanup.

In plain words
What is it for?
Showing repository and tag counts, previewing or performing old-tag deletion, finding stale repositories, and triggering garbage collection after cleanup.
Why use it?
Unused image tags and abandoned repositories consume registry storage and make it harder to identify the images that matter.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the digitalocean-skills plugin — 3 skills shipped together

Good fit Showing repository and tag counts, previewing or performing old-tag deletion, finding stale repositories, and triggering garbage collection after cleanup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup
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 Goodsmileduck/claude-registry --skill digitalocean-registry-cleanup
Clone the repo
git clone --depth 1 https://github.com/Goodsmileduck/claude-registry

Made for: Claude Code.

Or install digitalocean-skills, the plugin that ships this one along with the rest of its 3 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 digitalocean-registry-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup/github.svg)](https://agentmods.dev/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup)
Your own site
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup/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 digitalocean-registry-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/digitalocean-registry-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 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 $0.00081 $0.00398
Opus 5 $0.00041 $0.00199
Sonnet 5 $0.00016 $0.00080
Haiku 4.5 $0.00008 $0.00040

Measured 11d ago against content hash 2bf959174d3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

digitalocean-registry-cleanup 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/registry_cleanup.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/digitalocean-skills/skills/digitalocean-registry-cleanup/SKILL.md · 43 lines

What it actually says

DigitalOcean Registry Cleanup

Prerequisite: doctl CLI must be installed and authenticated (doctl auth init).

Script

Run scripts/registry_cleanup.py via Bash tool:

SCRIPT="<skill-path>/scripts/registry_cleanup.py"

# Analyze: show all repos with tag counts and dates
python3 $SCRIPT analyze

# Clean: delete old tags from a repo, keep newest N
python3 $SCRIPT clean <repo> --keep 5 --dry-run   # preview first
python3 $SCRIPT clean <repo> --keep 5              # execute

# Stale: find repos not updated in N months
python3 $SCRIPT stale --months 6                   # list only
python3 $SCRIPT stale --months 6 --delete          # delete all tags

# GC: trigger garbage collection to reclaim storage
python3 $SCRIPT gc

Workflow

  1. Run analyze to show registry overview
  2. Present the table to the user, ask which repos to clean and how many tags to keep
  3. Run clean <repo> --keep N --dry-run to preview
  4. On user confirmation, run clean <repo> --keep N to delete
  5. Run stale if user wants to find abandoned repos
  6. Run gc after all deletions to reclaim storage
  7. Run analyze again to show the result

Always use --dry-run first before destructive operations.

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. 11d ago First seen · 43 lines · 81 tokens per session scan A 2bf959174d3e

Subscribe to this mod's changes

digitalocean-registry-cleanup is a skill published in the GitHub repository Goodsmileduck/claude-registry (1 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 398 once invoked, about $0.0004 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.

Related

Other skills, from other repositories