photo-cleanup

photo-cleanup is a skill for Claude Code from drolosoft/immich-photo-manager. It costs 86 tokens per session (2,069 once invoked), scanned A, original, MIT.

A cleanup tool for an Immich photo library that finds screenshots, duplicate images, and low-quality photos. It presents possible removals for approval rather than deleting photos automatically.

In plain words
What is it for?
Use it to review screenshots, find duplicates, identify poor-quality images, and reclaim storage space.
Why use it?
It helps separate unwanted files from valuable photos while keeping the user in control of deletion.

Skill for Claude Code

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

Part of the immich-photo-manager plugin — 13 skills, 5 commands shipped together

Good fit Use it to review screenshots, find duplicates, identify poor-quality images, and reclaim storage space.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/drolosoft/immich-photo-manager/photo-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 drolosoft/immich-photo-manager --skill photo-cleanup
Clone the repo
git clone --depth 1 https://github.com/drolosoft/immich-photo-manager

Made for: Claude Code.

Or install immich-photo-manager, the plugin that ships this one along with the rest of its 13 skills, 5 commands.

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 photo-cleanup

README.md
[![agentmods](https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/photo-cleanup/github.svg)](https://agentmods.dev/skills/drolosoft/immich-photo-manager/photo-cleanup)
Your own site
<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/photo-cleanup"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/photo-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 photo-cleanup

Your own site · 80×15
<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/photo-cleanup"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/photo-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,069 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00086 $0.02069
Opus 5 $0.00043 $0.01035
Sonnet 5 $0.00017 $0.00414
Haiku 4.5 $0.00009 $0.00207

Measured 8d ago against content hash d01d488bc6e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

photo-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 8d 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.

skills/photo-cleanup/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Photo Cleanup

⚠️ Connection Required: ALWAYS CHECK FIRST

Before doing ANYTHING else in this skill, call ping on the Immich MCP server.

  • If ping succeeds → proceed with the skill normally.
  • If ping fails or the MCP tools are not available → STOP. Do not continue. Tell the user:

Immich is not connected. This plugin needs a running Immich MCP server to work.

Run /setup-immich-photo-manager to configure your Immich connection. You'll need:

  1. Your Immich server URL (e.g., http://192.168.1.100:2283)
  2. An Immich API key (how to create one)
  3. The MCP server configured (see /setup-immich-photo-manager)

Nothing in this plugin will work until the connection is configured.

Do NOT skip this check. Do NOT try to run any other tool first. Always ping, always block if it fails.

Intelligent photo library cleanup for Immich. Identifies and helps remove screenshots, duplicates, and low-quality images while protecting valuable photos.

Safety First

NEVER delete photos automatically. Always:

  1. Identify candidates for removal
  2. Present findings with counts and examples to the user
  3. Get explicit approval before any deletion
  4. Use delete_assets(asset_ids, force=False) to send photos to trash (recoverable). Use restore_assets or restore_trash to undo. Only use force=True for permanent deletion when the user explicitly requests it.

Cleanup Categories

1. Screenshot Detection

Screenshots are the #1 source of library bloat. Surface candidates with search_smart(query="screenshot") (CLIP) plus filename patterns (Screenshot*, Screen Shot*, Captura*) in search_metadata/list_assets results. Dimensions are NOT searchable. Then score each candidate by combining multiple signals (dimensions and EXIF come from get_asset_info, per asset):

Signal Weight How to detect
Screen resolution High get_asset_info dimensions match known screen sizes exactly
No GPS data Medium EXIF GPS fields empty
No lens info Medium No focal length, aperture, or lens model
Filename pattern Low Contains "Screenshot", "Screen Shot", "Captura"
No camera make/model Medium Missing or generic device info

Read the full file on GitHub · 165 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. 8d ago Changed d01d488bc6e2
  2. 8d ago Changed · +10 lines febbdd4a4bc8
  3. 12d ago First seen · 155 lines · 86 tokens per session scan A d1d917b7227d

Subscribe to this mod's changes

photo-cleanup is a skill published in the GitHub repository drolosoft/immich-photo-manager (47 stars, last pushed 8d ago), licensed MIT. It adds 86 tokens to every session and 2,069 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 2026-08-30.

Related

Other skills, from other repositories

ltxv2-video

Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models.

artokun/comfyui-mcp · 65 tokens

ideogram-ultra

Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.

artokun/comfyui-mcp · 68 tokens

video-extend

Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatchpusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into…

artokun/comfyui-mcp · 146 tokens

director

Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation.

artokun/comfyui-mcp · 32 tokens

ernie-image

Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…

artokun/comfyui-mcp · 98 tokens

model-compatibility

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.

artokun/comfyui-mcp · 47 tokens