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.
npx skills add drolosoft/immich-photo-manager --skill photo-cleanupgit clone --depth 1 https://github.com/drolosoft/immich-photo-managerWrote 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.
[](https://agentmods.dev/skills/drolosoft/immich-photo-manager/photo-cleanup)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
pingsucceeds → proceed with the skill normally. - If
pingfails 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:
- Your Immich server URL (e.g.,
http://192.168.1.100:2283)- An Immich API key (how to create one)
- 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:
- Identify candidates for removal
- Present findings with counts and examples to the user
- Get explicit approval before any deletion
- Use
delete_assets(asset_ids, force=False)to send photos to trash (recoverable). Userestore_assetsorrestore_trashto undo. Only useforce=Truefor 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 |
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.
- 8d ago Changed d01d488bc6e2
- 8d ago Changed · +10 lines febbdd4a4bc8
- 12d ago First seen · 155 lines · 86 tokens per session scan A d1d917b7227d
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.
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.
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.
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…
director
Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation.
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…
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.