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 album-managergit 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/album-manager)<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/album-manager"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/album-manager/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/album-manager"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/album-manager.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 | $0.00126 | $0.03433 |
| Opus 5 | $0.00063 | $0.01716 |
| Sonnet 5 | $0.00025 | $0.00687 |
| Haiku 4.5 | $0.00013 | $0.00343 |
Grade A, and why
album-manager 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 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.
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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Album Manager
⚠️ 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 running (
./immich-mcp-server)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 album creation and curation for Immich photo libraries. Organizes photos geographically by default: albums represent places, not dates.
Core Principle
Geography first, chronology second. A user who visited Mexico twice gets one "Mexico" album (or sub-albums by city), not "Mexico 2018" and "Mexico 2023". Dates are metadata shown inside the album, never the organizing principle.
Available MCP Tools
Use the Immich MCP tools for all API interactions:
search_metadata: Search by city, state, country, camera make/model, date range (taken_after/taken_before), favorites, or asset typesearch_smart: CLIP semantic search from a natural language description (e.g. "Colosseum Rome Italy")get_map_markers: Get GPS markers (up to 500) for all geotagged assets; filter by coordinates client-sidecreate_album: Create a new album with name and descriptionadd_assets_to_album: Add photos/videos to an album by asset IDsremove_assets_from_album: Remove assets from an albumlist_albums: List all albums with asset countsget_album: Get album details including all assetsdelete_album: Delete an album (does NOT delete the photos)create_shared_link: Create a public shared link for an album (makes it visible in Gallery)get_asset_info: Get full metadata for a specific asset (GPS, EXIF, dates)get_statistics: Get library statistics (total photos, videos, storage)get_asset_thumbnail: Get base64 thumbnail for an asset (used for gallery HTML generation)create_stack/list_stacks: Group near-identical shots under one cover asset instead of dropping them; the album shows the stack as a single itemget_download_info: Size of the zip an album would make, before building itdownload_archive: Write the album's originals to a zip on the machine running the server
What ships with it
2 files 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.
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.
- 7d ago Changed dd58a40f8540
- 8d ago Changed · +5 lines 378245725c0b
- 11d ago First seen · 286 lines · 126 tokens per session scan A d7d658b187e6
album-manager is a skill published in the GitHub repository drolosoft/immich-photo-manager (47 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 3,433 once invoked, about $0.0006 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.