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-reportgit 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-report)<a href="https://agentmods.dev/skills/drolosoft/immich-photo-manager/album-report"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/album-report/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-report"><img src="https://agentmods.dev/badge/skills/drolosoft/immich-photo-manager/album-report.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 | $0.00097 | $0.01144 |
| Opus 5.5 | $0.00039 | $0.00458 |
| Sonnet 5.5 | $0.00019 | $0.00229 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
album-report 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Album Report
⚠️ 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.
Build a PDF on the user's machine with export_pdf. Metadata comes from Immich; the descriptions come from you, after looking at the images.
Workflow
get_export_preview(album_id=...)(orasset_ids=...from a search). Note the count and which items are videos, with their duration.- Look:
get_album_images(album_id, size="thumbnail")for photos. For each video,get_video_frames(asset_id, count=6). - For a long video, skim it first with one call:
get_video_frames(asset_id, interval=5, sheet=true)returns contact sheets (30 stamped frames per image) instead of dozens of images. If a video needs a closer look (something passes between two frames), narrow it:get_video_frames(asset_id, count=8, start=8, end=12), orinterval=1for one frame per second. When the tool answers withconfirm_required, tell the user the number of frames and the estimated tokens and continue only if they agree (confirm=true). - Write one caption per asset (what it shows, in the user's language) into
captions={asset_id: text}. export_pdf(album_id=..., captions=..., frames_per_video=6); report the path, pages and warnings. Offerlayout="grid"for big sets,map=truewhen there is GPS data (explain it fetches OpenStreetMap tiles), and a higherframes_per_video(up to 120, free of tokens) for videos that matter.- If the user wants the photos themselves and not only the report,
get_download_info(album_id=...)says how big the zip would be and how many archives Immich would split it into, anddownload_archive(output_path=..., album_id=...)writes the originals next to the PDF. Say the size before downloading: originals and videos add up fast, and an existing file is never overwritten.
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.
- 1mo ago Changed 9b7178efcbb4
- 1mo ago Changed · +5 lines 6a16681c2f64
- 1mo ago First seen · 55 lines · 97 tokens per session scan A c35eba2c98bf
album-report is a skill published in the GitHub repository drolosoft/immich-photo-manager (60 stars, last pushed 22d ago), licensed MIT. It adds 97 tokens to every session and 1,144 once invoked, about $0.0004 per session on Opus 5.5. 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
pdf-report
Generate a branded PDF report: executive summary, campaign or channel review. "export this as a branded PDF".
dossier-builder
Generate complete buyer research reports and dealer proposals as HTML and PDF. Use for vehicle comparisons, market research, shortlists and default report delivery during a car-buying workflow. Triggers include "build dossier", "generate market research PDF", "dealer dossier", "decision document", "make dossier for…
doc-intel-contract-pl
Normalizuje wyjscie darmowego RODO-safe stacku OCR/PDF (opendataloader-pdf, pdftotext, Chandra OCR, LiteParse - OCR skanow na CPU, OCR PATRONa/Gaius-Lex) do jednego audytowalnego kontraktu {blocktype, bbox, text, confidence} inspirowanego architektura Mistral OCR 4 (idea, nie wagi - model zamkniety=SKIP). Daje trzy…
carfax-pdf-review
A review guide for dealer-provided PDFs, including CARFAX vehicle-history reports, service records, and out-the-door price proposals. It extracts accident information, service gaps, and extra financing or dealership charges.
waliduj-podpis-pdf-pl
Sprawdza podpis elektroniczny w PRZYCHODZĄCYM PDF - czy plik zmieniono po podpisaniu, kto go podpisał, kiedy, czy jest znacznik czasu i czy podpis obejmuje cały dokument. Działa lokalnie na pyHanko, bez sieci i bez wysyłania pliku gdziekolwiek (RODO-safe, tajemnica zawodowa). Wyłącznie odczyt - NIE podpisuje niczego.…
opendataloader-pdf
Wysokiej jakości konwerter PDF→JSON/Markdown dla AI - zachowuje reading order, strukturę tabel, headings. Użyj gdy użytkownik mówi "wysoka jakość PDF", "papers naukowe PDF", "tabele z PDF", "opendataloader", "PDF z skomplikowaną strukturą", albo gdy MarkItDown daje słaby output. Główny konwerter PDF→MD w pipeline…