What is immostage-staging?

A Claude skill for ImmoStage, a service that digitally furnishes empty property-room photos. It sends the image for processing and returns a download link.

It helps create virtual home staging for room photos and prepare furnished property images for download.

It removes the manual work of arranging virtual furniture and retrieving the finished image.

immostage-staging — Skill by LarryWalkerDEV

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.

agentmods

npx agentmods add skills/larrywalkerdev/mcp-immostage/skill

Any agent

npx skills add LarryWalkerDEV/mcp-immostage --skill skill

Clone the repo

git clone --depth 1 https://github.com/LarryWalkerDEV/mcp-immostage

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,062 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00090	$0.01062
Opus 5	$0.00045	$0.00531
Sonnet 5	$0.00018	$0.00212
Haiku 4.5	$0.00009	$0.00106

Measured 2d ago against content hash 4f81c96f12d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

immostage-staging 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 2d 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.

skill/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ImmoStage — Virtuelles Staging in Claude

This skill drives the ImmoStage MCP connector. The MCP runs all compute on ImmoStage's servers; you only collect inputs and hand back a download URL. Always respond in German.

Setup (guide the user if the connector is missing)

Claude Desktop, claude.ai, Claude Cowork (empfohlen):

Konto auf https://immostage.ai erstellen (3 kostenlose Bilder).
In Claude einen Custom Connector hinzufügen: URL https://mcp-immostage.vercel.app/api/mcp.
Mit dem ImmoStage-Konto anmelden — Claude übernimmt die Authentifizierung automatisch (OAuth). Kein Schlüssel nötig.

Claude Code (CLI): benötigt stattdessen einen Bearer-Schlüssel: Dashboard → Einstellungen → Claude / MCP Zugang → Schlüssel erstellen, dann als Authorization: Bearer mcp_live_…-Header verwenden.

If a tool call returns "Ungültiger Zugang", the OAuth-Anmeldung ist abgelaufen oder der CLI-Schlüssel ist ungültig/widerrufen — bei OAuth erneut anmelden lassen, bei der CLI auf das Dashboard verweisen, um einen neuen Schlüssel zu erstellen.

Optionen anbieten

Frage zuerst, was der Nutzer für seine Immobilie erstellen möchte, und zeige die Optionen:

Virtuelles Staging — leere Räume möblieren (verfügbar)
Marketing-Paket — 6 Social-Media-Posts, Exposé (PDF) und Immobilien-Video (verfügbar; das Video nur im Pro-Tarif)
Grundriss-Verschönerung — in Kürze

Workflow (Staging)

Frage nach dem Namen/der Adresse der Immobilie (z. B. „Hubertstraße 10, Berlin"). This groups the work into a project.
Sammle pro Raum: das Foto (öffentliche URL oder direkt eingefügtes Bild), den Stil (modern, scandinavian, classic, minimal, luxury) und den Raumtyp (living_room, bedroom, kitchen, bathroom, office, other).
Rufe stage_room mit property_name, Bild, style, room_type auf. Die Antwort enthält eine job_id (Staging läuft asynchron, i. d. R. 30–90 s).
Rufe check_staging mit der job_id auf. Kommt „Noch in Bearbeitung", nach ein paar Sekunden erneut prüfen. Wiederhole Schritt 2–4 für weitere Räume.
Optional: Möchte der Nutzer mehr als Bilder, rufe generate_marketing mit dem property_name auf — es erstellt 6 Social-Media-Posts, ein Exposé (PDF) und ein Immobilien-Video (asynchron, einige Minuten). Das Immobilien-Video erfordert den Pro-Tarif; weise Trial-/Starter-Nutzer vorab darauf hin. Meldet das Tool übersprungene Funktionen, gib den Hinweis samt Upgrade-Link unverändert weiter.
Wenn der Nutzer fertig ist, rufe get_download_link mit dem property_name auf und gib ihm die Download-Website: eine Seite mit allen Assets in strukturierten Ordnern (ZIP), 3 Tage gültig. Zusätzlich liefert das Tool den dauerhaften Link zum ImmoStage-Dashboard des Projekts (Login erforderlich) — dort bleiben die Assets über die 3 Tage hinaus verfügbar.

Read the full file on GitHub · 71 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.

2d ago First seen · 71 lines · 90 tokens per session scan A 4f81c96f12d3

Subscribe to this mod's changes

immostage-staging is a skill published in the GitHub repository LarryWalkerDEV/mcp-immostage (3 stars, last pushed 28d ago), licensed MIT. It adds 90 tokens to every session and 1,062 once invoked, about $0.0005 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.

Creative and media ai-staging immobilien mcp mcp-server proptech real-estate

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

xcodebuildmcp-structured-output-review

Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.

getsentry/XcodeBuildMCP · 37 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

mcp-transport-contract-auditor

Route shaft-mcp transport-contract audits to the canonical playbook.

ShaftHQ/SHAFT_ENGINE · 22 tokens

create-operator

MUST READ before creating or moving any operator (createop, copyop, setopposition, or executepython builds). Required verification, canonical positioning recipe, and error-checking steps.

dylanroscover/Embody · 42 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens