litellm-vertex-ai-proxy

litellm-vertex-ai-proxy is a skill for Claude Code from rhtevan/agentfs. It costs 24 tokens per session (2,282 once invoked), scanned A, original, Apache-2.0.

A setup guide for LiteLLM, a local proxy that gives applications a common OpenAI-compatible interface, while sending requests to Claude models through Google Cloud Vertex AI.

In plain words
What is it for?
Use it to run the proxy on Linux, connect it to Vertex AI with a service account, and let compatible coding tools use the available models.
Why use it?
It gathers authentication, model routing, and automatic startup into one local service instead of configuring each application separately.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to run the proxy on Linux, connect it to Vertex AI with a service account, and let compatible coding tools use the available models.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rhtevan/agentfs/litellm-vertex-ai-proxy
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 rhtevan/agentfs --skill litellm-vertex-ai-proxy
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

Made for: Claude Code.

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 litellm-vertex-ai-proxy

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhtevan/agentfs/litellm-vertex-ai-proxy/github.svg)](https://agentmods.dev/skills/rhtevan/agentfs/litellm-vertex-ai-proxy)
Your own site
<a href="https://agentmods.dev/skills/rhtevan/agentfs/litellm-vertex-ai-proxy"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/litellm-vertex-ai-proxy/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 litellm-vertex-ai-proxy

Your own site · 80×15
<a href="https://agentmods.dev/skills/rhtevan/agentfs/litellm-vertex-ai-proxy"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/litellm-vertex-ai-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,282 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.
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 $0.00024 $0.02282
Opus 5 $0.00012 $0.01141
Sonnet 5 $0.00005 $0.00456
Haiku 4.5 $0.00002 $0.00228

Measured 8d ago against content hash 909192c7f683, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

litellm-vertex-ai-proxy 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/detect-sa.sh, scripts/probe-models.sh, scripts/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/litellm-vertex-ai-proxy/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LiteLLM Proxy for GCP Vertex AI

Set up a local LiteLLM proxy that fronts GCP Vertex AI as an OpenAI-compatible endpoint, managed by systemd, with proper service account credentials.

Overview

This skill deploys LiteLLM locally as a proxy that:

  • Exposes http://127.0.0.1:4000/v1 (OpenAI-compatible)
  • Routes requests to GCP Vertex AI (Anthropic Claude models)
  • Uses a GCP service account key (no expiring refresh tokens)
  • Auto-starts at boot via a systemd user service

Any AI agent or application that supports OpenAI-compatible endpoints can use this proxy. See agent-specific skills (goose-litellm-provider, hermes-litellm-provider) for integration guidance.

Prerequisites

  • Linux with systemd (Fedora, RHEL, Ubuntu, etc.)
  • uv package manager (which uv or install from https://docs.astral.sh/uv/)
  • gcloud CLI authenticated (gcloud auth login)
  • A GCP project with Vertex AI API enabled
  • A GCP service account key (JSON) with roles/aiplatform.user permission
  • python3 with google-auth package

Known Available Models (as of 2026-08-10)

Model Region Context Window
claude-opus-4-6 us-east5 1M tokens
claude-sonnet-4-6 us-east5 1M tokens
claude-haiku-4-5 us-east5 200k tokens

Workflow

Step 1 — Detect GCP Configuration

bash ~/.agents/skills/litellm-vertex-ai-proxy/scripts/detect-sa.sh

Identifies GCP project, active account, and all service account key files. Prints metadata (type, email, truncated key ID) — never exposes private keys.

Step 2 — Test Service Account Permissions

bash ~/.agents/skills/litellm-vertex-ai-proxy/scripts/test-sa.sh \
  --sa-key <path_to_key.json> \
  --project <project_id> \
  --region us-east5

Sends a minimal Vertex AI request using the SA key. If 403, the account needs roles/aiplatform.user — contact GCP admin.

Step 3 — Discover Available Models

bash ~/.agents/skills/litellm-vertex-ai-proxy/scripts/probe-models.sh \
  --project <project_id> --region us-east5

Read the full file on GitHub · 198 lines

Files

What ships with it

6 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.

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 First seen · 198 lines · 24 tokens per session scan A 909192c7f683

Subscribe to this mod's changes

litellm-vertex-ai-proxy is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,282 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

stripe-projects

Provision SaaS services + sync creds via Stripe Projects.

NousResearch/hermes-agent · 15 tokens

azure-eventhub-dotnet

Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming"…

microsoft/skills · 94 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

django-storages-s3

Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…

Jeffallan/claude-skills · 138 tokens

wikipedia

Search and read Wikipedia via x wkp — MediaWiki API, no API key, zero install; query, extract, suggest, and DDG route in one module. Load for wiki, wikipedia, encyclopedia lookup, article summary.

x-cmd/x-cmd · 49 tokens

cve

Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.

x-cmd/x-cmd · 49 tokens