What is dsh-litellm-provider?

A configuration guide that connects DeepSeek Harness to a local LiteLLM proxy using an OpenAI-compatible interface. DeepSeek Harness is the application being configured, while LiteLLM is a proxy that presents model services through a common API.

Use it to write the provider settings into DeepSeek Harness, including the local proxy address and available model identifiers. It requires an installed Harness and a running LiteLLM proxy.

It avoids configuring each model connection directly in the Harness web interface. Models served by the local proxy can appear as selectable routes in that interface.

dsh-litellm-provider — Skill for Claude Code by rhtevan

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 dsh-litellm-provider

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rhtevan/agentfs/dsh-litellm-provider/github.svg)](https://agentmods.dev/skills/rhtevan/agentfs/dsh-litellm-provider)

Your own site

<a href="https://agentmods.dev/skills/rhtevan/agentfs/dsh-litellm-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/dsh-litellm-provider/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rhtevan/agentfs/dsh-litellm-provider"><img src="https://agentmods.dev/badge/skills/rhtevan/agentfs/dsh-litellm-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,657 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.

Model	Per session	Once invoked
Fable 5.1	$0.00026	$0.01657
Opus 5	$0.00013	$0.00829
Sonnet 5	$0.00005	$0.00331
Haiku 4.5	$0.00003	$0.00166

Measured 8d ago against content hash 15e067cdb215, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dsh-litellm-provider 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 2 executable files (scripts/setup.sh, scripts/verify.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/dsh-litellm-provider/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configure DSH with Local LiteLLM Proxy Provider

Set up DeepSeek Harness to use a local LiteLLM proxy as a custom OpenAI-compatible provider. This writes the provider configuration to DSH's settings.yaml so the Claude models served by LiteLLM (via Vertex AI) are available as model routes in the DSH WebUI.

For DSH installation, see the dsh-setup skill first.

Prerequisites

DSH installed and launchable (see skill dsh-setup)
LiteLLM proxy running locally at http://127.0.0.1:4000 (see skill litellm-vertex-ai-proxy to set one up)
Use skill litellm-proxy-status to verify the proxy is healthy before proceeding

Architecture

DSH stores settings in ~/.dsh/settings.yaml (or $DSH_HOME/settings.yaml). The llm-pi-ai plugin manages model providers. A custom provider needs:

Field	Purpose
`baseURL`	LiteLLM endpoint: `http://127.0.0.1:4000/v1`
`api`	Protocol: `openai-completions`
`apiKeyEnv`	Env var holding a dummy API key (DSH requires non-empty)
`models`	List of model IDs matching LiteLLM's `model_name` entries
`compat`	Protocol compatibility flags for LiteLLM

Reference Configuration

File: ~/.dsh/settings.yaml (relevant section)

⚠️ Use this exact schema. Do NOT write from memory or improvise field names. Copy this template and substitute only the marked placeholders.

llm-pi-ai:
  providers:
    litellm-vertex-ai:
      apiKeyEnv: LITELLM_VERTEX_AI_API_KEY
      api: openai-completions
      baseURL: http://127.0.0.1:4000/v1
      compat:
        supportsDeveloperRole: false
        maxTokensField: max_tokens
      models:
        - id: claude-opus-4-6
          input: [text, image]
        - id: claude-sonnet-4-6
          input: [text, image]
        - id: claude-haiku-4-5
          input: [text, image]

Compatibility Flags

Flag	Value	Why
`supportsDeveloperRole`	`false`	LiteLLM proxies `role: "developer"` as-is but Vertex AI Claude doesn't accept it. Forcing `false` makes DSH send `role: "system"` instead.
`maxTokensField`	`max_tokens`	LiteLLM uses the OpenAI `max_tokens` field, not `max_completion_tokens`.

Read the full file on GitHub · 164 lines

Files

What ships with it

3 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.

8d ago First seen · 164 lines · 26 tokens per session scan A 15e067cdb215

Subscribe to this mod's changes

dsh-litellm-provider is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,657 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.

Backend and APIs Data and AI

gemini-api-agent-platform

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

davila7/claude-code-templates · 61 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens

gemini-api-dev

Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best…

google-gemini/gemini-skills · 73 tokens

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…

NVIDIA/skills · 219 tokens

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

azure-search-documents-ts

Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.

microsoft/skills · 48 tokens