llm-gateway-and-multi-provider-routing

llm-gateway-and-multi-provider-routing is a skill for Claude Code from selvarajmurugesan90/ops-engineering-skills. It costs 150 tokens per session (4,308 once invoked), scanned A, original, Apache-2.0.

A guide for configuring an LLM gateway, a proxy that gives applications one interface to several AI model providers.

In plain words
What is it for?
Use it to set routing and fallback rules, balance requests across providers, and monitor spending and rate-limit capacity through one API.
Why use it?
It centralizes provider routing, fallback when a provider is unavailable or rate-limited, traffic distribution, and tracking of usage costs and limits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions Gemini CLI.

Part of the ai-agent-skills plugin — 20 skills shipped together

Good fit Use it to set routing and fallback rules, balance requests across providers, and monitor spending and rate-limit capacity through one API.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing
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 selvarajmurugesan90/ops-engineering-skills --skill llm-gateway-and-multi-provider-routing
Clone the repo
git clone --depth 1 https://github.com/selvarajmurugesan90/ops-engineering-skills

Made for: Claude Code.

Or install ai-agent-skills, the plugin that ships this one along with the rest of its 20 skills.

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 llm-gateway-and-multi-provider-routing

README.md
[![agentmods](https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing/github.svg)](https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing)
Your own site
<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing/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 llm-gateway-and-multi-provider-routing

Your own site · 80×15
<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/llm-gateway-and-multi-provider-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 7 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 68
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 259
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 376
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 80
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 212
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 377
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Data Exfiltration · line 189
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00150 $0.04308
Opus 5 $0.00075 $0.02154
Sonnet 5 $0.00030 $0.00862
Haiku 4.5 $0.00015 $0.00431

Measured 13d ago against content hash 71d2ca3084b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

llm-gateway-and-multi-provider-routing scanned grade A with 1 finding 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 13d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://<gateway>/key/generate \
plugins/ai-agent/skills/llm-gateway-and-multi-provider-routing/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Gateway and Multi-Provider Routing

Purpose

Calling model providers directly from application code works until you need more than one provider — a fallback when a primary provider has an outage or exhausts a rate limit, a way to shift traffic between providers/regions/API keys for cost or availability, or a single place to see spend and rate-limit headroom across every provider your agents use. An LLM gateway (LiteLLM proxy, Portkey, OpenRouter, or an equivalent internal proxy) solves this by presenting one unified API surface backed by a routing/fallback layer, so application code targets "the gateway" once instead of hand-rolling provider-specific retry and failover logic in every agent. This skill covers configuring that gateway layer specifically — provider/model routing rules, fallback chains, load balancing, and unified rate-limit/cost tracking — not the per-workflow cost/latency tuning of what you send to a model (see llm-cost-and-latency-optimization) or the fast triage of a single workflow's cost/latency spike (see agent-cost-and-latency-spike-investigation), both of which assume a gateway (if one exists) is already routing correctly.

When to use

  • Standing up a gateway/proxy in front of two or more LLM providers (or two or more accounts/regions of the same provider) so agent code calls one endpoint instead of provider-specific SDKs directly.
  • Adding a fallback model/provider that should take over automatically when the primary provider returns 5xx errors, times out, or returns a rate-limit (429) response.
  • A provider outage or rate-limit event happened and fallback either didn't trigger, triggered too late, or routed to a fallback that itself failed silently.
  • Setting per-team, per-project, or per-API-key budgets and rate limits that need to be enforced consistently across multiple providers, not per-provider in each provider's own console.
  • Load-balancing traffic across multiple API keys/deployments of the same model to work around a single key's rate limit.
  • Needing one place to see aggregate spend and usage across providers, rather than reconciling separate invoices/dashboards per vendor.

Read the full file on GitHub · 378 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.

  1. 13d ago First seen · 378 lines · 150 tokens per session scan A 71d2ca3084b2

Subscribe to this mod's changes

llm-gateway-and-multi-provider-routing is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (39 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 150 tokens to every session and 4,308 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens