ExtremeRouter: Skill for Claude Code

.agents/skills/extreme-router-gateway-engine/SKILL.md

extreme-router-gateway-engine is a skill for Claude Code, Codex from rsalmn/ExtremeRouter. It costs 81 tokens per session (2,318 once invoked), scanned A, original, MIT.

A skill describing how ExtremeRouter sends AI requests through different providers, including routing, retries, format conversion, streaming, and usage tracking.

In plain words
What is it for?
Use it when adding providers, changing fallback or token-refresh behavior, translating API formats, optimizing token use, or investigating request routing.
Why use it?
It helps an agent locate the part of the request pipeline responsible for receiving, translating, executing, and returning an AI request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Gemini CLI.

This is rsalmn/ExtremeRouter's own configuration. It tells Claude Code and Codex how to work on ExtremeRouter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ExtremeRouter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rsalmn/ExtremeRouter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rsalmn/ExtremeRouter/main/.agents/skills/extreme-router-gateway-engine/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rsalmn/ExtremeRouter

Made for: Claude Code, Codex.

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 extreme-router-gateway-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/rsalmn/extremerouter/extreme-router-gateway-engine/github.svg)](https://agentmods.dev/skills/rsalmn/extremerouter/extreme-router-gateway-engine)
Your own site
<a href="https://agentmods.dev/skills/rsalmn/extremerouter/extreme-router-gateway-engine"><img src="https://agentmods.dev/badge/skills/rsalmn/extremerouter/extreme-router-gateway-engine/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 extreme-router-gateway-engine

Your own site · 80×15
<a href="https://agentmods.dev/skills/rsalmn/extremerouter/extreme-router-gateway-engine"><img src="https://agentmods.dev/badge/skills/rsalmn/extremerouter/extreme-router-gateway-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,318 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00081 $0.02318
Opus 5 $0.00041 $0.01159
Sonnet 5 $0.00016 $0.00464
Haiku 4.5 $0.00008 $0.00232

Measured 11d ago against content hash 14d73d4efdb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

extreme-router-gateway-engine 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 11d 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.

.agents/skills/extreme-router-gateway-engine/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Gateway Engine Expertise

You are an expert in AI Gateway architecture, provider routing, and API compatibility.

Core Concepts

Request Flow

Client Request → /v1/* endpoint
  → Route handler (src/app/api/v1/*)
  → Chat handler (src/sse/handlers/chat.js)
  → Core orchestrator (open-sse/handlers/chatCore.js)
  → Provider executor (open-sse/executors/*)
  → Upstream provider API
  → Response translation (open-sse/translator/*)
  → Client response (SSE stream or JSON)

Key Components

1. Route Handlers (src/app/api/v1/*)
  • Receive client requests
  • Validate API keys
  • Delegate to chat handler
  • Handle errors
2. Chat Handler (src/sse/handlers/chat.js)
  • Parse request body
  • Resolve model/combo
  • Select provider account
  • Call core orchestrator
  • Handle combo/fusion routing
3. Core Orchestrator (open-sse/handlers/chatCore.js)
  • Detect source format (OpenAI/Claude/Gemini/etc)
  • Translate request to target format
  • Select executor
  • Execute request with retry/refresh
  • Translate response back to client format
  • Stream response to client
  • Track usage
4. Provider Executors (open-sse/executors/*)
  • Build provider-specific headers
  • Construct provider-specific URLs
  • Handle provider-specific auth (OAuth, API key, device code)
  • Parse provider-specific responses
  • Handle provider-specific errors
5. Format Translators (open-sse/translator/*)
  • Convert between API formats
  • Request translators: openai-to-*, claude-to-*, etc
  • Response translators: *-to-openai, etc
  • Concerns: shared translation logic (tool calls, usage, reasoning, etc)

Provider Management

Adding a New Provider

  1. Create executor (open-sse/executors/[provider].js)

    • Extend BaseExecutor
    • Implement buildHeaders(credentials, stream)
    • Implement buildUrl(model, stream, urlIndex, credentials)
    • Implement execute(request, credentials, options)
    • Handle provider-specific auth refresh
  2. Register provider (open-sse/config/providers.js)

    • Add provider config (baseUrl, headers, capabilities)
    • Define supported models
    • Set auth type (oauth/api_key/device_code)

Read the full file on GitHub · 336 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. 11d ago First seen · 336 lines · 81 tokens per session scan A 14d73d4efdb3

Subscribe to this mod's changes

extreme-router-gateway-engine is a skill published in the GitHub repository rsalmn/ExtremeRouter (34 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,318 once invoked, about $0.0004 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 2026-08-30.