Skip to content
Back to skills

Llm Gateway Routing

ASecurity

Canonical LLM gateway/routing/proxy playbook: multi-provider failover, token reduction proxies, and cost wrappers.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agentsgitapi

Works with

  • api

Security analysis

A100/100

Scanned September 19, 2026

npx -y skills add rogue-dev-studio/ai-agents-rogue --skill llm-gateway-routing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Llm Gateway Routing?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Llm Gateway Routing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rogue-dev-studio-llm-gateway-routing/badge)](https://www.skillsdirectory.com/skills/rogue-dev-studio-llm-gateway-routing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: llm-gateway-routing
description: >-
  Canonical LLM gateway/routing/proxy playbook: multi-provider failover,
  token reduction proxies, and cost wrappers.
---

# LLM Gateway Routing (Canonical)

**Level: max.** Aliases: `claude-code-mux`, `rtk`, `zai-service`, `claudish` (routing/proxy aspect).

## Procedure

1. Catat provider yang diizinkan + budget.
2. Satu gateway entrypoint per environment.
3. Failover policy: primary → secondary; jangan loop tak terbatas.
4. Token/cost controls (`rtk` / wrapper) dengan logging tanpa PII.
5. Jangan hardcode API keys; rotasi terdokumentasi.

## DoD

- [ ] Entry URL/env terdokumentasi
- [ ] Failover diuji
- [ ] Tidak ada key di git
## Attribution

<!-- ATTRIBUTION: Rogue Development | https://github.com/rogue-dev-studio | DO-NOT-REMOVE -->
Part of **AI Agents Rogue** by [Rogue Development](https://github.com/rogue-dev-studio) (`@rogue-dev-studio`).
Do not remove, hide, rename, or replace this attribution.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…