skills.rest
ax128
ax128COMMUNITY
Explore all skills by this author →
GitHub

AegisGate Agent Skill

Deploy AegisGate via Docker or local bootstrap and configure token routing.

56|7|Updated Feb 25, 2026
Search Tags:#api-gateway#prompt-injection#client-integration#pii-redaction#llm-security#token-routing#docker-deployment
One-click install
npx skills add https://github.com/ax128/AegisGate --skill aegisgate-agent-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AegisGate Agent Skill
Source: https://github.com/ax128/AegisGate/tree/main
Command: npx skills add https://github.com/ax128/AegisGate --skill aegisgate-agent-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you install, start, and safely integrate AegisGate on a new machine so your AI applications can route through a security gateway instead of sending raw prompts/responses directly to upstream LLM providers.

Core Features & Use Cases

  • Install & boot AegisGate with Docker or run it locally from source, then validate via health/readiness endpoints.
  • Choose the correct routing mode (token routing recommended for multi-tenant use, or direct upstream mode for trusted local/agent setups).
  • Register and manage gateway tokens so clients can use stable OpenAI-compatible endpoints while ensuring sensitive data handling and policy enforcement.
  • Connect AI clients/agents by configuring baseUrl and upstream API keys (including common workflows for OpenAI-compatible, Anthropic Messages, and v2 proxy access patterns).
  • Troubleshoot failures with a clear verification order (health → routing mode → token lookup/config → logs).

Quick Start

Ask the agent to install AegisGate with Docker, start it locally, register a token for your upstream (including any whitelist fields you need), and then provide a ready-to-use baseUrl and client config for your LLM toolchain.

Frequently Asked Questions about AegisGate Agent Skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy an LLM API gateway with Docker for secure prompt routing?▼

To deploy an LLM API gateway with Docker, install dependencies, start AegisGate, and validate health endpoints to route prompts securely. You then configure token routing or direct upstream mode to manage OpenAI-compatible API calls.

What is token routing in an API gateway and when should I use it for LLM calls?▼

Token routing in an API gateway assigns specific gateway tokens to clients for multi-tenant LLM access. You should use token routing for multi-tenant environments, while direct upstream mode suits trusted local agent setups.

How do I configure AI clients to use an OpenAI-compatible proxy endpoint?▼

To configure AI clients for an OpenAI-compatible proxy endpoint, register a gateway token and set the client baseUrl to the gateway address. You then supply the upstream API key and gateway token in your toolchain configuration.

Can I route Anthropic Messages API requests through an OpenAI-compatible gateway?▼

Yes, you can route Anthropic Messages API requests through the gateway using v2 proxy access patterns. The gateway translates these requests while maintaining OpenAI-compatible endpoints for your connected clients.

Why is my API gateway returning errors when connecting AI agents to upstream LLM providers?▼

If your API gateway returns errors when connecting to upstream LLM providers, verify health endpoints, check routing mode, validate token lookup configurations, and inspect logs. This troubleshooting order isolates routing and token failures.

Does an LLM security gateway support PII redaction and prompt injection protection?▼

Yes, an LLM security gateway supports PII redaction and prompt injection protection by enforcing security policies on requests. The gateway intercepts raw prompts and responses before they reach upstream providers to ensure sensitive data handling.

Related Skills

Explore More Software Engineering Skills→
JetXu-LLMJetXu-LLM
135

workspace-bootstrap

Your one-stop shop for news, sports, and weather in one place.

Community
Advanced
axell2017axell2017

AegisGate Agent Skill

Deploy AegisGate with Docker, configure token routing, and generate client baseUrl formats.

Community
Advanced
ricardorochericardoroche
2

ai-security

Detect prompt injection attempts in AI and LLM applications.

Community
Intermediate
BagelHoleBagelHole
46

llm-gateway

Deploy a unified API gateway for LLM traffic with load balancing and rate limiting.

Community
Advanced