A service and skill for routing requests to many AI language models through one OpenAI-compatible API and API key.

It is for model switching, comparing responses, image analysis, choosing models by cost or task, and setting fallback routes when a model fails.

It avoids managing separate provider connections when switching between models such as GPT, Claude, Gemini, Qwen, DeepSeek, or Grok.

llm-router — Skill for Claude Code and Codex by AIsa-team/agent-skills

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 AIsa-team/agent-skills --skill llm-router

Clone the repo

git clone --depth 1 https://github.com/AIsa-team/agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aisa-team/agent-skills/llm-router/github.svg)](https://agentmods.dev/skills/aisa-team/agent-skills/llm-router)

Your own site

<a href="https://agentmods.dev/skills/aisa-team/agent-skills/llm-router"><img src="https://agentmods.dev/badge/skills/aisa-team/agent-skills/llm-router/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/aisa-team/agent-skills/llm-router"><img src="https://agentmods.dev/badge/skills/aisa-team/agent-skills/llm-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,083 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: 10 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 Data Exfiltration · line 88
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.
medium Data Exfiltration · line 94
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.
medium Data Exfiltration · line 161
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.
medium Data Exfiltration · line 185
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.
medium Data Exfiltration · line 207
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.
medium Data Exfiltration · line 236
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.
medium Data Exfiltration · line 240
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.
medium Data Exfiltration · line 444
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.
medium Data Exfiltration · line 94
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.
medium Data Exfiltration · line 161
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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.05083
Opus 5.5	$0.00024	$0.02033
Sonnet 5.5	$0.00012	$0.01017
Haiku 4.5	$0.00006	$0.00508

Measured 18d ago against content hash b10dbd30d474, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-router 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 18d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/llm_router_client.py), 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.

Makes network callslowCapability

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

compatibility: Designed for Agent Skills compatible clients such as OpenClaw, Claude Code, Hermes, and GitHub-backed skill catalogs. Requires system binaries curl, python3, environment variables AISA_API_KEY and internet

ai-models/llm-router/SKILL.md · 528 lines

How it starts

The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIsa LLM Router 🧠

AIsa agent rules (shared)

These rules apply to every AIsa-backed skill and are copied from https://aisa.one/llms.txt, the single authoritative agent rule source. When this block and the rest of this skill disagree, follow this block.

Connect (MCP first)

Pick the first option that applies. Run the command yourself; the user only approves the browser sign-in.

A. Your client supports remote MCP and can open a browser (default). Add a remote MCP server named AIsa with URL https://mcp.aisa.one/mcp (Streamable HTTP), using your client's own command or config file. Auth: browser OAuth, no key needed. In a chat app (Claude, ChatGPT), the user adds it as a custom connector in settings. Adding the server does not always start sign-in. If no sign-in window opens, start it from the client's own MCP authentication entry (a menu, command, or connector button); if only the user can reach that entry, tell them where it is. Sign-in is the slow step, not the API. Before it starts, tell the user in one line that an AIsa sign-in window or card is about to open and to click Allow (one click if the browser is already signed in to AIsa). Do not call step 2 until the user says sign-in is done or the AIsa tools appear; calling it earlier only returns 401, so do not retry in a loop. If the client must restart to load the server, tell the user and wait. If you cannot add the connector yourself (sandbox, permission denied), give the user the server name and URL above and wait. Do not fall back to another method.
B. Your client supports remote MCP but has no browser (CI, SSH, container). Same endpoint, with the header Authorization: Bearer $AISA_API_KEY set in your client's MCP config instead of browser sign-in. If AISA_API_KEY is not set, ask the user to create a key at https://console.aisa.one/api-keys and set it in the environment; never ask them to paste it into chat. Never print, log, or commit the key.
C. The client has no MCP support. Use the CLI: npm install -g @aisa-one/cli && aisa login (Node.js 18+). Guide: https://aisa.one/docs/get-started/cli.md
D. Calling AIsa over HTTP from your own code. LLMs, OpenAI-compatible: https://api.aisa.one/v1 (Gemini GenerateContent: https://api.aisa.one/v1beta). Data APIs: https://api.aisa.one/apis/v1. Auth: Authorization: Bearer $AISA_API_KEY. Exact paths and schemas: https://aisa.one/docs/api-reference

Read the full file on GitHub · 528 lines

Files

What ships with it

4 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.

18d ago Changed · +49 lines b10dbd30d474
25d ago Changed · +1 lines 06d637c3e06f
2mo ago First seen · 478 lines · 61 tokens per session scan A 232e4a32afb1

Subscribe to this mod's changes

llm-router is a skill published in the GitHub repository AIsa-team/agent-skills (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 5,083 once invoked, about $0.0002 per session on Opus 5.5. 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.

Backend and APIs Data and AI

llm-router next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-routerAIsa-team/agent-skills	Skill	28	yesterday	Apache-2.0	A	61	Claude Code, Codex
gemini-api-agent-platformdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	61	Claude Code, Codex
open-sourcebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	137	Claude Code
prowler-mcpprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	67	Claude Code
gemini-api-devgoogle-gemini/gemini-skills	Skill	4.4k	yesterday	Apache-2.0	A	85	Claude Code
deepstream-sopNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	219	Claude Code
azure-search-documents-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	102	Claude Code

llm-router