model-router

model-router is a skill for Claude Code from AiAi-Mastermind/aiai-mastermind-tools-and-skills. It costs 33 tokens per session (765 once invoked), scanned A, original, MIT.

A guide for running Claude Code sessions, one-off workers, and subagents through a local proxy that routes work to different models.

In plain words
What is it for?
Use it to configure the proxy, select a worker model, run one task, or delegate work from an orchestrating session.
Why use it?
It explains the model choices, settings, and command forms needed to use routed models without changing the main session's login.

Skill for Claude Code

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

Part of the model-router plugin — 3 skills, 3 commands, 1 agent shipped together

Good fit Use it to configure the proxy, select a worker model, run one task, or delegate work from an orchestrating session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router
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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill model-router
Clone the repo
git clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-skills

Made for: Claude Code.

Or install model-router, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 agent.

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 model-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router/github.svg)](https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router)
Your own site
<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-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.

agentmods 80×15 button for model-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/model-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 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.
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 $0.00033 $0.00765
Opus 5 $0.00016 $0.00382
Sonnet 5 $0.00007 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 12d ago against content hash 5e93ebb9815b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

model-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 12d 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 -s "${MODEL_ROUTER_URL:-http://127.0.0.1:8317}/v1/models" \
skills/model-router/skills/model-router/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Router - routing knowledge

This skill teaches the three ways to run work on a routed model (any model your proxy serves), and how to switch models. The proxy is CLIProxyAPI running locally; it holds the user's OTHER subscription logins (ChatGPT/Codex, Gemini, Grok, Kimi). The main Claude session always stays on its normal direct login.

Configuration (shared by everything in this plugin)

Env var Default Meaning
MODEL_ROUTER_URL http://127.0.0.1:8317 proxy address
MODEL_ROUTER_KEY my-proxy-key an api-keys entry from the proxy's config.yaml
MODEL_ROUTER_MODEL gpt-5.6-sol default routed model
MODEL_ROUTER_EFFORT low default worker effort

Mode 1 - orchestrator + worker (the flagship): /fabsol <brief>

Your main model plans and verifies; the routed model does 100% of the building via headless calls. Cheapest way to ship real builds - see the fabsol command.

Mode 2 - one-shot worker run (any model, one task)

ANTHROPIC_BASE_URL="${MODEL_ROUTER_URL:-http://127.0.0.1:8317}" \
ANTHROPIC_AUTH_TOKEN="${MODEL_ROUTER_KEY:-my-proxy-key}" \
claude -p "the task" \
  --model "${MODEL_ROUTER_MODEL:-gpt-5.6-sol}" \
  --effort "${MODEL_ROUTER_EFFORT:-low}" \
  --bare --max-turns 20 --permission-mode acceptEdits

Or use the wrapper: scripts/worker.sh "the task" [model] [effort] (scripts/worker.ps1 on Windows).

Mode 3 - full session on a routed model (terminal or VSCode)

scripts/session.sh [model] (or session.ps1) launches a whole Claude Code terminal session on the routed model. scripts/vscode.sh [folder] (or vscode.ps1) does the same for a VSCode window - it uses a separate VSCode profile dir because an already-running VSCode ignores new env vars. In such a session, the plugin's worker subagent also resolves, so subagents can run on routed models too.

Switching models

Any ID the proxy serves works everywhere a model is named. Discover what your proxy serves:

Read the full file on GitHub · 70 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. 12d ago First seen · 70 lines · 33 tokens per session scan A 5e93ebb9815b

Subscribe to this mod's changes

model-router is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 765 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

wiki-ingest

Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…

AgriciDaniel/claude-obsidian · 88 tokens

autoresearch

Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…

AgriciDaniel/claude-obsidian · 80 tokens

canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

AgriciDaniel/claude-obsidian · 72 tokens

defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

AgriciDaniel/claude-obsidian · 57 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

AgriciDaniel/claude-obsidian · 68 tokens