- Home
- Skills
- Agents & Orchestration
- Model Router Beginner: Right Model for Every Task
Works with the AI Agents you already use
Model Router Beginner: Right Model for Every Task
Teaches your AI agent which model and effort to use for each task, so planning, building, reading and review each get the right tier and you stop wasting tokens.
$8.99
Model Router Beginner: Right Model for Every Task
Example session with this skill installed
I just downloaded the model-router-beginner skill into ./skills/model-router-beginner. Read its SKILL.md and follow it.
My setup: I use Claude Code as my only AI tool, with Claude Opus, Sonnet and Haiku available, on a Claude Max subscription.
Do the first-run setup for this project now (write the filled files into this project as the skill says), then show me how you would route this task: "add a password reset flow to our Express API, with email tokens and rate limiting".
End with a short summary of what you set up and the routing decision.
- Read your context and instructions
- Compiled the model router beginner
(Real run, 2026-10-03: Codex CLI as the agent, the beginner pack unzipped into a fresh Express project. Final reply, unedited apart from local file links. The run prompt also told the agent to ignore unrelated instructions on the test machine.)
Wrote the filled rules, briefs and protocols into ai-orchestrator/, plus the CLAUDE.md loading entry.
- Checks: four automated checks passed. Fresh-session instruction loading remains UNVERIFIED.
- Opus: plan reset-token security, expiry, single-use handling, email integration and rate-limit policy.
- Sonnet: implement the scoped Express changes and positive/negative tests, using high effort where supported.
- Haiku: optional bounded file inventory or test-output formatting.
Review: fresh-context Opus can self-check. All three models share the Claude family, so the skill’s required independent audit remains pending before release.
Summary: Set up project-local Claude Code routing for Claude Max. Password reset routes through Opus planning, Sonnet implementation and Opus self-check; no API code was changed.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem: most AI agents use one model at one effort for everything. Simple lookups burn your strongest model, hard architecture calls get a quick pass, and nobody checks the work before it ships.
What you get: a routing method your agent follows inside the tool you already use. It sorts every task into planning, working or cheap-model work, picks the effort to match, and builds from written checks so "done" means proven.
What your agent learns
- Three model tiers: a planning model for ambiguous decisions and architecture, a working model for scoped builds and review, a cheap model for bulk reading and formatting.
- Task classification: a decision tree covering bulk work, reading many files, live data, review, verification, planning and builds.
- Build from checks: quote the request, freeze acceptance checks, probe what tools exist, and collect one shared context file before work starts.
- Task briefs: a template that hands any worker the scope, files, non-goals, checks and what it has and lacks.
- One honest review: an independent review by a different model family when you have one, and a recorded limitation when you do not.
- 10 protocols: building, context files, acceptance checks, decision logs, renames, gap analysis, research, calculation, notes and documentation checks.
How setup works
On first run your agent asks which AI tools and models you have, copies the rules into your project, and fills in its own routing table from what it can verify. No installer, no account, no config to edit by hand.
Works inside one agent: Claude Code, Codex, Cursor, Gemini CLI or any agent that reads SKILL.md. When you add a second AI tool, the Intermediate pack adds delegation across them.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Routes inside one agent; delegation across several AI tools is in the Intermediate pack. Your agent needs permission to read and write files in your project. Models, quotas and effort settings the agent cannot see are confirmed with you or marked UNVERIFIED. An independent review needs a model from a different family; with one family, the agent records a self-check.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
Writes the filled routing files into a folder in your project (default ai-orchestrator/).