Build Smarter Bundle: Model Router Beginner + Website Build
Two skill packs that work together for anyone building with one AI agent.
Model Router Beginner teaches your agent which model and reasoning effort fits each task, so planning, building, reading and review each go to the right model and you spend fewer tokens.
Website Build Skill teaches it current website-building expertise: research, design, code, accessibility, performance, search and security.
Together, your agent plans a site with the right model for each step, then builds it through a staged workflow, from three visual mockups to a release-ready audit. Both are SKILL.md packs your agent reads directly, with no installer needed.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 2 skills unlock instantly in your library.
What's included
2 skillsTeaches 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.
Turns your AI into an expert website builder: current research, design, code, accessibility, speed, SEO and security, alone or as a team.
See it in action
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.
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 these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
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.