Model Orchestrator
Splits big multi-step tasks across Haiku, Sonnet and Opus sub-agents by difficulty, so you get the same quality for less usage. Includes a Salesforce delivery layer.
$5
Works with the AI Agents you already use
About this skill
Turns your top model into the boss: it plans, routes each chunk of work to the cheapest sub-agent model that can handle it, reviews the results and escalates one tier at a time when something fails.
What's inside
- When to orchestrate at all: a cost rule that skips orchestration for small jobs, where sub-agent startup costs more than it saves.
- Routing table: Haiku for lookups and mechanical edits, Sonnet for code, tests and verification, Opus for architecture and hard debugging (Fable when available).
- Brief checklist: goal, method, sized budget, priority order, source rules and a fixed report format, so cheap models don't drift.
- Cost and cache playbook: warm-first launches, immediate top-ups, reduce-before-delegate scripting and few boss turns.
- Research playbook: breadth scan, pricing slice, and a scoped verifier for anything you'll rely on.
- Escalation ladder: fix the brief, retry, move up one tier, then hand back. No loops.
- Safety: nothing irreversible (deploys, sends, data changes) happens without your explicit yes.
Salesforce layer (the extra in this edition) Build order from objects to permissions, one deployment per org at a time, validate-only deploys with tests before shipping, Apex bulkification and governor-limit review, and no Apex written by Haiku.
Needs an agent that can spawn sub-agents on different models. Not worth using for small or single-step tasks.
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 any payment.
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 4 days ago
Requires
Permissions
No special permissions declared or detected