- Home
- Skills
- Agents & Orchestration
- Delegate AI Subtasks
Delegate AI Subtasks
Stop burning expensive model tokens on repetitive subtasks. This skill delegates mechanical work to cheaper models and writes handoff snapshots so you never lose context switching between sessions.
$5
Works with the AI Agents you already use
Delegate AI Subtasks
Example session with this skill installed
We need to build these 12 CSS modules and then I want to switch to a cheaper model to save on costs. Can you handle the boilerplate and prep a handoff?
- Read your context and instructions
- Compiled the delegate ai subtasks
I've delegated the creation of 12 boilerplate CSS modules to a Haiku sub-agent. Meanwhile, I've generated HANDOFF.md with our architectural decisions regarding the React context provider. You can now switch to a cheaper model; just tell it to "Read HANDOFF.md and continue."
Connects securely to your tools. The creator never sees your data.
About this skill
When you give your agent a complex task, it does everything with the same expensive model. Reformatting 10 files? Opus. Generating boilerplate from a spec? Opus. Running a script and checking output? Still Opus. Meanwhile, most of those subtasks could be handled by Haiku at a fraction of the cost. Smart Router does two things. First, it automatically identifies which parts of a task are mechanical or repetitive and delegates them to a cheaper model. Creating a batch of similar files, converting formats, running validation checks, generating boilerplate. The skill writes fully self contained prompts so the subagent has everything it needs without any conversation context. Your main model focuses on the work that actually requires judgment: architecture, debugging, the final user facing deliverable. Second, it handles context handoffs when you switch models or start a new session. It writes a structured HANDOFF.md snapshot that captures not just what was done, but why. Key decisions and their rationale, rejected approaches and why they didn't work, specific next steps, and any user preferences that came up in conversation. The next model reads that file and picks up exactly where you left off without asking you to repeat yourself. You can use either feature independently or both together. On a big task, you might delegate boilerplate to Haiku, do the complex work yourself, and then write a handoff when the user wants to continue later with a different model. Works with Claude Code, Cursor, Codex CLI, VS Code Copilot, and any agent that supports the SKILL.md standard.
- Subagents lack conversation history; requires perfectly self-contained prompts. - Overhead of spawning subagents can exceed benefits for tiny 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
This skill has been used 4 times.
Trust & safety
Security scan
Security scan passed 7 months ago
Permissions
No special permissions declared or detected