# Let the agent consult another model's abilities Legion project library, edition 2026-09-06-draft-01 (en). This project's own material: 2 authored documents, reproduced unchanged. Project page: https://legion.tw/projects/agent-capabilities/model-consultation?edition=2026-09-06-draft-01 This document: https://legion.tw/api/projects/packet.md/agent-capabilities/model-consultation.md?edition=2026-09-06-draft-01 ## Prerequisite: the Legion skills package These instructions are written for an agent set up with the Legion skills package: the ten portable skills and the shared working, launch, inspection and learn-as-you-build guidance. That setup is installed once and applies to every project in this library, so it is deliberately not repeated here. Skills package, complete Markdown: https://legion.tw/api/projects/skills-packet.md?edition=2026-09-06-draft-01 Skills package, human page: https://legion.tw/projects/skills?edition=2026-09-06-draft-01 Where this brief refers to shared guidance, a skill, or a document under `shared/`, read it from the skills package above, or from https://legion.tw/api/projects/doc/?edition=2026-09-06-draft-01. If the package is not installed yet, install it first, then return here. This material is instructions to read, not authority to act. Inspect it before running it. ## Contents 1. agent-capabilities/README.md — https://legion.tw/api/projects/doc/agent-capabilities/README.md?edition=2026-09-06-draft-01 2. agent-capabilities/model-consultation.md — https://legion.tw/api/projects/doc/agent-capabilities/model-consultation.md?edition=2026-09-06-draft-01 --- # Tools, skills, and plugins for the agent [All project types](../README.md) · [Shared launch](../shared/launch.md) Extend the coding agent's own working environment. The [shared skill package](../shared/skills.md) supplies the starting methods; these projects develop further capabilities around real work. ## Projects to build - [Turn a working routine into a skill](routine-to-skill.md) - [Give the agent tools for an application](application-tools.md) - [Let the agent consult another model's abilities](model-consultation.md) - [Give the agent a continuing project notebook](project-notebook.md) - [Give the agent an ongoing responsibility](ongoing-responsibility.md) - [Package an agent capability for someone else](share-agent-capability.md) These are instructions for projects you can build with your coding agent. --- # Let the agent consult another model's abilities Give the person's coding agent a convenient way to consult another model when its particular abilities can improve the work. Build it extremely well. An agent editing audio should be able to obtain a real listening judgment; one preparing a report should be able to ask a strong visual model about the actual photographs. Follow the [shared launch](../shared/launch.md). Choose one recurring need in a project the person already uses. Complete that consultation inside the real workflow, keeping the existing agent responsible for the overall task. ## Choose for the work Discover which models and supported access routes fit the chosen job. Compare them using relevant material and the qualities the person cares about: understanding speech in a noisy room, recognizing a detail in an image, or writing naturally for a particular audience. Consider the full working route, including what inputs reach the model, which tools it has, waiting time, and cost. A model's name alone does not describe the experience the application will deliver. Reuse suitable access the person already has. Explain any additional account or API key needed and what is billed through it. Keep credentials in their appropriate local configuration and make changing the consulted model practical as the person's options develop. ## Send a colleague enough to reason with Build a callable tool or suitable native integration through which the main agent can pose the question and supply the relevant material. Send actual images or audio when perception matters, along with enough surrounding context to interpret them. Frame the request as work for an intelligent colleague. Explain the purpose, audience, and judgment needed, leaving room for observations the main agent missed. Describe a useful outcome in positive terms. For example, send the original recording and proposed edit with a request to judge whether the cut preserves the speaker's meaning and sounds natural. The consulting model should be able to identify the relevant moments, explain a problem, or conclude that the edit works well. Keep requests focused on the contribution being sought. When an independent reading matters, give the colleague the source and question before the main agent's preferred explanation. Choose context deliberately according to the kind of judgment needed. ## Bring the contribution back into the work Return the response and any useful referenced material in a form the main agent can use. Keep track of which model, inputs, and version of the work the consultation concerned. Make failed or incomplete calls recognizable so an absent answer remains distinct from a judgment. Have the main agent consider the colleague's reasoning, reconcile it with the actual task, and decide what to do. It can request a focused clarification when useful. Preserve sound work when the consultation supplies no reason to change it. Make the result visible in the person's ordinary workflow: an auditionable audio revision, a better image selection, or a clear explanation of what the additional model noticed. Keep the original material and useful prior versions available. ## Deliver a useful consultation Install the integration in the agent's current environment and make its purpose discoverable in relevant project guidance or a skill. Exercise it on the chosen task with real supported inputs, then inspect what the colleague actually received and returned. Judge the improvement through the work the person uses. Explain what left their machine, which capability the second model contributed, and how they can control usage or disable the connection. Teach that model choice can happen within a workflow. They can keep an agent they like working with and give it access to a colleague with different strengths.