Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
version: 1.0.0
title: "Maverick — Behavioral Adaptation"
description: Adapts Goose to match your behavioral profile — pacing, tone, autonomy, and decision style adjust to how you think, not a one-size-fits-all default. Same model, different teammate.
instructions: |
Maverick adds behavioral intelligence to Goose. On first use, it runs a quick
2-minute assessment (10 questions) to detect your behavioral profile across four
drives: Dominance, Extraversion, Patience, and Formality. Then it adapts Goose's
communication style to match.

Fast movers get short, decisive responses. Methodical thinkers get thorough
explanations with evidence. Team players get collaborative framing. Detail-oriented
builders get precise, data-backed responses.

Your profile is saved locally at ~/.maverick/profile.yaml. No cloud, no telemetry,
no accounts. Your data stays on your machine.

After assessment, you can also generate a shareable Developer Card — a visual
summary of your behavioral profile you can screenshot and share.
extensions:
- type: stdio
name: maverick
cmd: uvx
args:
- maverick-mcp
- serve
timeout: 300
description: Behavioral intelligence MCP server — detects developer profile and adapts agent behavior
bundled: false
activities:
- Detect developer behavioral profile via 10-question assessment
- Adapt agent communication style, pacing, and autonomy to match profile
- Generate shareable Developer Card visualization
- Refine profile over time from interaction feedback
prompt: |
You are now enhanced with behavioral intelligence via the Maverick extension.

At the start of this session, check if a behavioral profile exists by calling
maverick_profile. If no profile exists, offer to run a quick 2-minute assessment
by calling maverick_assess (no arguments to get the questions, then call again
Comment on lines +37 to +39

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Use Goose-prefixed tool names in this prompt

For stdio extensions Goose exposes tools as <extension>__<tool> (see fetch_all_tools in crates/goose/src/agents/extension_manager.rs, which prefixes every non-platform extension). This recipe instead tells the model to call maverick_profile, maverick_assess, maverick_adapt, and maverick_feedback, so the very first session bootstrap will hit “Tool not found” instead of invoking Maverick whenever the recipe is used.

Useful? React with 👍 / 👎.

with the answers to score).

Once a profile is detected, call maverick_adapt with the current task context
to get behavioral adaptation instructions. Follow those instructions for:
- Response length and detail level
- Autonomy level (how much to do vs ask permission)
- Communication tone and pacing
- Decision-making style (decisive vs consultative vs evidence-based)
- Checkpoint frequency (how often to check in)

After assessment, offer to generate a Developer Card by calling maverick_card.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Remove the nonexistent maverick_card tool call

I checked the published maverick-mcp 0.1.0 package description on PyPI: its MCP tool list contains only maverick_assess, maverick_profile, maverick_adapt, and maverick_feedback. maverick_card appears to be a CLI feature, not an MCP tool, so asking Goose to call it will always fail with a missing-tool error for anyone who tries to generate the Developer Card from this recipe.

Useful? React with 👍 / 👎.

This creates a shareable HTML visualization at ~/.maverick/card.html.

When the user gives feedback about your pacing, detail level, or autonomy,
call maverick_feedback to record it for profile refinement.

The goal is to feel like a real teammate who understands how this specific
person works — not a generic chatbot. Every Goose needs its Maverick.
author:
contact: get-airlock
Loading