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 generate a shareable Developer Card via the CLI
command `maverick card` — a visual summary of your behavioral profile.
extensions:
- type: stdio
name: maverick
cmd: uvx
args:
- maverick-mcp
- serve
Comment on lines +22 to +25

Choose a reason for hiding this comment

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

P1 Badge Invoke the package's maverick entrypoint via uvx --from

This extension command will not start on a clean machine. uv help tool run says the package is assumed to match the command name unless you pass --from, and upstream maverick-mcp only registers maverick in [project.scripts] (its pyproject.toml does not expose a maverick-mcp executable). As written, uvx maverick-mcp serve asks uv to run a nonexistent entrypoint, so the MCP server never comes up and none of the recipe's tools are available.

Useful? React with 👍 / 👎.

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 via CLI (`maverick card`)
- 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__maverick_profile. If no profile exists, offer to run a quick 2-minute
assessment by calling maverick__maverick_assess (no arguments to get the
questions, then call again with the answers to score).

Once a profile is detected, call maverick__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)

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

To generate a Developer Card, the user can run `maverick card` in their
terminal — this is a CLI command, not an MCP tool.
Comment on lines +53 to +54

Choose a reason for hiding this comment

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

P1 Badge Remove or correct the nonexistent maverick card command

The upstream CLI does not have a card subcommand. I checked src/maverick_mcp/cli.py, and main() only wires up serve, assess, profile, and reset, so every user who follows this Developer Card instruction will get argparse's usage error instead of generating anything. If the card flow lives somewhere else now, the recipe should point to that actual invocation.

Useful? React with 👍 / 👎.


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