masalaloe/antigravity-customization-system/agy-customizations

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Comprehensive guide and reference for the Antigravity Customization System. Use to explain how customizations work, their loading priority, discovery mechanisms, and to guide the creation of skills, rules, plugins, hooks, and MCP servers.

Install

npx vskill@latest install masalaloe/antigravity-customization-system/agy-customizations

SKILL.md

The same SKILL.md was published earlier as jeffna1/antigravity-voxel-godot-setup/agy-customizations.

Antigravity Customization System Guide

The Antigravity Customization System allows you to tailor the agent's behavior, teach it new workflows, enforce guidelines, and integrate it with external tools. By customizing the agent, you can transition it from a general-purpose assistant to an expert pair programmer specialized in your project's codebase and processes.


Customization Types: Quick Reference

Choose the right customization type based on your goal:

Type | Config File/Folder | Scope | Best For | Learn More :-------------- | :--------------------------- | :------------------------ | :-------------------------------------------------------------------------------------- | :--------- Rules | GEMINI.md, AGENTS.md | Contextual / Hierarchical | Enforcing coding styles, API restrictions, and local guidelines. | Rules Guide Skills | skills/<name>/SKILL.md | On-Demand (Progressive) | Teaching the agent multi-step procedures, runbooks, and tool workflows. | Skills Guide Plugins | plugins/<name>/plugin.json | Bundle | Packaging related skills, rules, and MCP configs into a single unit. | Plugins Guide Hooks | hooks.json | Lifecycle Event | Running scripts/commands at specific agent lifecycle points (e.g., pre-tool execution). | Hooks Guide MCP Servers | mcp_config.json | Tool Integration | Connecting the agent to external services and custom tool providers. | MCP Guide


Customization Discovery and Locations

Antigravity automatically discovers your own customizations by traversing specific directories. Built-in customizations are not found this way: the agent config names the ones it mounts.

Discovery Locations
  1. Workspace Customizations (Project-Specific):
  • Path: .agents/ (or .agent/, _agents/, _agent/) at the root of

your project.

  • Use this to share customizations with your team by checking them into

version control (VCS).

  • The agent walks from your current working directory up to the repository

root (e.g., the folder containing .git) to find these directories.

  1. Directory & Project Rules (Hierarchical):
  • Paths: GEMINI.md, AGENTS.md, .agents/rules/*.md
  • As you open or edit files, the agent walks up from the file's directory

to the repository root, loading all rules it finds.

  1. Global Configuration (Machine-Local):
  • Path: ~/.gemini/config/
  • Applies to all projects and workspaces run on your machine.

Loading Priority and Precedence

When multiple customizations are discovered, they are loaded and applied in a specific order. If there are naming conflicts (e.g., two skills with the same name), the higher-priority customization overrides the lower-priority one.

The priority order (from highest to lowest) is:

  1. Workspace Project: Hierarchical discovery walking up from the CWD to the

repository root.

  1. Declared Configurations: Customizations explicitly listed in

skills.json or plugins.json in your workspace.

  1. Global Discovery: ~/.gemini/config/
  2. Built-in Customizations: Default skills bundled with the application,

mounted by name rather than discovered.

  1. Global Declared Configurations: Explicitly listed in global JSON

configs.


How Customizations are Applied

Progressive Disclosure (Skills and Rules)

To prevent overwhelming the model's context window, Antigravity uses progressive disclosure:

  • Skills are not loaded into the context window by default. Only their

names and descriptions are injected. The full content of a skill is only loaded if the model (or the user) explicitly decides to activate it.

  • Rules with trigger: model_decision behave similarly. Only always_on

rules are loaded unconditionally.

Deduplication

All customizations (especially rules) are deduplicated by their resolved file paths. A rule file will never be injected more than once in a single conversation turn, even if it matches multiple trigger conditions.


Advanced Management: JSON Configs

For customizations stored in non-standard locations, you can use skills.json and plugins.json to explicitly register them and inherit from shared configurations.

  • Learn how to configure these in the

JSON Configurations Guide.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/masalaloe/antigravity-customization-system/agy-customizations/badge)](https://verified-skill.com/skills/masalaloe/antigravity-customization-system/agy-customizations)

Something wrong with this skill or its page? Tell us.