More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AntiGravity Starter Kit — Context Optimizer & Lean Core

    1

    Eliminates context bloat, audits rule files for token bleed, and enforces the under-40-line Lean Core standard.

    $26

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AntiGravity Starter Kit — Context Optimizer & Lean Core

    AntiGravity Starter Kit — Context Optimizer & Lean Core

    Example session with this skill installed

    Audit my 450-line AGENTS.md and .cursorrules file for context bloat, identify token waste per conversation turn, and convert it to the Lean Core standard.

    • Read your context and instructions
    • Compiled the antigravity starter kit

    Rule File Token Audit

    • Original Root Rule Size: 462 lines (14,800 tokens per turn)
    • Attention Degradation Risk: 🔴 HIGH (Lost-in-the-Middle trigger detected)
    • Token Bleed Projection: ~296,000 wasted tokens over a 20-step debugging session

    Refactored Lean Core Architecture:

    1. Root AGENTS.md: Stripped down to 24 lines of universal invariants (720 tokens).
    2. Modular References (references/): 4 specialized markdown files created for on-demand loading.
    3. Subagent Router (rules/model_routing.md): Configured for automatic task delegation.
    
    # AGENTS.md — Lean Core Standard (<30 lines)
    1. Invariant: Maintain 100% test pass rate before committing code.
    2. Routing: Load specialized references on-demand using view_file.
    3. Subagents: Heavy refactoring runs in isolated subagents (context: fork).
    
    AGENTS.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    AntiGravity Starter Kit — Context Optimizer & Lean Core Rules

    Tired of your AI coding assistant forgetting earlier instructions, burning tokens at lightning speed, or drifting into hallucinations?

    The AntiGravity Starter Kit diagnoses and solves Context Bloat across Claude Code, Cursor, Windsurf, OpenClaw, Codex CLI, and Google Antigravity.

    ⚠️ The Problem: Monolithic Instructions Degrade LLMs

    When your root rule files (AGENTS.md, .cursorrules, CLAUDE.md) exceed 80–100 lines:

    1. Attention Degradation (Lost-in-the-Middle): The LLM dilutes constraints, causing the assistant to violate safety rules or repeat mistakes.
    2. First-Token Latency (TTFT) & Token Waste: Every turn re-reads the full system prompt. Over 125,000 wasted tokens in a 50-step session.
    3. Premature Context Overflow: Heavy instructions push the session into early context exhaustion.

    ⚡ The Solution: The AntiGravity 3-Tier Lean Core (<40 lines)

    • Tier 1: Lean Root Core (<40 lines): Universal behavioral invariants only.
    • Tier 2: Modular Reference Modules: Domain knowledge loaded on-demand from references/.
    • Tier 3: Isolated Subagents (context: fork): Heavy refactoring in sandboxed sub-windows.

    📦 What's Included:

    • scripts/token_inspector.py (CLI diagnostic audit)
    • assets/AGENTS.template.md (18-line production starter)
    • references/ (Architecture guides and recipes)
    • agents/openai.yaml (Codex CLI metadata)

    🔒 100% Local-First & Zero Telemetry

    Runs entirely on your local machine using your existing CLI environment. Zero data telemetry, zero cloud egress.

    Focuses on instruction optimization. Does not audit application code performance, database queries, or cloud infrastructure costs.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Required to audit local rule files and refactor rule structures into modular directories.

    Listed1 month ago
    Updated29 days ago

    What's inside

    Frequently Asked Questions

    It addresses 'context bloat'—when long instruction files cause AI agents to hallucinate, ignore constraints, or waste expensive tokens—by refactoring them into a high-performance 40-line architecture.

    The kit is compatible with any AI coding environment that uses instruction files, specifically optimized for Cursor (.cursorrules), Windsurf, Claude Code (CLAUDE.md), and the Antigravity framework.

    You receive the token_inspector.py diagnostic utility, the 3-tier modular architecture templates, and a step-by-step implementation guide to migrate your existing rules into the lean format.

    No, this skill is designed to work locally with your existing Markdown configuration files and includes a Python-based diagnostic tool that runs in your terminal or IDE environment.

    While the 40-line core is the target for maximum focus, the kit uses a modular 'Reference' system that allows you to store unlimited technical documentation without cluttering the agent's primary reasoning window.

    The kit includes a specialized handover protocol that automatically triggers state summaries once a session hits 25,000 tokens, preventing the agent from losing the thread during deep work.

    New in Prompt & Skill Engineering