What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	9701
title	Implement Progressive Disclosure for Agent Skills Context Assembly
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Apr 4, 2026, 7:09 PM
updatedAt	Apr 4, 2026, 7:12 PM
githubUrl	https://github.com/neomjs/neo/issues/9701
author	tobiu
commentsCount	1
parentIssue	9672
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 4, 2026, 7:12 PM

Implement Progressive Disclosure for Agent Skills Context Assembly

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closedenhancementai

tobiu commented on Apr 4, 2026, 7:09 PM

Background

Currently, Neo.ai.context.Assembler loads the entirety of all .agent/skills/*/SKILL.md files into the system prompt unconditionally for every session. As we build massive instructional frameworks (like the 87-line unit-test guide), this causes severe context window bloat and distracts the background LLM during unrelated tasks.

Proposed Solution

Implement the Anthropic "Progressive Disclosure" strategy within ContextAssembler.loadSkillsSync():

Parse the YAML Frontmatter of each SKILL.md to extract name, description, and explicit triggers.
Inject only these lightweight triggers into the <agent_skills> block of the overarching continuous system prompt.
Remove the injection of the full SKILL.md markdown body.
Refactor .agent/workflows/unit-test.md into a self-contained .agent/skills/unit-test/ folder (where the SKILL.md acts purely as the routing trigger, and the heavy Markdown is kept in a /references/ subfolder).

Note: This will be linked as a sub-task of Epic #9672.

tobiu added the enhancement label on Apr 4, 2026, 7:09 PM

tobiu added the ai label on Apr 4, 2026, 7:09 PM

tobiu added parent issue #9672 on Apr 4, 2026, 7:09 PM

tobiu assigned to @tobiu on Apr 4, 2026, 7:09 PM

tobiu Apr 4, 2026, 7:12 PM

Progressive Disclosure logic implemented successfully. ContextAssembler now natively strips the YAML frontmatter for all .agent/skills/*/SKILL.md files instead of injecting their entire body, drastically reducing unnecessary prompting overhead. The unit-test.md file was restructured into this new pattern mapping to the /references/ sub-directory folder.

tobiu closed this issue on Apr 4, 2026, 7:12 PM

tobiu referenced in commit d7cd447 - "feat: implement progressive disclosure for agent skills (#9701)" on Apr 4, 2026, 7:12 PM

tobiu referenced in commit 6d9c97a - "test: utilize assembler.ready() lifecycle in tests (#9701)" on Apr 4, 2026, 7:14 PM