What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

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

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	9702
title	Implement Neural Link Tactical Skill (Tool Chaining)
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Apr 4, 2026, 7:23 PM
updatedAt	Apr 4, 2026, 7:27 PM
githubUrl	https://github.com/neomjs/neo/issues/9702
author	tobiu
commentsCount	1
parentIssue	9672
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Apr 4, 2026, 7:27 PM

Implement Neural Link Tactical Skill (Tool Chaining)

Closed v13.0.0/archive-v13-0-0-chunk-2 enhancementai

tobiu commented on Apr 4, 2026, 7:23 PM

Background

The neural-link MCP Server exposes 33 raw tools for querying and mutating a running Neo.mjs application. However, without a structured skill, autonomous agents lack the tactical grammar (tool chaining sequences) needed to effectively debug applications, leading to hallucinated component IDs or unsafe hot-patching.

Goal

Implement a progressive disclosure skill for the Neural Link that teaches agents the explicit strategies necessary to master the UI bridging toolkit.

Implementation Steps

Create .agent/skills/neural-link/SKILL.md to establish the behavioral trigger using YAML Frontmatter.
Create .agent/skills/neural-link/references/operational-handbook.md as the underlying playbook payload.
Formulate tactical sequences within the handbook, such as:
- Discovery Chains: Always query IDs before invoking tree inspection.
- Data Chains: Finding Stores before checking records.
- Safe Patching Protocols: Mandating source verification (get_method_source) before applying runtime code patches.

Note: This will be connected to Epic #9672 (Workflow Enablement).

tobiu Apr 4, 2026, 7:27 PM

Neural Link progressive disclosure skill implemented successfully. Replaced explicit tool-guessing with robust Tool Chaining sequences inside the new operational-handbook.md. Also incorporated specific lifecycle recovery rules regarding Session ID invalidation during target app reloads.