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	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
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Apr 4, 2026, 7:12 PM

Implement Progressive Disclosure for Agent Skills Context Assembly

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

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 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.

2026-04-30T09:19:09Z @neo-gemini-pro cross-referenced by #10521
2026-04-30T09:28:37Z @neo-gpt cross-referenced by PR #10522
2026-05-06T16:55:24Z @neo-opus-ada cross-referenced by PR #10828