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	12496
title	Batch-rollout-plan artifact from skill-baggage inventory (#11605 AC6)
state	Closed
labels	documentationenhancementaimodel-experience
assignees	neo-gpt
createdAt	Jun 4, 2026, 2:03 PM
updatedAt	Jun 4, 2026, 2:47 PM
githubUrl	https://github.com/neomjs/neo/issues/12496
author	neo-opus-ada
commentsCount	0
parentIssue	11605
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jun 4, 2026, 2:47 PM

Batch-rollout-plan artifact from skill-baggage inventory (#11605 AC6)

Closed v13.0.0/archive-v13-0-0-chunk-16 documentationenhancementaimodel-experience

neo-opus-ada commented on Jun 4, 2026, 2:03 PM

Sub of Epic #11605 (compress skill baggage → decision-atom maps). Fills the AC6 BLOCKER from @neo-gpt's epic-resolution review: the ai:skill-size-report inventory tooling exists (#11915), but no closeout-ready rollout-plan artifact converts inventory output → prioritized batch groups.

Scope

Produce a batch-rollout-plan artifact (a learn/agentos/ doc, or the #11605 epic body) that takes live ai:skill-size-report output and groups the remaining baggage-heavy skills into risk/size-ordered batches for decision-atom compression. Topology only (the plan), not the compressions themselves.

Acceptance Criteria

Rollout-plan artifact derived from live ai:skill-size-report output (not a stale static list).
Skills grouped into risk/size-ordered batches with a compression order.
Each batch maps to a future sub/PR (or notes a skill already lean — e.g. pr-review post-pilot).

Contract Ledger

Target Surface	Source of Authority	Proposed Behavior	Fallback	Docs	Evidence
batch-rollout-plan doc	#11605 AC6 + gpt resolution matrix	inventory → risk/size-ordered batch groups	—	yes	derived from `ai:skill-size-report`

tobiu referenced in commit 5bc93d0 - "docs(agentos): add skill compression rollout plan (#12496) (#12498) on Jun 4, 2026, 2:47 PM

tobiu closed this issue on Jun 4, 2026, 2:47 PM