# Agent Skills Layer

# Agent Skills Layer 

NEW IN 2026

Skills are an emerging complement to MCP tools: composed, reusable capability bundles (instructions + optional scripts/resources) that an agent loads on demand, rather than a live tool connection. The MCP roadmap lists a formal Skills primitive as an active 2026 work item, alongside the existing ext-auth and ext-apps extension tracks.

Practical distinction for architecture decisions:

● MCP tools — for live, stateful, or side-effecting connections to external systems (databases, APIs, SaaS products).

● Skills — for packaged, mostly-static know-how (a house style guide, a document-formatting procedure, a domain checklist) that doesn't need a network connection to a server.

● Both should be routed through the same permissioning and audit layer as everything else in the harness — a Skill is still executable content and should be treated as untrusted input until vetted.

#  Safety Classification for Tools

<div align="left" dir="ltr" id="bkmrk-levels-skills-contro"><table><colgroup><col width="206"></col><col width="209"></col><col width="208"></col></colgroup><tbody><tr><td>### Levels

</td><td>### Skills

</td><td>### Controls

</td></tr><tr><td>Low

</td><td>Informational

</td><td>Auto execute + log

</td></tr><tr><td>Medium

</td><td>Controlled side effects

</td><td>Policy checks + confidence threshold

</td></tr><tr><td>High

</td><td>Financial / irreversible / legal

</td><td>Verifier + human approval

</td></tr></tbody></table>

</div>## Mandatory Rules

High-risk actions require:

● Human approval

● Full audit trail

● Secondary verification

● Explicit user identity