---
type: "post"
id: "openclaw-released-v2026-10-1-with-installed-skill-424ac5"
slug: "openclaw-released-v2026-10-1-with-installed-skill-424ac5"
title: "OpenClaw released v2026.10.1 with installed-skill discovery, MCP Apps alongside conversations"
description: "OpenClaw v2026.10.1 moves installed-skill discovery out of the prompt’s static skill list and into a permission-aware search-and-read path."
retrieval_nugget: "OpenClaw v2026.10.1 moves installed-skill discovery out of the prompt’s static skill list and into a permission-aware search-and-read path."
published_at: "2026-10-11"
updated_at: "2026-10-11"
record_date: "2026-10-11"
date_kind: "published_at"
topics: ["mcp"]
source_urls: ["https://docs.openclaw.ai/releases/2026.10.1"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:openclaw-released-v2026-10-1-with-installed-skill-424ac5"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:70c18e2145c57a238cd99c3cd6288f276369c085be519a59549adbaec87f5404","reviewed_at":"2026-10-11T20:03:32.407Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":3,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"A capable agent workflow can discover relevant instructions without loading every installed skill into context, while keeping discovery distinct from permission to act.","observed_facts":[{"text":"OpenClaw v2026.10.1 adds installed-skill search returning matching names and descriptions, followed by a separate exact-name read of instructions.","source_urls":["https://docs.openclaw.ai/releases/2026.10.1"]},{"text":"The release says skill search follows the agent's current read permission and that reading a skill does not grant permission to install or run it.","source_urls":["https://docs.openclaw.ai/releases/2026.10.1"]},{"text":"The release adds MCP Apps beside chat with visible approval controls for app messages and workspace-file operations.","source_urls":["https://docs.openclaw.ai/releases/2026.10.1"]},{"text":"Full backups can be stored on external storage or Cloudflare R2 and restored into a fresh staging directory.","source_urls":["https://docs.openclaw.ai/releases/2026.10.1"]}],"mechanism":"Permission-aware search locates candidate installed skills, with a separate read step for full instructions; execution authorization remains distinct.","why_now":"The release says eligible installed skills remain discoverable when prompt-size limits leave them out of the skill list.","implications":["Teams can avoid loading a complete skill library into every prompt while retaining a discovery path.","Skill discovery must remain distinct from authorization to install or execute a skill.","MCP App interactions and file operations gain visible approval controls."],"evidence_boundary":"These are documented product changes, not evidence of adoption, reliability in production, or measured context savings. The notes also caution that instruction search can be partial: for some long files, only a prefix is covered, so a missing match does not prove that no suitable skill exists.","watch_conditions":["Whether later releases document wider instruction-search coverage or evidence of teams using discovery while preserving execution permission boundaries."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied; this release adds a distinct permission-aware discovery mechanism alongside app approvals and backup changes."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/openclaw-released-v2026-10-1-with-installed-skill-424ac5/","markdown":"https://newruntime.com/posts/openclaw-released-v2026-10-1-with-installed-skill-424ac5.md","json":"https://newruntime.com/posts/openclaw-released-v2026-10-1-with-installed-skill-424ac5.json"}
---

# OpenClaw released v2026.10.1 with installed-skill discovery, MCP Apps alongside conversations

## Retrieval answer

OpenClaw v2026.10.1 moves installed-skill discovery out of the prompt’s static skill list and into a permission-aware search-and-read path.

OpenClaw v2026.10.1 moves installed-skill discovery out of the prompt’s static skill list and into a permission-aware search-and-read path. A capable agent workflow can discover relevant instructions without loading every installed skill into context, while keeping discovery distinct from permission to act. The release says search follows the agent’s current read permission; reading a selected skill does not grant permission to install or run it. Permission-aware search locates candidate installed skills, with a separate read step for full instructions; execution authorization remains distinct.

The release says eligible installed skills remain discoverable when prompt-size limits leave them out of the skill list. Teams can avoid loading a complete skill library into every prompt while retaining a discovery path. The release also adds MCP Apps beside chat: compatible apps can expose forms and workspace files, with visible approval controls for messages and file opens. Backups may now be stored on external storage or Cloudflare R2 and restored into a fresh staging directory.

These are documented product changes, not evidence of adoption, reliability in production, or measured context savings. The notes also caution that instruction search can be partial: for some long files, only a prefix is covered, so a missing match does not prove that no suitable skill exists. Whether later releases document wider instruction-search coverage or evidence of teams using discovery while preserving execution permission boundaries.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)