skills.rest
mvschwarz
mvschwarzCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

mental-model-ha

Preserve and restore a pod's shared mental model across compaction events and restarts.

60|9|Updated Apr 1, 2026
Search Tags:#multi-agent#compaction#librarian#high-availability#session-logs#mental-model#restore-protocol
One-click install
npx skills add https://github.com/mvschwarz/openrig --skill mental-model-ha
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mental-model-ha
Source: https://github.com/mvschwarz/openrig/tree/main/packages/daemon/specs/agents/shared/skills/mental-model-ha
Command: npx skills add https://github.com/mvschwarz/openrig --skill mental-model-ha

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Preserves and restores a pod's shared mental model across compaction events and session restarts, ensuring continuity of multi-agent work across the lifecycle of a rig.

Core Features & Use Cases

  • The filesystem serves as durable memory, externalizing scope knowledge, session logs, and restore artifacts to survive compaction and restart.
  • The filesystem is multiplayer: scope folders are readable and writable by every agent, enabling cross-agent restoration.
  • One place for everything: artifacts are centralized to support consistent restoration, governance, and reasoning across pods and roles.
  • Phased Restore Protocol guides post-compaction recovery, validation, and dialogue-based synchronization between peers.
  • Continuous state maintenance: regular updates to scope-knowledge, session logs, and restore artifacts to keep memory fresh.

Quick Start

Boot a demo rig and review the pod session logs to begin practicing continuous mental-model maintenance.

Frequently Asked Questions about mental-model-ha

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I preserve multi-agent mental models across compaction events?▼

You preserve multi-agent mental models by externalizing scope knowledge and session logs to the filesystem, ensuring durable continuity across compaction events and restarts.

How does a phased peer restore protocol work for multi-pod topologies?▼

A phased peer restore protocol guides post-compaction recovery, validation, and dialogue-based synchronization between agents to restore shared mental models in multi-pod topologies.

Can I use the filesystem as durable memory for cross-agent restoration?▼

Yes, the filesystem serves as multiplayer durable memory where scope folders are readable and writable by every agent, enabling cross-agent restoration and externalized state.

What is the best way to maintain continuous state for OpenRig pipelines?▼

Maintain continuous state by regularly updating scope-knowledge, session logs, and restore artifacts to keep memory fresh across OpenRig pipelines and multi-agent pods.

Does multi-agent mental model restoration support single agents and pairs?▼

Multi-agent mental model restoration applies to single agents, pairs, and multi-pod topologies within OpenRig pipelines, satisfying five-layer restore model requirements.

Related Skills

Explore More Software Engineering Skills→
richardmbaileyrichardmbailey

rb-working-diary

Maintain structured markdown diaries of decisions, findings, and next actions.

Community
Intermediate
jduttonjdutton
3

recovering-work

Restore lost files from validation snapshots and git history using tree-hashes.

Community
Advanced
zachmayerzachmayer
2

session-lifecycle

Coordinate orientation, planning, and persistence across git repositories and GitHub issues.

Community
Advanced
arugo11arugo11
1

checkpoining

Execute the Codex-native checkpointing workflow to save current progress.

Community
Basic