What problem does it solve? When multiple AI agent sessions (Claude, Codex, Gemini) run as connected nodes on the nodeterm canvas, each session is blind to what the others have done. This Skill lets an agent pull the context of a linked node on demand, enabling handoffs, continuation of work, and coordination without manual copy-pasting. ## Core Features & Use Cases - List Linked Nodes: Run the list command to see every agent node and sticky note connected to the current session via a context-link edge. - Read Summaries and Transcripts: Fetch the last N lines of a linked node's conversation with summary, or its full transcript with transcript. - Inspect Terminal Output: Use terminal to view a linked node's recent visible terminal buffer. - Read Live Sticky Notes: Linked sticky notes appear in list marked (note) and are read live from the canvas, so their current text is always returned. - Use Case: A Claude node finishes scaffolding an API and a linked Codex node needs to continue the implementation; the Codex session runs summary to see what Claude already did before writing code. ## Quick Start Ask the agent to list the nodes it is linked to on the nodeterm canvas and summarize what the connected node has been doing.