Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).
Ask your Agent
Use this Skill: https://skilld.dev/gh/google/adk-python/adk-architecture
This session only. Nothing lands on disk.
≈113 tokens on demand. Your agent reads this file only when SKILL.md points to it.
These three are deliberately separate:
Merging Runner and NodeRunner would deadlock on nested workflows (inner workflow's NodeRunner would block the outer's Runner).
Source: SKILL.md on GitHub
This skill consists of comprehensive architectural documentation for the Agent Development Kit (ADK). It provides technical guidance on the framework's node execution model, context scoping, and observability patterns. No security considerations were identified as the content is purely informational and follows standard developer documentation practices.
No alerts
Risk: LOW · No issues
Signed by skilld at f7a1cd4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub yesterday.