Create Agent
vectorize-io/hindsight
Create a new Hindsight-powered subagent with long-term memory.
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.
Install Adk Architecture
$ npx skills add google/adk-python --skill adk-architecture -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install google/adk-python adk-architecture --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/adk-architecture .claude/skills/adk-architecture && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .claude/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/google/adk-python/tree/main/.agents/skills/adk-architectureType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add google/adk-python --skill adk-architecture -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install google/adk-python adk-architecture --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/adk-architecture .agents/skills/adk-architecture && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .agents/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google/adk-python --skill adk-architecture -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install google/adk-python adk-architecture --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/adk-architecture .cursor/skills/adk-architecture && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .cursor/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/google/adk-python.git --path .agents/skills/adk-architecture--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add google/adk-python --skill adk-architecture -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install google/adk-python adk-architecture --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/adk-architecture .gemini/skills/adk-architecture && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .gemini/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install google/adk-python adk-architectureInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add google/adk-python --skill adk-architecture -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/adk-architecture .github/skills/adk-architecture && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .github/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add google/adk-python --skill adk-architecture -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install google/adk-python adk-architecture --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/adk-architecture .opencode/skills/adk-architecture && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "adk-architecture" agent skill from https://github.com/google/adk-python/tree/main/.agents/skills/adk-architecture into .opencode/skills/adk-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "adk-architecture", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
adk-architecture- GitHub stars
- 22k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 386 words
- Files
- 15 (incl. references)
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
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.
- Answering how does X work about ADK internals
- SKILL.md covers Pick a reference and Where the code lives
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Tracing where an event
What it does
Adk Architecture is an agent skill from google/adk-python, published by the product's own GitHub organization. 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…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including reference files (for example `references/api-principles.md`, `references/architecture-checkpoint-resume.md` and `references/architecture-context.md`).
It sits in Agent Workflows, covering Building AI agents. The repository describes itself as: An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. The licence is Apache-2.0.
When your agent uses it
- Answering how does X work about ADK internals
- Tracing where an event
- A piece of state comes from
- Deciding where a new capability belongs
Example prompts
- “how does X work”
- “Use the adk-architecture skill to explain how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint…”
- “/adk-architecture”
What it can do on your machine
Read from SKILL.md and the folder at commit 097ae1e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Adk Architecture loads about 1.2k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 183 tokens; SKILL.md has 386 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from google/adk-python at commit 097ae1e, republished under its Apache-2.0 licence (© google). 386 words, ~1,210 tokens.
Download SKILL.mdSave it as
.claude/skills/adk-architecture/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.- name
- adk-architecture
- description
- 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).
ADK Architecture
The runtime is a graph of nodes. BaseNode is the unit of execution.
Workflow is a node that schedules other nodes along declared edges.
NodeRunner executes exactly one node. Runner owns the invocation and the
session. Agents are nodes too — BaseAgent extends BaseNode.
A node communicates with its parent through a per-execution Context, and
with the session through Events it yields. Those are two separate channels:
ctx carries the result upward, events carry persistence and streaming.
Read the source before relying on any signature here. These notes drift; the
code does not. Paths below are relative to src/google/adk/.
Pick a reference
| Question | Reference |
|---|---|
| What must a node implement? What may it yield? Which config fields exist? | BaseNode |
| How does the graph schedule nodes, dedup dynamic children, propagate interrupts? | Workflow |
| How does a caller start an invocation? | Runner |
What is Agent, and which methods do I call on it? | Agent |
| I am subclassing an agent — what do I override? | BaseAgent |
What is on an Event, and what may I assume about its lifetime? | Event |
What does a node read and write on ctx? | Context |
| Who creates the child Context, stamps events, retries, catches errors? | NodeRunner |
| Why are Runner, NodeRunner and Workflow three separate things? | Runner roles |
| How does a human-in-the-loop pause and resume work for one node? | Checkpoint and resume |
How does a whole workflow survive a pause, and what does is_resumable change? | Workflow resumability |
| How are spans created, and what attributes do they carry? | Observability |
| Why does the model not see the raw event log? | LLM context orchestration |
| Is this change a breaking change? Where does a new export belong? | API principles |
Show full SKILL.md (112 more words)Show less
Where the code lives
| Concept | Module |
|---|---|
BaseNode, START | workflow/_base_node.py |
Workflow, _LoopState | workflow/_workflow.py |
Graph, edge compilation | workflow/_graph.py |
NodeRunner | workflow/_node_runner.py |
DynamicNodeScheduler, DynamicNodeState, DynamicNodeRun | workflow/_dynamic_node_scheduler.py |
ReplayManager (resume scan) | workflow/utils/_replay_manager.py |
check_interception (replay fast-forward) | workflow/utils/_replay_interceptor.py |
NodeInterruptedError, NodeTimeoutError | workflow/_errors.py |
Context, ctx.run_node() | agents/context.py |
ReadonlyContext | agents/readonly_context.py |
InvocationContext | agents/invocation_context.py |
BaseAgent, LlmAgent (aliased Agent) | agents/base_agent.py, agents/llm_agent.py |
BaseLlmFlow, SingleFlow, AutoFlow, flows/llm_flows/ subpackages (context/, prompt/, tools/, extensions/, core/) | flows/llm_flows/ |
Event, NodeInfo | events/event.py |
EventActions | events/event_actions.py |
Branch paths (parent.child@1) | events/_branch_path.py |
Node paths (wf@1/child@2) | events/_node_path_builder.py |
Runner, InMemoryRunner | runners.py |
LiveRequestQueue, LiveRequest | live/live_request_queue.py |
Node spans, TelemetryContext | telemetry/node_tracing.py |
ResumabilityConfig | apps/_configs.py |
Everything under workflow/ is a leading-underscore module. Treat those names
as internal — they can change without a major version bump, so a change there
is not automatically a breaking change.
© google, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 14 other files (references) in .agents/skills/adk-architecture of google/adk-python.
- SKILL.md
- references/api-principles.md
- references/architecture-checkpoint-resume.md
- references/architecture-context.md
- references/architecture-llm-context-orchestration.md
- references/architecture-node-runner.md
- references/architecture-observability.md
- references/architecture-runner-roles.md
- references/architecture-workflow-resumability.md
- references/interface-agent.md
- references/interface-base-agent.md
- references/interface-base-node.md
- references/interface-event.md
- references/interface-runner.md
- references/interface-workflow.md
Open the folder on GitHubat commit 097ae1e
Compare with similar skills
Adk Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Adk Architecture this skillgoogle/adk-python | 22k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Create Agentvectorize-io/hindsight | 47k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Topologychmod777john/swarm-ide | 1.5k | — | ~447 | Automated safety check: Pass | None | |
| Agent Skills PlatformFrancyJGLisboa/agent-skills-platform | 2.4k | — | ~12k | Automated safety check: Notes | MIT | |
| Dashclaw Governanceucsandman/DashClaw | 310 | — | ~2.7k | Automated safety check: Pass | MIT | |
| Agent Creatorjdforsythe/forge | 151 | — | ~4.5k | Automated safety check: Pass | MIT |
Similar skills
Topology
chmod777john/swarm-ide
Explain the IM+Agent framework: create+send as minimal primitives, IM system vs agent loop separation, message vs llmHistory, and the recursive property.
Agent Skills Platform
FrancyJGLisboa/agent-skills-platform
Create cross-platform agent skills from workflow descriptions.
Dashclaw Governance
ucsandman/DashClaw
Governance behavior for AI agents governed by DashClaw. An agent skill from ucsandman/DashClaw.
Agent Creator
jdforsythe/forge
Creates structured agent definitions using the 7-component format grounded in persona science (the alignment-accuracy tradeoff), vocabulary routing, and the MAST failure taxonomy + Forge watchlist.
- Official
Deep Agents
langchain-ai/docs
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.
More from google/adk-python
All 13 skills in this repo- Official
Adk Verify Snippets
google/adk-python
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…
- Official
Adk Sample Creator
google/adk-python
Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use.
- Official
Adk Unit Guide
google/adk-python
Writes a hands-on developer guide for one ADK code unit — a minimal runnable example, how it works, a configuration-option table, advanced uses, limitations, and links to related samples — to…
- Official
Adk Git
google/adk-python
Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and…
- Official
Adk Setup
google/adk-python
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…
- Official
Adk Agent Builder
google/adk-python
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between…
Related
Categories
Questions about Adk Architecture
What does Adk Architecture do?
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. Adk Architecture is an agent skill from google/adk-python, published by the product's own GitHub organization. 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.
When should I use Adk Architecture?
Adk Architecture fits situations like: answering how does X work about ADK internals; tracing where an event; A piece of state comes from; deciding where a new capability belongs.
How do I install Adk Architecture in Claude Code?
Run `npx skills add google/adk-python --skill adk-architecture -a claude-code`. Or copy the skill folder (.agents/skills/adk-architecture in google/adk-python) into .claude/skills/adk-architecture in your project. Claude Code loads it when a task matches its description.
How do I install Adk Architecture in Codex?
Run `npx skills add google/adk-python --skill adk-architecture -a codex`. Or copy the skill folder (.agents/skills/adk-architecture in google/adk-python) into .agents/skills/adk-architecture in your project. Codex loads it when a task matches its description.
Can I use Adk Architecture in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google/adk-python --skill adk-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adk-architecture, .gemini/skills/adk-architecture, .github/skills/adk-architecture and .opencode/skills/adk-architecture in your project.
What does Adk Architecture need to run?
SKILL.md names no scripts, command-line tools or credentials: Adk Architecture is instructions for the agent only.
Does Adk Architecture access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Adk Architecture safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Adk Architecture use?
Adk Architecture is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Adk Architecture use?
About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.
What are the alternatives to Adk Architecture?
Skills that share tags, products or a category with Adk Architecture: Create Agent (vectorize-io/hindsight, 47k stars), Topology (chmod777john/swarm-ide, 1.5k stars), Agent Skills Platform (FrancyJGLisboa/agent-skills-platform, 2.4k stars) and Dashclaw Governance (ucsandman/DashClaw, 310 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Adk Architecture?
google (a GitHub organization, an official publisher) maintains it in google/adk-python, which has 21,736 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.
Source: google/adk-python on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.