Agent Development Kit is a Python framework for building, evaluating, deploying, and coordinating AI agents as software applications. Developers use it to compose workflows, delegate tasks between specialized agents, manage state, and connect agents to tools while choosing supported models and deployment environments. The catalogue add-ons provide workflows for using the toolkit.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add google/adk-python --skill adk-architecturegit clone --depth 1 https://github.com/google/adk-pythonWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/google/adk-python/adk-architecture)<a href="https://agentmods.dev/skills/google/adk-python/adk-architecture"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/google/adk-python/adk-architecture"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.01215 |
| Opus 5.5 | $0.00063 | $0.00486 |
| Sonnet 5.5 | $0.00031 | $0.00243 |
| Haiku 4.5 | $0.00016 | $0.00121 |
Grade A, and why
adk-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/api-principles.md 2.7 KB
- references/architecture-checkpoint-resume.md 2.6 KB
- references/architecture-context.md 4.2 KB
- references/architecture-llm-context-orchestration.md 1.9 KB
- references/architecture-node-runner.md 4.8 KB
- references/architecture-observability.md 4.0 KB
- references/architecture-runner-roles.md 452 B
- references/architecture-workflow-resumability.md 7.7 KB
- references/interface-agent.md 2.0 KB
- references/interface-base-agent.md 2.0 KB
- references/interface-base-node.md 4.9 KB
- references/interface-event.md 3.2 KB
- references/interface-runner.md 3.0 KB
- references/interface-workflow.md 20 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 23d ago Changed · +2 lines 44901394ad6e
- 1mo ago First seen · 76 lines · 157 tokens per session scan A 10f510ec9911
adk-architecture is a skill published in the GitHub repository google/adk-python (21,864 stars, last pushed today), licensed Apache-2.0. It adds 157 tokens to every session and 1,215 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
security-conductor
Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.
grocery-prices
A skill to calculate grocery prices with country-specific taxes.