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-sample-creatorgit 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-sample-creator)<a href="https://agentmods.dev/skills/google/adk-python/adk-sample-creator"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-sample-creator/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-sample-creator"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-sample-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00150 | $0.01264 |
| Opus 5.5 | $0.00060 | $0.00506 |
| Sonnet 5.5 | $0.00030 | $0.00253 |
| Haiku 4.5 | $0.00015 | $0.00126 |
Grade A, and why
adk-sample-creator 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 1mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADK Sample Creator
Creates samples under contributing/samples/. These are deliberately minimal
agents that each exercise one or two features — distinct from the adk-samples
repository, which hosts full end-to-end applications.
Read the adk-style skill first for ADK 2.0 conventions if you have not
already.
1. Pick the category directory
Almost every sample lives at
contributing/samples/{category}/{sample_name}/. List the categories and
confirm with the user which one the sample belongs in before creating
anything — a workflow sample landing outside workflows/ is the usual mistake.
ls contributing/samples/
Categories include workflows, patterns, core, multi_agent, tools,
models, live, mcp, a2a, evaluation, and plugins. A handful of
samples nest one level further when a single feature needs several variants, as
plugins/plugin_reflect_tool_retry/basic/ does.
Name the sample directory in snake_case after the feature it demonstrates:
dynamic_nodes, fan_out_fan_in, streaming_tool_events.
Do not add an _agent suffix, and do not repeat the category as a prefix —
every sample is an agent, and the category is already in the path. Many existing
directories still carry both; do not copy them.
2. Write agent.py
Contents of a sample directory:
| File | Required | Purpose |
|---|---|---|
agent.py |
yes | The agent or workflow. Must expose root_agent. |
README.md |
yes | See readme-template.md. |
__init__.py |
sometimes | Present when the sample is imported as a package. |
tests/*.json |
no | Recorded sessions used as eval sets. |
Use absolute imports so the file can be run and imported directly.
Do not set model= on Agent instances. Samples inherit the
system-configured model, which keeps them working when the default model
changes; hardcoding model="gemini-2.5-flash" pins the sample to a model that
will be retired. Set it only when the user explicitly asks for a specific model.
What ships with it
1 file 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.
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.
- 1mo ago First seen · 159 lines · 150 tokens per session scan A 19bce171b731
adk-sample-creator is a skill published in the GitHub repository google/adk-python (21,864 stars, last pushed today), licensed Apache-2.0. It adds 150 tokens to every session and 1,264 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.