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-setupgit 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-setup)<a href="https://agentmods.dev/skills/google/adk-python/adk-setup"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-setup/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-setup"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 41 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- low Supply Chain · line 41 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00146 | $0.00957 |
| Opus 5.5 | $0.00058 | $0.00383 |
| Sonnet 5.5 | $0.00029 | $0.00191 |
| Haiku 4.5 | $0.00015 | $0.00096 |
Grade C, and why
adk-setup scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADK Python Development Setup
Set up a working adk-python checkout: a uv-managed virtual environment with
every dependency extra, pre-commit hooks, and a green unit-test run.
Prerequisites
-
Python. ADK supports 3.11 through 3.15 (
requires-python = ">=3.11"inpyproject.toml). These steps use 3.11, the version the repo's own tooling defaults to.python3 --version -
uv. Dependencies are declared in
pyproject.toml. Theuv syncstep below creates a localuv.lock, which this repository ignores. Run that step beforetox, whose lock runner requires the file.uv --versionInstall it if missing:
curl -LsSf https://astral.sh/uv/install.sh | sh
Setup
Run these from the repository root.
-
Create and activate the virtual environment:
uv venv --python "python3.11" ".venv" source .venv/bin/activate -
Install every dependency extra:
uv sync --all-extras--all-extrasis what pulls in thetestanddevextras. Syncing only the default dependencies leavespytestand the linters uninstalled. -
Install pre-commit and tox as standalone tools:
uv tool install pre-commit uv tool install tox --with tox-uvBoth are also in the
devextra; installing them as uv tools puts them on PATH so the git hook and multi-version test runs work without an activated venv. -
Install
addlicense(optional, requires Go):go install github.com/google/addlicense@latestWithout it the pre-commit hook prints
Warning: addlicense not installed, skippingand passes, so a missing Go toolchain does not block setup — CI catches missing license headers instead. -
Install the git hooks:
pre-commit installOn each commit the hooks auto-format with
isort,pyink, andmdformat, then runruff,addlicense,codespell, and the repo's own compliance checks.
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.
- 3d ago Changed da08e0bab99c
- 9d ago Changed 2262507dccf5
- 16d ago Changed · +1 lines 1591b44b6207
- 1mo ago First seen · 116 lines · 146 tokens per session scan C 3e76a0773469
adk-setup is a skill published in the GitHub repository google/adk-python (21,864 stars, last pushed today), licensed Apache-2.0. It adds 146 tokens to every session and 957 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
python-providers
Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.
writing-tests
Kiro Crew repo only: how to write a backend pytest test with NO side effects that does not flake. Use when adding, editing, reviewing or debugging a test there: which conftest applies, what leaks (temp dirs, data home, /.kiro, cron, threads), the seven flake classes, cross-platform traps.
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…