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-stylegit 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-style)<a href="https://agentmods.dev/skills/google/adk-python/adk-style"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-style/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-style"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-style.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 | $0.00187 | $0.00790 |
| Opus 5.5 | $0.00075 | $0.00316 |
| Sonnet 5.5 | $0.00037 | $0.00158 |
| Haiku 4.5 | $0.00019 | $0.00079 |
Grade A, and why
adk-style 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 7d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADK Style Guide
Conventions for src/google/adk/ and tests/unittests/. Most are enforced by
a pre-commit hook or a CI job, so a violation blocks the PR rather than
surfacing in review. Read the one reference for the topic you are touching.
Pick a reference
| Task | Reference |
|---|---|
Adding a .py file; deciding public vs private; __init__.py and __all__ |
visibility.md |
Writing import lines; relative vs absolute; circular imports; TYPE_CHECKING; lazy imports |
imports.md |
Annotating args and returns; AgentMode vs raw mode strings; _NodePathBuilder, _BranchPath, and build_node; Optional vs | None; keyword-only args; isinstance; asserts; mypy; # type: ignore and cast |
typing.md |
| Defining a Pydantic model, validator, private attribute, or on-wire payload | pydantic.md |
| Indentation, line length, quotes; running the formatter; what each hook checks | formatting.md |
| Writing a docstring or an explanatory comment | documentation.md |
| Emitting a log record; naming the module logger; picking a level | logging.md |
| Anything that performs I/O — network, disk, database | async.md |
| Where a new file goes; license header; where its test goes and what to call it | file-organization.md |
Writing or restructuring a unit test; the testing_utils fakes |
testing.md |
A check failed — where to look
| Failing check | Reference |
|---|---|
check-new-py-prefix |
visibility.md |
compliance-checks |
logging.md (logger name), typing.md (from __future__ import annotations), imports.md (cli/ import direction) |
pyink, isort, ruff, addlicense, codespell |
formatting.md |
| Mypy Check CI job | typing.md |
tests/unittests/test_import_loading.py |
imports.md |
What ships with it
10 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/async.md 880 B
- references/documentation.md 1.1 KB
- references/file-organization.md 1.1 KB
- references/formatting.md 2.5 KB
- references/imports.md 3.1 KB
- references/logging.md 1.2 KB
- references/pydantic.md 5.2 KB
- references/testing.md 9.7 KB
- references/typing.md 7.7 KB
- references/visibility.md 3.3 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.
- 7d ago Changed a6cdd06b8cf5
- 13d ago Changed · +1 lines 6eee291fc5b5
- 1mo ago First seen · 46 lines · 187 tokens per session scan A e7e4eba3530c
adk-style is a skill published in the GitHub repository google/adk-python (21,864 stars, last pushed today), licensed Apache-2.0. It adds 187 tokens to every session and 790 once invoked, about $0.0007 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
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
fastmcp
Build, test, inspect, and deploy Python MCP servers with FastMCP.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
vigilante-issue-implementation-on-python
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Python repository with idiomatic tooling and security guidance.
dependency-manager
Manage Python dependencies using UV, pip-tools, or requirements.txt. Use when setting up dependency management, resolving conflicts, or choosing between UV, pip-tools, and requirements.txt workflows.
python-packaging
Configure Python package metadata, setup.py, and pyproject.toml for distribution using UV or setuptools. Use when setting up Python packages, configuring build systems, or preparing projects for PyPI publication.