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-unit-guidegit 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-unit-guide)<a href="https://agentmods.dev/skills/google/adk-python/adk-unit-guide"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-unit-guide/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-unit-guide"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-unit-guide.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 | $0.00199 | $0.02382 |
| Opus 5.5 | $0.00080 | $0.00953 |
| Sonnet 5.5 | $0.00040 | $0.00476 |
| Haiku 4.5 | $0.00020 | $0.00238 |
Grade A, and why
adk-unit-guide 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 10d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADK code unit guide
A unit guide is granular usage documentation for one code unit, deeper than what ships on adk.dev — so detail that would bloat the published documentation has somewhere to live. The reader wants to call the unit from an application, so lead with working code.
Unit guides focus on public APIs and caller-visible behavior. Do not discuss internal implementation details (such as private methods, internal state mechanisms, or unexported helpers).
Voice
Write to help the reader understand, not to instruct them from above.
- Give the reason, not only the rule. Whenever the guide states a constraint, a default, or a recommendation, say why it is that way. A reader who knows the reason can handle the case the guide did not anticipate.
- Do not decide for the reader. Phrasings such as "most applications never need this" or "you will rarely" tell people what they want. State the trade-off and let them choose.
- Explain at the caller's level. Explaining what happens is required; explaining the machinery that makes it happen is not. If an explanation needs a private symbol to make sense, it is pitched at the wrong layer.
- Length follows understanding. Brevity is not the goal. Where a reader would have a follow-up question, answer it. Where the sentence already lands, leave it.
- Problem before syntax. Say what the reader is trying to do, then show the code.
- Every heading has at least one sentence under it before the next heading, and every code block has a sentence introducing what it does.
Sentence-level rules, following the Google developer documentation style guide:
present tense, no contractions, no parentheticals (use commas), no bare "This"
as a subject, no e.g. or etc., no superlatives, sentence case in headings,
and no heading deeper than H3.
What the difference looks like
From the BaseNode guide. Before:
Most applications never subclass
BaseNode, so the sections that follow cover the settings first.
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.
- 10d ago Changed · +7 lines faa2dc83e5a8
- 22d ago Changed · +61 lines 3e0d48c91ca8
- 1mo ago First seen · 150 lines · 199 tokens per session scan A 1578310ebb28
adk-unit-guide is a skill published in the GitHub repository google/adk-python (21,864 stars, last pushed today), licensed Apache-2.0. It adds 199 tokens to every session and 2,382 once invoked, about $0.0008 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
flashcards
Create strict JSON flashcard decks for active-recall study.
quiz
Create strict JSON single-answer multiple-choice quizzes.
manim-video
Generate mathematical/explanatory animations with Manim (Python). Use for animated explainers, math visualizations, and step-by-step animations the user can render to MP4.
ai-engineering-curriculum
Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.
accredible-certificates-automation
Automate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas.
blackboard-automation
Automate Blackboard tasks via Rube MCP (Composio). Always search tools first for current schemas.