adk-unit-guide

A hands-on guide for using one ADK code unit, with a runnable example, configuration options, advanced uses, limitations, and related samples.

In plain words
What is it for?
Use it to write detailed usage documentation for a public ADK class, method, or other code unit.
Why use it?
It gives developers practical instructions for calling a specific part of ADK without requiring them to search through the whole codebase.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/google/adk-python/adk-unit-guide
Any agent
npx skills add google/adk-python --skill adk-unit-guide
Clone the repo
git clone --depth 1 https://github.com/google/adk-python

Made for: Claude Code, Codex.

Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00199 $0.01577
Opus 5 $0.00100 $0.00788
Sonnet 5 $0.00040 $0.00315
Haiku 4.5 $0.00020 $0.00158

Measured 2d ago against content hash 1578310ebb28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.agents/skills/adk-unit-guide/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 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.

Read the full file on GitHub · 150 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 150 lines · 199 tokens per session scan A 1578310ebb28

Subscribe to this mod's changes

adk-unit-guide is a skill published in the GitHub repository google/adk-python (21,331 stars, last pushed 2d ago), licensed Apache-2.0. It adds 199 tokens to every session and 1,577 once invoked, about $0.0010 per session on Opus 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.