Google Agent Development Kit is a code-first toolkit for building, evaluating, deploying, and coordinating AI agents. Developers use it to create agents and multi-agent systems with tools, orchestration, tracing, and deployment options, while the catalogue entries are example agents and skills built around 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-docs --skill adk-bot-reviewgit clone --depth 1 https://github.com/google/adk-docsWrote 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-docs/adk-bot-review)<a href="https://agentmods.dev/skills/google/adk-docs/adk-bot-review"><img src="https://agentmods.dev/badge/skills/google/adk-docs/adk-bot-review/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-docs/adk-bot-review"><img src="https://agentmods.dev/badge/skills/google/adk-docs/adk-bot-review.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 | $0.00058 | $0.01601 |
| Opus 5.5 | $0.00023 | $0.00640 |
| Sonnet 5.5 | $0.00012 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
adk-bot-review 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review changes proposed by adk-bot (adk-bot-review)
This skill guides a rigorous review of adk-bot changes. It ensures documentation updates are technically accurate, appropriately sized, and follow ADK docs conventions, based on Google's developer documentation style.
Step 1: Verify and research the proposed adk-bot change
- Check that the PR title briefly describes the topic being updated, not only the issue.
- Confirm changes are made directly in the
.mdfiles and no "do not merge" status tags were prematurely removed. - Check the PR's mergeable state and CI status. Note git conflicts and failing checks as findings to resolve or to fix in the consolidating PR.
- The input is one adk-bot-authored PR, or occasionally a few. From the PR, trace back to the issue and the specific item it addresses. Identify the item from the PR title ("Update ADK doc according to issue # - ") and body. adk-bot often opens more than one PR for the same item. If multiple PRs are provided, confirm they all address the same item and review them together as one consolidation set. If they address different items, ask the user which one to focus on before continuing.
- Search closed issues and merged/rejected PRs across the repository for similar topics. Ensure the bot is not re-introducing changes, APIs, or stylistic choices that human maintainers have previously debated and rejected.
- Summarize the item's intended change and stated reasoning, and carry that intent into the technical validation in the next steps.
Step 2: Assess update criteria and architecture
- Prioritize smaller, surgical updates over comprehensive overhauls unless the existing docs are entirely unclear.
- Verify that the update provides a useful learning experience and is actionable for a developer.
- Ensure the content is placed appropriately within the ADK docs information architecture.
- Confirm the update length and prioritization are appropriate for the specific code change (check if it is already covered by existing docs or API references).
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 · 140 lines · 58 tokens per session scan A 3d1e1a42ae95
adk-bot-review is a skill published in the GitHub repository google/adk-docs (1,524 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,601 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…