agentmods.dev

google-adk

google-adk is a skill for Claude Code, Codex from fmind/dot. It costs 44 tokens per session (1,279 once invoked), scanned A, original, MIT.

A development toolkit for building, testing, and deploying Google ADK agents in Go or Python. ADK is Google's framework for programs that use AI agents.

In plain words
What is it for?
Use it to create ADK projects, serve agents with a console or web interface, evaluate them, and deploy them to Agent Runtime or Cloud Run.
Why use it?
It provides documented paths for running agents locally or deploying them to Google-managed or container-based services.

Skill for Claude CodeCodex

not rated 4 today A scan 44 tokens original MIT
View the source file fmind/dot
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/fmind/dot/google-adk
Any agent
npx skills add fmind/dot --skill google-adk
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for google-adk

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/google-adk.svg)](https://agentmods.dev/skills/fmind/dot/google-adk)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/google-adk"><img src="https://agentmods.dev/badge/skills/fmind/dot/google-adk.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 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 $0.00044 $0.01279
Opus 5 $0.00022 $0.00639
Sonnet 5 $0.00009 $0.00256
Haiku 4.5 $0.00004 $0.00128

Measured yesterday against content hash 252549b9bab2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

google-adk 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 yesterday.

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.

skills/google-adk/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google ADK Agents

The Agent Development Kit is the default agent framework: code-first, model-agnostic, Gemini-optimized, with a launcher serving console, web UI, REST, and A2A from one binary. Go is the default; Python when agents-cli scaffolding, evaluation, or Agent Runtime matter more than a single static binary. Language APIs live in go-stack §6 and python-stack §5.

1. Choose the Path

  • Go service, CLI, or single binary: google.golang.org/adk/v2 with full.NewLauncher() per go-stack §6.
  • Python with generated CI, eval, and deploy scaffold: agents-cli, run as uvx google-agents-cli (uvx ships with uv; nothing to install) per §2.
  • Managed runtime (sessions, memory, registry): Agent Runtime (Gemini Enterprise Agent Platform, formerly Vertex AI) via agents-cli deploy --deployment-target agent_runtime.
  • Self-managed container: Cloud Run via agents-cli deploy --deployment-target cloud_run, or the Go launcher's web mode per cloud-run.

2. Python Workflow (agents-cli)

uvx google-agents-cli create <name> --agent adk --deployment-target cloud_run --region europe-west1 --agent-guidance-filename AGENTS.md   # name <= 26 chars, lowercase
cd <name> && uvx google-agents-cli install --locked   # dependencies
uvx google-agents-cli playground                      # local web UI with live reload
uvx google-agents-cli run "hello"                     # one prompt, then shutdown
uvx google-agents-cli eval run                        # dataset in tests/, LLM-as-judge metrics (approval: model cost)
uvx google-agents-cli deploy --dry-run                # review; real deploys need explicit approval
  • Agent Runtime targets omit --session-type; other targets accept --session-type agent_platform_sessions; --cicd-runner github_actions generates the workflow.
  • Keep the generated app/ layout (agent.py, fast_api_app.py) and agents-cli-manifest.yaml; add the canonical mise.toml tasks around it and never hand-write A2A plumbing.
  • Test wiring and scaffold normalization are in python-stack §5.

Read the full file on GitHub · 68 lines

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. yesterday First seen · 68 lines · 44 tokens per session scan A 252549b9bab2

Subscribe to this mod's changes

google-adk is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,279 once invoked, about $0.0002 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 2026-09-03.

Building agentsai-agentschezmoiclaude-codedotfilesfish-shellgemini-cli
Related

Other skills, from other repositories

go-stack

Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.

fmind/dotfiles · 31 tokens

python-stack

Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.

fmind/dotfiles · 41 tokens

k8s-local

Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.

fmind/dotfiles · 50 tokens

chezmoi

Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.

fmind/dotfiles · 32 tokens

hugo

Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.

fmind/dotfiles · 46 tokens

mise

Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.

fmind/dotfiles · 27 tokens