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 agentmods add skills/saski/arnesto/google-adk-agent-patternsnpx skills add saski/arnesto --skill google-adk-agent-patternsgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/google-adk-agent-patterns)<a href="https://agentmods.dev/skills/saski/arnesto/google-adk-agent-patterns"><img src="https://agentmods.dev/badge/skills/saski/arnesto/google-adk-agent-patterns.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00092 | $0.01141 |
| Opus 5 | $0.00046 | $0.00571 |
| Sonnet 5 | $0.00018 | $0.00228 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
google-adk-agent-patterns 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 5d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google ADK Agent Patterns
When to Use / When Not to Use
Use this skill when:
- Defining or modifying an
Agent(LlmAgent) with model, instructions, or tools. - Writing Python function tools registered in
tools=[...]. - Composing multi-agent pipelines (sequential, loop, parallel, router).
- Passing state between agents using
output_key/{var}injection.
Do not use this skill when:
- Setting up a new ADK project from scratch (use
google-adk-setup). - Deploying to Cloud Run (covered in
google-adk-setupreferences).
Agent Configuration (LlmAgent / Agent)
from google.adk.agents.llm_agent import Agent
root_agent = Agent(
name="my_agent",
model="gemini-2.5-flash",
description="One-sentence description used by other agents for routing.",
instruction="You are a helpful assistant. Answer: {topic?}",
tools=[my_tool],
)
Key parameters:
| Parameter | Purpose |
|---|---|
name |
Unique identifier for the agent |
model |
Gemini model string (e.g. gemini-2.5-flash) |
description |
Used by orchestrators for routing — be precise |
instruction |
System prompt; supports {var} (required) and {var?} (optional) state injection |
tools |
List of Python functions or AgentTool instances |
output_schema |
Pydantic model for structured output |
output_key |
Writes agent output to shared session state under this key |
include_contents |
Controls which conversation history is passed |
generate_content_config |
Fine-grained generation parameters |
Critical constraint: output_schema and tools cannot both be set on most models. Choose one.
Function Tools
See references/tool-patterns.md for full examples.
Minimal function tool
def get_weather(city: str) -> dict:
"""Return current weather for the given city name.
Args:
city: The city name to look up.
"""
return {"status": "success", "temperature_c": 22}
agent = Agent(model="gemini-2.5-flash", name="weather_agent", tools=[get_weather])
What ships with it
2 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.
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.
- 5d ago First seen · 157 lines · 92 tokens per session scan A 1651ebd1f1bf
google-adk-agent-patterns is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 9d ago), licensed Unlicense. It adds 92 tokens to every session and 1,141 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
pixir-delegate
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill ! preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (pixir --json), parallel fan-out to N children (pixir delegate --spec), resumable steering (pixir resume), evidence…
pixir-delegate-codex
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution…
pixir-diagnostics
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
pixir-delegate-native
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawnagent, waitagent, closeagent, listagents, sendinput) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates …
repo-contracts-and-boundaries
Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.