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-verify-snippetsgit 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-verify-snippets)<a href="https://agentmods.dev/skills/google/adk-python/adk-verify-snippets"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-verify-snippets/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-verify-snippets"><img src="https://agentmods.dev/badge/skills/google/adk-python/adk-verify-snippets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 97 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 103 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 112 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00149 | $0.01333 |
| Opus 5.5 | $0.00060 | $0.00533 |
| Sonnet 5.5 | $0.00030 | $0.00267 |
| Haiku 4.5 | $0.00015 | $0.00133 |
Grade C, and why
adk-verify-snippets scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
Put `<!-- verify-snippets: ignore -->` alone on a line immediately before the How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Markdown Snippets
Extracts every ```python block from a Markdown file, runs each one in its
own subprocess via the bundled run.py harness, and writes a report covering
load status, run status, and line coverage per snippet.
Read-only contract
Verifying a doc must never change the doc. Do not create, modify, or delete any file in the repository — including the Markdown being verified, its code blocks, and this SKILL.md. Report the failures; do not fix them and do not offer patches.
The script performs the only two writes that happen: temporary .py files in a
system temp directory outside the repository (removed when it exits), and the
report beside the source Markdown file.
Prerequisites
-
An ADK development environment — run from the repository root with the
uvvirtual environment active (see theadk-setupskill). -
coverage, optional. It is not a declared project dependency, so install it explicitly; without it the Coverage column shows—.uv pip install coverage -
A Gemini API key, needed only for snippets that build an
Agent,App, orWorkflow— those are executed against the live API.export GEMINI_API_KEY="{your_key}" # or export GOOGLE_API_KEY="{your_key}"If both are set the harness drops
GOOGLE_API_KEY, soGEMINI_API_KEYwins.
Usage
uv run --no-sync python .agents/skills/adk-verify-snippets/scripts/verify_md.py {path_to_markdown_file}
The script prints per-snippet progress, then writes the report beside the source file and prints its full path.
The report filename is the source file's stem lowercased with everything except
[a-z0-9_] stripped, plus _REPORT.md. Workflow-Guide.md therefore produces
workflowguide_REPORT.md, not Workflow-Guide_REPORT.md — read the path the
script prints rather than reconstructing it.
The report contains an Executive Summary table with one row per snippet, then a detailed section per snippet holding the code block, the execution logs (stdout plus stderr/traceback), and the coverage output.
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.
- 1mo ago First seen · 137 lines · 149 tokens per session scan C 24fbbd3bc36b
adk-verify-snippets is a skill published in the GitHub repository google/adk-python (21,885 stars, last pushed today), licensed Apache-2.0. It adds 149 tokens to every session and 1,333 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
python-providers
Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.
writing-tests
Kiro Crew repo only: how to write a backend pytest test with NO side effects that does not flake. Use when adding, editing, reviewing or debugging a test there: which conftest applies, what leaks (temp dirs, data home, /.kiro, cron, threads), the seven flake classes, cross-platform traps.
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…