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 frankxai/claude-skills-library --skill partner-googlegit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/partner-google)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/partner-google"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-google/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/frankxai/claude-skills-library/partner-google"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/partner-google.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00077 | $0.02032 |
| Opus 5.5 | $0.00031 | $0.00813 |
| Sonnet 5.5 | $0.00015 | $0.00406 |
| Haiku 4.5 | $0.00008 | $0.00203 |
Grade A, and why
partner-google 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Cloud — Partner Intelligence
Current state (as of 2026-05-17)
Gemini 3 is the current flagship model line, with Gemini 3.1 Flash Image ("Nano Banana 2" / NB2) as the multimodal image-edit + generation surface, Veo for video, and Imagen for stills. The Google Agent Development Kit (ADK) is the first-party agent framework — Python primary, TypeScript second-class — and the A2A (Agent-to-Agent) protocol is the first-party interop spec for cross-agent communication via Agent Cards. Vertex AI continues to anchor the managed-model + managed-pipeline lane on Google Cloud. Cloud Partner Advantage is the partner program (Sell + Service + Build engagement tracks).
Product map
- Gemini (model family) — Gemini 3 (flagship), Gemini 3 Pro, Gemini 3 Flash, Gemini 3.1 Flash Image (NB2 / Nano Banana 2), Veo (video), Imagen (stills). Frank uses Gemini 3.1 Flash Image daily for multimodal delivery.
- Vertex AI — managed model serving, training, evaluation, deployment. The enterprise lane for Gemini and partner models on Google Cloud.
- Google AI Studio — developer surface for Gemini API.
- Agent Development Kit (ADK) — first-party agent framework. Python primary. Multi-agent orchestration, tool use, deployment to Vertex AI Agent Engine.
- Agent Engine (Vertex AI) — managed runtime for ADK agents.
- A2A protocol (Agent-to-Agent) — open spec for cross-agent communication via Agent Cards. JSON-RPC-style wire format, capability discovery via Agent Card, task lifecycle primitives. Public spec.
- Google Agents CLI — Python CLI + skills bundle for ADK (NOT a separate framework — it ships ADK ergonomics).
- Google Cloud Partner Advantage — partner program. Tracks: Sell, Service, Build. Entry criteria: revenue + technical certifications + customer references (to verify against current Partner Advantage page).
- Open-source artifacts — ADK (Apache 2.0), A2A protocol spec + reference servers (Apache 2.0), Vertex AI SDK (Apache 2.0).
Pricing tiers (May 2026, to verify against current pricing page)
- Free (AI Studio) — free Gemini API tier with daily request limits, no commercial use on free tier.
- Pay-as-you-go (Vertex AI) — per-token pricing. Gemini 3 Pro ~$1.25/$10 per million input/output (to verify); Gemini 3 Flash significantly lower.
- Veo / Imagen — per-generation pricing on Vertex AI.
- Enterprise (Vertex AI + contracted spend) — committed-use discounts via Google Cloud sales.
- Agent Engine — per-agent + per-task compute pricing (to verify).
- Cloud Partner Advantage — no fee for entry; revenue + certification gates determine tier.
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 · 78 lines · 77 tokens per session scan A 4076a00d3719
partner-google is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,032 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
fetch-llm-apps
Regenerate the ranked GitHub LLM applications pool (section/xllmapps.md) with fetchllmapps.py. USE FOR: refreshing the pool linked from applications.md. DO NOT USE FOR: hand-curating entries in applications.md or adding star badges to the generated file.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-prompt-regression-testing
Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.
prompt-refiner
Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.
prompt-modeler
Generate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…