gemini-3-prompting

gemini-3-prompting is a skill for Claude Code from Vit129/agy-plugin-cc. It costs 26 tokens per session (402 once invoked), scanned A, original, MIT.

Guidance for writing clearer prompts for Antigravity, also called agy, and Gemini 3 models. It covers goals, context, scope, and completion criteria.

In plain words
What is it for?
Use it when forwarding a task to agy, especially for debugging, scoped code changes, or requests that require a specific output format.
Why use it?
It helps turn vague requests into instructions that another coding agent can act on and evaluate more easily.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the agy plugin — 3 skills, 9 commands, 3 hooks shipped together

Good fit Use it when forwarding a task to agy, especially for debugging, scoped code changes, or requests that require a specific output format.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vit129/agy-plugin-cc/gemini-3-prompting
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.

Any agent
npx skills add Vit129/agy-plugin-cc --skill gemini-3-prompting
Clone the repo
git clone --depth 1 https://github.com/Vit129/agy-plugin-cc

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 3 skills, 9 commands, 3 hooks.

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 gemini-3-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/vit129/agy-plugin-cc/gemini-3-prompting/github.svg)](https://agentmods.dev/skills/vit129/agy-plugin-cc/gemini-3-prompting)
Your own site
<a href="https://agentmods.dev/skills/vit129/agy-plugin-cc/gemini-3-prompting"><img src="https://agentmods.dev/badge/skills/vit129/agy-plugin-cc/gemini-3-prompting/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.

agentmods 80×15 button for gemini-3-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/vit129/agy-plugin-cc/gemini-3-prompting"><img src="https://agentmods.dev/badge/skills/vit129/agy-plugin-cc/gemini-3-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00026 $0.00402
Opus 5 $0.00013 $0.00201
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 9d ago against content hash 8afb18cc270c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gemini-3-prompting 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 9d 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.

plugins/agy/skills/gemini-3-prompting/SKILL.md · 39 lines

What it actually says

Gemini 3 Prompting for agy

Use this skill only to tighten a user's request into a better agy prompt before forwarding to task.

Effective prompt structure

  1. State the goal clearly — one sentence describing the desired end state
  2. Provide context — relevant files, error messages, or constraints the agent should know
  3. Specify scope — what agy should and should not touch
  4. State acceptance criteria — how to know when the task is done

Do

  • Be specific about files, functions, or components involved
  • Include error messages verbatim if debugging
  • Mention the tech stack (React, Python, etc.) if not obvious from the repo
  • Ask for a specific output format when the result needs to be consumed downstream

Don't

  • Don't ask agy to "look at everything" — scope it to the relevant area
  • Don't include Claude-side analysis in the prompt — forward the raw task
  • Don't add commentary or padding — agy works best with concise, direct prompts
  • Don't include --background, --continue, or --fresh flags in the prompt text

Prompt antipatterns

Antipattern Better
"Fix the bug somewhere in the auth flow" "Fix the 401 error in src/auth/middleware.js:42 — token is not being verified before route access"
"Improve the code" "Refactor src/utils/parser.js to remove duplicate null checks and add JSDoc for the public functions"
"Look at everything and tell me what's wrong" "Review src/features/aiInvestment/ for stale state patterns and Zustand anti-patterns"
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. 9d ago First seen · 39 lines · 26 tokens per session scan A 8afb18cc270c

Subscribe to this mod's changes

gemini-3-prompting is a skill published in the GitHub repository Vit129/agy-plugin-cc (5 stars, last pushed 17d ago), licensed MIT. It adds 26 tokens to every session and 402 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

gemini-prompting

Internal guidance for composing Gemini and AGY prompts for coding, review, diagnosis, and research tasks inside the Gemini Claude Code plugin.

arcobaleno64/agy-plugin-cc · 31 tokens

agy-prompting

Internal helper — how to tighten a user request into a sharp prompt for the Antigravity CLI (agy / Gemini 3.x with native web search and agentic tools).

MarcosNahuel/antigravity-plugin-cc · 40 tokens

gemini-proxy

A prompt-polishing mode that sends the next set of substantial requests to Gemini, which rewrites them into clearer, more detailed instructions before the agent responds. Gemini improves the wording but does not replace the conversation or perform the task itself.

freestyler-arb/imagine-gemini-for-claude-codex · 120 tokens

ai-product

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when "keywords…

omer-metin/skills-for-antigravity · 74 tokens

few-shot-architect

Professional Few Shot Architect skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 28 tokens

llm-prompt-master

Professional LLM Prompt Master skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.

AtulPurohit/Antigravity-Awesome-Skills · 30 tokens