gemini-agentic-vision

gemini-agentic-vision is a skill for Claude Code, Codex from joonlab/joonlab-claudecode-setting-for-share. It costs 173 tokens per session (1,383 once invoked), scanned A, original, MIT.

An image-analysis workflow that combines Gemini's vision model with extended reasoning and code execution. It can inspect an image and then write and run code to produce the requested result.

In plain words
What is it for?
Use it to analyze, crop, transform, detect objects in, or extract data from images, including tasks that need generated code.
Why use it?
It helps with image tasks that need more precise analysis or generated processing code than basic image understanding provides. The workflow can move from inspection to a saved output.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to analyze, crop, transform, detect objects in, or extract data from images, including tasks that need generated code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision
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 joonlab/joonlab-claudecode-setting-for-share --skill gemini-agentic-vision
Clone the repo
git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-share

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 gemini-agentic-vision

README.md
[![agentmods](https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision/github.svg)](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision)
Your own site
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision/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-agentic-vision

Your own site · 80×15
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-agentic-vision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 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 $0.00173 $0.01383
Opus 5 $0.00086 $0.00691
Sonnet 5 $0.00035 $0.00277
Haiku 4.5 $0.00017 $0.00138

Measured 9d ago against content hash 258293542c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gemini-agentic-vision 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gemini_vision.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude/skills/gemini-agentic-vision/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Agentic Vision

Gemini API의 Vision + Extended Thinking + Code Execution을 조합하여, 이미지를 입력받고 자율적으로 분석→코드 작성→실행→결과물 생성을 수행하는 스킬.

환경 요구사항

  • Python 패키지: google-genai (설치됨)
  • API 키: GEMINI_PAID_API_KEY 환경변수 (.zshrc에 설정됨)
  • 모델: gemini-3-flash-preview

사용법

기본 실행

source ~/.zshrc && python3 ~/.claude/skills/gemini-agentic-vision/scripts/gemini_vision.py \
  "<이미지_경로>" \
  "<프롬프트>"

출력 디렉토리 지정

source ~/.zshrc && python3 ~/.claude/skills/gemini-agentic-vision/scripts/gemini_vision.py \
  "<이미지_경로>" \
  "<프롬프트>" \
  --output-dir "<출력_디렉토리>"

생성된 코드 저장

source ~/.zshrc && python3 ~/.claude/skills/gemini-agentic-vision/scripts/gemini_vision.py \
  "<이미지_경로>" \
  "<프롬프트>" \
  --save-code "/tmp/generated.py"

JSON 결과 출력 (파싱용)

source ~/.zshrc && python3 ~/.claude/skills/gemini-agentic-vision/scripts/gemini_vision.py \
  "<이미지_경로>" \
  "<프롬프트>" \
  --json

중요: 반드시 source ~/.zshrc &&를 앞에 붙여 GEMINI_PAID_API_KEY 환경변수를 로드한다.

워크플로우

Phase 1: 프롬프트 구성

사용자의 요청을 Gemini에 최적화된 프롬프트로 변환한다:

사용자 요청 최적 프롬프트
"동물만 잘라내줘" "Detect all animals, crop each one, and save as separate images"
"데이터 추출해줘" "Extract all data from this chart and output as CSV"
"빨간 박스로 표시해줘" "Draw red bounding boxes around all buttons and save the annotated image"
"개수 세줘" "Count all items, number each one on the image, and report total"
"비교해줘" "Analyze this image and describe key visual elements in detail"

프롬프트는 영어로 작성하면 Gemini의 코드 실행 정확도가 높아진다.

Phase 2: 스크립트 실행

scripts/gemini_vision.py를 Bash로 실행한다. 스크립트가 자동으로:

  1. 이미지를 base64로 인코딩하여 Gemini API에 전달
  2. Gemini가 이미지를 분석하고 사고 과정(Thinking)을 노출
  3. 필요시 Python 코드를 자율 생성하고 서버에서 실행
  4. 실행 결과(텍스트, 이미지, 데이터)를 반환

Phase 3: 결과 확인

스크립트 출력에서:

  • 🖼️ [Output Image] 뒤의 경로 → 생성된 이미지 파일
  • 📝 뒤의 텍스트 → Gemini의 분석 결과
  • 💻 [Code] → 실행된 코드 (참고/재사용 가능)
  • ✅ [Result] → 코드 실행 출력

출력된 이미지 파일은 Read 도구로 사용자에게 보여준다.

Phase 4: 후속 처리

Gemini 결과를 바탕으로 추가 작업이 필요하면:

  • 생성된 코드를 로컬에서 수정·재실행
  • 출력 이미지를 추가 가공
  • 추출된 데이터를 다른 형식으로 변환

Read the full file on GitHub · 141 lines

Files

What ships with it

1 file 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.

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 · 141 lines · 173 tokens per session scan A 258293542c20

Subscribe to this mod's changes

gemini-agentic-vision is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 173 tokens to every session and 1,383 once invoked, about $0.0009 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

stable-diffusion

Text-to-image generation, inpainting, and img2img.

NousResearch/hermes-agent · 18 tokens

huggingface-lora-space-builder

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers…

huggingface/skills · 187 tokens

seedance-antislop

This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.

Emily2040/seedance-2.0 · 48 tokens

seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.

Emily2040/seedance-2.0 · 57 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

seedance-vocab-zh

This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.

Emily2040/seedance-2.0 · 55 tokens