vision

vision is a skill for Claude Code, Codex from GOU-GEE/deepseek-vision. It costs 92 tokens per session (2,028 once invoked), scanned A, original, MIT.

A picture-understanding skill that sends images to a separate vision model and returns descriptions or extracted text.

In plain words
What is it for?
It is for describing scenes, reading text from screenshots, finding visual errors, identifying objects, and comparing images.
Why use it?
It helps a text-only coding agent handle image files, URLs, clipboard images, and image attachments without guessing what they contain.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

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.

agentmods
npx agentmods add skills/gou-gee/deepseek-vision/vision
Any agent
npx skills add GOU-GEE/deepseek-vision --skill vision
Clone the repo
git clone --depth 1 https://github.com/GOU-GEE/deepseek-vision

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 vision

README.md
[![agentmods](https://agentmods.dev/badge/skills/gou-gee/deepseek-vision/vision.svg)](https://agentmods.dev/skills/gou-gee/deepseek-vision/vision)
Your own site
<a href="https://agentmods.dev/skills/gou-gee/deepseek-vision/vision"><img src="https://agentmods.dev/badge/skills/gou-gee/deepseek-vision/vision.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00092 $0.02028
Opus 5 $0.00046 $0.01014
Sonnet 5 $0.00018 $0.00406
Haiku 4.5 $0.00009 $0.00203

Measured 5d ago against content hash a2d2cb0724c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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.

plugins/dsh-plugin-deepseek-vision/skills/vision/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision Skill — 图片理解

DeepSeek 主模型是纯文本模型,无法直接“看”图片。本 Skill 通过 MCP 工具 (analyze_image / analyze_clipboard / compare_images)把图片交给第三方 OpenAI 兼容视觉模型(如智谱 GLM-4.6V、硅基流动 Qwen2.5-VL、通义千问 qwen-vl-plus),再把识别文本返回给主模型。

触发条件

满足以下任一条件时,必须调用视觉工具,而不是假装能看到图片:

  1. 用户输入中包含本地图片路径,例如 ./screenshot.png~/Desktop/photo.jpg、 或绝对路径 /Users/me/1.png
  2. 用户输入中包含图片 URL,例如 https://example.com/foo.png
  3. 用户输入中包含 base64 图片数据(可能带 data:image/...;base64, 前缀)。
  4. 用户提到剪贴板:说「看看剪贴板里有什么」「我截图了」「刚复制的图片」 ——调用 analyze_clipboard
  5. 用户要求对比多张图片:说「对比这两张图」「这两张有什么区别」——调用 compare_images,把各图片路径/URL 放进 images 数组。
  6. 用户明确要求识别 / 理解 / 描述图片内容,例如:
    • “帮我看看这张图里有什么错误”
    • “提取这张图片里的文字”
    • “这张截图显示了什么报错信息?”
    • “描述一下这张照片的场景”
  7. 用户上传了图片但主模型无法直接处理(例如在 DeepSeek Harness / Codex 中以附件形式传入),此时同样应调用工具。

必须执行的操作

  1. 先确认工具可用:调用前确认当前会话工具列表里有对应的视觉工具。 若没有,说明 MCP 未加载,提示用户检查配置并重启,不要硬编造结果

  2. 判断图片输入形式:本地路径 / URL / base64 / 剪贴板,选择对应工具:

    • 单张图片 → analyze_image(image=..., prompt=?, task=?)
    • 剪贴板图片 → analyze_clipboard(prompt=?, task=?)
    • 多图对比 → compare_images(images=[...], prompt=?)
  3. 选择 task(预置任务,无需自己拼 prompt;也可用 prompt 自定义指令, prompt 优先级更高):

    task 用途 效果
    describe(默认) 通用描述 详细描述图片内容
    ocr 提取文字 逐字提取,保留排版换行,不做评论
    describe_ui UI 截图 布局 / 组件 / 可见文字 / 状态
    diagnose_error 报错截图 错误信息 / 原因 / 修复步骤
    understand_diagram 流程图/架构图 类型 / 组成 / 关系 / 目的
    analyze_chart 数据图表 类型 / 坐标轴 / 趋势 / 洞察
    code_from_screenshot 代码截图 语言 / 可编辑代码块

    自定义 prompt 示例:

    • 提取文字:请提取图片中的所有文字,保持原有排版顺序。
    • 找错误:请识别图片中的错误信息,并说明可能的原因。
    • 描述场景:请描述图片中的场景、人物、物体和环境细节。
    • 其他需求:把用户的原始诉求改写为对视觉模型的清晰指令。
  4. 调用 MCP 工具:

    analyze_image(image="<路径或URL或base64>", task="ocr")
    analyze_clipboard(task="diagnose_error")
    compare_images(images=["./a.png", "https://example.com/b.jpg"], prompt="对比两者差异")
    
  5. 工具返回 JSON:{"success": true/false, "result": "...", "model": "...", "provider": "...", "fallback_used": true/false, "attempts": 0, "usage": {...}, "cached": true/false}

    • success: true:把 result 中的识别文本直接作为回答呈现给用户, 可适当补充说明(来自哪个模型);cached: true 只表示命中同会话缓存, 内容仍可正常使用。
    • success: false:把 error 字段(如 IMAGE_LOAD_FAILEDVISION_API_ERRORCONFIG_ERRORCLIPBOARD_ERROR)和 result 中的 错误信息转告用户,并给出修复建议(检查路径/URL 是否有效、API Key 是否 配置、图片是否超限、剪贴板是否有图等)。

Read the full file on GitHub · 146 lines

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. 5d ago First seen · 146 lines · 92 tokens per session scan A a2d2cb0724c1

Subscribe to this mod's changes

vision is a skill published in the GitHub repository GOU-GEE/deepseek-vision (5 stars, last pushed 10d ago), licensed MIT. It adds 92 tokens to every session and 2,028 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.

Related

Other skills, from other repositories

submit-dsh-plugin

验证并提交 DeepSeek Harness 插件到 imsai-sh/awesome-deepseek-harness-plugins 社区目录。适用于插件作者要求收录、发布或提交自己的插件,创建目录 JSON,修复目录提交 PR,或者发起合规 PR。检查公开仓库、dsh-plugin topic、dsh.bundle.patch、作者测试证据、双语元数据和单文件差异,并在获得授权后执行 fork、push 和创建 PR。.

imsai-sh/awesome-deepseek-harness-plugins · 103 tokens

dsh-plugin-guide

Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…

PerryLink/dsh-plugin-guide · 76 tokens

ito-compute

Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô…

gongyijie85/dsh-ecc · 90 tokens

ito-inference

Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted…

gongyijie85/dsh-ecc · 80 tokens

ito-training

Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training…

gongyijie85/dsh-ecc · 68 tokens

dsh-plugin-schemes

开发任何 deepseek-harness 插件前,先按本规范选对形态,再动手。.

JasperGuWP/dsh-plugin-schemes · 128 tokens