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 arieslee/deepseek-vision-mcp --skill visiongit clone --depth 1 https://github.com/arieslee/deepseek-vision-mcpWrote 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/arieslee/deepseek-vision-mcp/vision)<a href="https://agentmods.dev/skills/arieslee/deepseek-vision-mcp/vision"><img src="https://agentmods.dev/badge/skills/arieslee/deepseek-vision-mcp/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.
<a href="https://agentmods.dev/skills/arieslee/deepseek-vision-mcp/vision"><img src="https://agentmods.dev/badge/skills/arieslee/deepseek-vision-mcp/vision.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 | $0.00041 | $0.00882 |
| Opus 5 | $0.00020 | $0.00441 |
| Sonnet 5 | $0.00008 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
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 8d 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.
What it actually says
Vision — 图片识别 / 分析
识别、分析、查看图片内容时统一走 deepseek-vision-mcp 封装好的 CLI（底层通过 stdio MCP 协议调用其 analyze_image 工具，模型默认 gemini-3.5-flash）。
0. 定位 deepseek-vision-mcp 项目目录（按顺序，不要跳过）
- 若环境变量
VISION_MCP_DIR已设置 → 它就是项目目录。 - 若当前工作目录或其任一父目录下存在
scripts/analyze-image.mjs→ 该目录即项目根。 - 若本 SKILL.md 的路径形如
<项目根>\skills\vision\SKILL.md（skill 安装在项目内）→ 向上两级即为项目根。 - 在常见位置（用户主目录、工具目录等）快速查找
analyze-image.mjs（它位于项目根的scripts/下）；仍找不到就询问用户项目目录在哪，不要自行猜测路径。
令 $MCP = 找到的项目目录。
前提
- 需要
GEMINI_API_KEY：CLI 会自动加载项目.env（$MCP\.env），也可来自环境变量。两者都没有时，提示用户配置（写入$MCP\.env一行GEMINI_API_KEY=你的Key），不要编造。 - 若
$MCP\dist\index.js不存在，先在$MCP目录运行npm run build。
标准流程
-
确认图片来源（让用户提供或从对话中提取）：
- 本地文件：推荐绝对路径，如
C:\photos\a.png - 网络图片：完整 URL，如
https://example.com/a.jpg - base64：
data:image/png;base64,xxxx
- 本地文件：推荐绝对路径，如
-
运行命令：
node "$MCP\scripts\analyze-image.mjs" "<图片路径或URL>" "<可选的识别指令>"常见用法：
- 默认描述：
node "$MCP\scripts\analyze-image.mjs" "C:\photos\a.png" - 定向问题：
node "$MCP\scripts\analyze-image.mjs" "C:\photos\a.png" "图里有哪些文字？逐字输出" - 提取代码（OCR）：
node "$MCP\scripts\analyze-image.mjs" "C:\photos\code.png" "把图片中的代码逐字完整识别出来，保留缩进、空格和标点，不要改写或省略" --max-tokens 8192 - 限制长度：
node "$MCP\scripts\analyze-image.mjs" "C:\photos\a.png" "用一句话总结" --max-tokens 256
- 默认描述：
-
把模型输出作为识别结果按原样呈现给用户，不要加工杜撰。
-
若输出以
[错误]开头：向用户转述错误并给出修复建议（常见：未配置GEMINI_API_KEY、未执行npm run build、图片路径不存在、网络问题；若报模型不存在，提示用户在$MCP\.env中改GEMINI_MODEL）。
规则
- 用户说"识别/分析/看这张图片"但没给路径时，先向用户确认图片位置，不要猜测。
- 识别结果一律以模型输出为准，禁止自己凭空描述图片内容。
- 模型是视觉模型，只处理图片；不要用它做与图片无关的任务。
- 不要泄露或硬编码任何 API Key。
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.
- 8d ago First seen · 50 lines · 41 tokens per session scan A aee3a498967b
vision is a skill published in the GitHub repository arieslee/deepseek-vision-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 41 tokens to every session and 882 once invoked, about $0.0002 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.