Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WALKERKILLER/Look-Tongji-Notesnpx agentmods add skills/walkerkiller/look-tongji-notes/vision-supportWrote 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/walkerkiller/look-tongji-notes/vision-support)<a href="https://agentmods.dev/skills/walkerkiller/look-tongji-notes/vision-support"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/vision-support/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/walkerkiller/look-tongji-notes/vision-support"><img src="https://agentmods.dev/badge/skills/walkerkiller/look-tongji-notes/vision-support.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 | $0.00225 | $0.01355 |
| Opus 5 | $0.00112 | $0.00678 |
| Sonnet 5 | $0.00045 | $0.00271 |
| Haiku 4.5 | $0.00022 | $0.00136 |
Grade A, and why
vision-support 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- vision-support — 100% identical, 218 lines differ
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Support — 非多模态模型的图片识别桥接
铁律：本技能配置的所有模型仅用于图片内容识别，绝不参与主逻辑推理。 这些模型不会代替主模型做任何决策、分析或编码，它们只负责"看"图片然后把看到的内容用文字描述出来。
什么时候使用此技能
- 用户在对话中附带了图片，但当前模型不支持图片理解
- 用户提到截图/图片/界面/设计："看看这个截图"、"界面有问题"、"这个设计稿"
- 用户描述了一个视觉问题但说不清楚："网页显示不对"、"布局乱了"
- agent 在工作中遇到图片文件（PNG/JPG/WebP 等）
- 通过指令
/vision或/skill:vision-support手动触发
首次使用 — 一键初始化
node SKILL_DIR/scripts/vision.mjs init
交互式引导，只需三步：
- 选 Provider — 从预置的主流平台列表中选择
- 填密钥 — 输入 API Key（或环境变量名）
- 选模型 — 自动从 API 拉取可用模型列表供选择（如拉取失败则显示推荐列表）
支持的平台覆盖国内外主流：
| 分类 | 平台 |
|---|---|
| 国际 | OpenAI、Google Gemini、Anthropic Claude、DeepSeek、Groq、Mistral、xAI (Grok)、OpenRouter、Fireworks AI |
| 国内 | 通义千问 (Qwen VL)、智谱 GLM (GLM-4V)、Moonshot (Kimi)、阶跃星辰 (Step)、MiniMax、SiliconFlow (硅基流动)、小米 MiMo |
| 本地 | Ollama、LM Studio |
| 自定义 | 任何 OpenAI 兼容的第三方平台（自填 baseUrl） |
添加备用模型
node SKILL_DIR/scripts/vision.mjs config add
同样的交互式引导，添加的模型作为 fallback 回退。主模型失败后自动尝试。
所有配置命令
# 交互式
node SKILL_DIR/scripts/vision.mjs init # 初始化主模型
node SKILL_DIR/scripts/vision.mjs config add # 添加 fallback
node SKILL_DIR/scripts/vision.mjs config edit [name] # 编辑模型
# 快捷命令
node SKILL_DIR/scripts/vision.mjs config list # 列出所有模型
node SKILL_DIR/scripts/vision.mjs config primary [name] # 设置主模型
node SKILL_DIR/scripts/vision.mjs config remove <name> # 删除模型
node SKILL_DIR/scripts/vision.mjs config set-key <name> <key> # 设置密钥
node SKILL_DIR/scripts/vision.mjs config set-url <name> <url> # 设置 API 地址
node SKILL_DIR/scripts/vision.mjs config test [name] # 测试连通性
使用方法 — 识别图片
单张
node SKILL_DIR/scripts/vision.mjs ./screenshot.png
node SKILL_DIR/scripts/vision.mjs ./ui.png "这个界面的布局有什么问题？"
node SKILL_DIR/scripts/vision.mjs "https://example.com/img.png" "描述这张图片"
多张
node SKILL_DIR/scripts/vision.mjs img1.png img2.png "对比这两张图的差异"
node SKILL_DIR/scripts/vision.mjs ./screenshots/*.png "分析这些界面截图"
node SKILL_DIR/scripts/vision.mjs ./local.png https://example.com/remote.jpg "描述这两张"
What ships with it
17 files 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.
- AGENTS.md 4.1 KB
- bin/AGENTS.md 2.0 KB
- bin/cli.mjs 2.0 KB runs code
- bin/postinstall.mjs 2.0 KB runs code
- config.example.json 1.7 KB
- images/AGENTS.md 1.4 KB
- images/usage-recognize.png 170 KB
- images/usage-result.png 121 KB
- install.mjs 8.8 KB runs code
- install.sh 4.1 KB runs code
- package.json 1.0 KB
- README.md 4.6 KB
- README.zh.md 5.2 KB
- references/AGENTS.md 1.7 KB
- references/supported-models.md 4.5 KB
- scripts/AGENTS.md 2.5 KB
- scripts/vision.mjs 50 KB runs code
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.
- 10d ago First seen · 110 lines · 225 tokens per session scan A 854cc2087df9
vision-support is a skill published in the GitHub repository WALKERKILLER/Look-Tongji-Notes (41 stars, last pushed 2mo ago), licensed MIT. It adds 225 tokens to every session and 1,355 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
stable-diffusion
Text-to-image generation, inpainting, and img2img.
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…
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.
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.
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.
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.