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 shen-shanshan/vllm-dev-skills --skill vllm-multimodal-open-issue-analyzergit clone --depth 1 https://github.com/shen-shanshan/vllm-dev-skillsWrote 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/shen-shanshan/vllm-dev-skills/vllm-multimodal-open-issue-analyzer)<a href="https://agentmods.dev/skills/shen-shanshan/vllm-dev-skills/vllm-multimodal-open-issue-analyzer"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-multimodal-open-issue-analyzer/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/shen-shanshan/vllm-dev-skills/vllm-multimodal-open-issue-analyzer"><img src="https://agentmods.dev/badge/skills/shen-shanshan/vllm-dev-skills/vllm-multimodal-open-issue-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00187 | $0.00908 |
| Opus 5 | $0.00093 | $0.00454 |
| Sonnet 5 | $0.00037 | $0.00182 |
| Haiku 4.5 | $0.00019 | $0.00091 |
Grade A, and why
vllm-multimodal-open-issue-analyzer 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 11d 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
vllm 多模态 Open Issues 分析
工作流
- 运行
scripts/fetch_multimodal_issues.py - 脚本自动抓取、去重、分类，生成 Markdown 报告
- 报告默认保存至
<skill_root>/outputs/vllm_multimodal_issues_<timestamp>.md - 告知用户报告路径及 issue 总数
运行脚本
python3 scripts/fetch_multimodal_issues.py
可选参数：
| 参数 | 说明 | 示例 |
|---|---|---|
--token |
GitHub token（有 gh CLI 时不需要） | --token ghp_xxx |
--output-dir |
自定义报告输出目录 | --output-dir /tmp/reports |
--keywords |
追加额外关键词（逗号分隔） | --keywords "DeepSeek-VL,Kimi" |
--stdout |
输出到终端而非文件 | --stdout |
搜索关键词覆盖范围
通用术语: multimodal, multi-modal, VLM, vision language, image input
VL 模型: Qwen-VL/2/2.5, LLaVA, InternVL, MiniCPM-V, Phi-3/4-vision, PaliGemma, Florence, Pixtral, CogVLM, LLaMA-Vision, Idefics
Omni/音频: Qwen-Omni/2/2.5, audio, whisper, speech
视频: video understanding, video input, temporal
特性关键词: ViT, visual encoder, cuda graph, EPD, prefix caching, image token, image patch
问题类型分类逻辑
脚本对每个 issue 的标题、label、body（前 500 字符）做关键词匹配，归入以下类别（一个 issue 可属于多个类别）：
- Bug / 错误报告
- Feature Request / 功能请求
- Performance / 性能问题
- CUDA Graph / 计算图
- EPD / 编解码分离
- Prefix Caching / 前缀缓存
- ViT / 视觉编码器
- Video Multimodal / 视频多模态
- Audio / Speech / 音频语音
- VL Model: Qwen-VL系列 / Qwen-Omni系列 / LLaVA系列 / InternVL系列 / 其他模型
- Image Token / 输入处理
- Compatibility / 兼容性
- Documentation / 文档
- 其他 / Other
报告结构
生成的 Markdown 报告包含三部分：
- Issue 总览（表格）：编号、标题、作者、创建日期、Labels
- 按问题类型分类：每个类别列出匹配 issue（含链接、创建日期）
- 分类统计：各类别 issue 数量汇总表
认证说明
- 有 gh CLI（推荐）：自动使用，无速率限制
- 无 gh CLI，有 token：使用
--token - 无认证：搜索批次间自动等待 6 秒，避免触发 GitHub 10 req/min 限制
What ships with it
2 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.
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.
- 11d ago First seen · 74 lines · 187 tokens per session scan A 348b0357936f
vllm-multimodal-open-issue-analyzer is a skill published in the GitHub repository shen-shanshan/vllm-dev-skills (17 stars, last pushed 2d ago), licensed Apache-2.0. It adds 187 tokens to every session and 908 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 2026-08-30.
Other skills, from other repositories
serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
human-agent-trust-exploit-detection
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.