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 wotonger/vision-router-mcp --skill vision-routergit clone --depth 1 https://github.com/wotonger/vision-router-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/wotonger/vision-router-mcp/vision-router)<a href="https://agentmods.dev/skills/wotonger/vision-router-mcp/vision-router"><img src="https://agentmods.dev/badge/skills/wotonger/vision-router-mcp/vision-router/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/wotonger/vision-router-mcp/vision-router"><img src="https://agentmods.dev/badge/skills/wotonger/vision-router-mcp/vision-router.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 | $0.00069 | $0.01036 |
| Opus 5 | $0.00034 | $0.00518 |
| Sonnet 5 | $0.00014 | $0.00207 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
vision-router 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Router Skill
Use the vision-router MCP tools when the user provides an image or asks a
question that depends on image content, and the current runtime cannot
inspect images natively.
Core rules
- Never claim you directly saw an image unless the current runtime explicitly supports image input.
- Use
vision_analyzeto obtain visual information. - Never send API keys through tool arguments, chat messages, generated commands, logs, or responses.
- The system has no default vision model. Do not silently pick one.
- Do not silently switch providers — that may send the image to a different third party.
- Treat vision results as potentially fallible; never invent unreadable text or hidden content.
Provider selection
The system has no built-in default visual model.
When the user explicitly names a configured provider:
- Call
vision_list_models. - Match the requested provider id.
- Confirm it is enabled and configured.
- Call
vision_analyzewith that provider id.
When the user has not selected a provider:
- Call
vision_list_models. - Present the enabled and configured providers with their recommended use cases and cost notes.
- Ask the user to choose one.
- Do not analyze the image until the user selects a provider — even if only one provider is configured.
Suggested descriptions:
- Gemini Flash: general images, screenshots, charts, documents; may have a free tier.
- Qwen VL / DashScope: Chinese OCR, Chinese documents, screenshots, tables, product images.
- SiliconFlow: hosted open-source vision models, low-cost experiments.
- OpenRouter: model comparison, experimental free models; availability may change.
- Custom OpenAI-compatible: private gateways or another compatible provider.
Never promise that a cloud model is permanently free.
Analysis mode
Select the narrowest suitable mode:
general: scenes, people, objects, actions, general image questions.ocr: extracting visible text with minimal interpretation.document: contracts, invoices, receipts, forms, reports, tables.screenshot: websites, applications, terminals, error messages, UI state.
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 · 157 lines · 69 tokens per session scan A 76ce60856c20
vision-router is a skill published in the GitHub repository wotonger/vision-router-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,036 once invoked, about $0.0003 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.