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 Swih/mistral-mcp --skill mistral-routergit clone --depth 1 https://github.com/Swih/mistral-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/swih/mistral-mcp/mistral-router)<a href="https://agentmods.dev/skills/swih/mistral-mcp/mistral-router"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/mistral-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/swih/mistral-mcp/mistral-router"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/mistral-router.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 | $0.00049 | $0.01109 |
| Opus 5.5 | $0.00020 | $0.00444 |
| Sonnet 5.5 | $0.00010 | $0.00222 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
mistral-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 28d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mistral router
Read mistral://capabilities to identify the active profile, endpoint, and registered tools. Inspect the selected tool's input schema before calling it. Tool arguments mix snake_case and camelCase; preserve their exact spelling.
The default Mistral Cloud profile, core, exposes six tools:
| Task | Tool | Input shape |
|---|---|---|
| Invoice or contract extraction | process_document |
source, explicit kind, options |
| Text generation, summaries, code review | mistral_chat |
messages: [{role, content: "text"}] |
| Image understanding | mistral_vision |
messages with text and image parts |
| Raw PDF or image OCR | mistral_ocr |
document |
| Code insertion between known boundaries | codestral_fim |
prompt, suffix |
| Audio transcription | voxtral_transcribe |
audio |
For invoices and contracts, prefer process_document with supplied text or Markdown:
{
"source": { "type": "text", "text": "<document text or Markdown>" },
"kind": "invoice",
"options": { "cache": "bypass" }
}
Use kind: "contract" for contracts. OCR sources are { "type": "url", "url": "https://example.com/document.pdf" } or { "type": "file_id", "fileId": "<existing upload ID>" }. Text skips OCR and upload; typed extraction still calls chat. OCR depends on endpoint support and account quota. Do not promise free processing. Use the pdf-invoice-extractor or contract-analyzer skill for result interpretation.
Other common shapes:
- Raw OCR:
document: {type: "document_url", documentUrl: "https://..."}ordocument: {type: "file", fileId: "..."}. - Vision: a user message whose
contentcontains{type: "text", text: "..."}and{type: "image_url", imageUrl: "https://..."}. - Audio:
audio: {type: "file_url", fileUrl: "https://..."}oraudio: {type: "file", fileId: "..."}. Seeaudio-dispatchfor speaker attribution. - Structured chat:
response_format: {type: "json_schema", json_schema: {name: "result", schema: {...}, strict: true}}. The generated JSON is instructuredContent.text; parse and validate it before use.
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.
- 28d ago Changed · -25 lines · -10 tokens per session 4e7e5238569c
- 1mo ago First seen · 88 lines · 59 tokens per session scan A dc00ea8e1401
mistral-router is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 28d ago), licensed MIT. It adds 49 tokens to every session and 1,109 once invoked, about $0.0002 per session on Opus 5.5. 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
gigachat-chat
A chat command that sends a user prompt to GigaChat, an AI text-generation service, through MCP, a way for tools to connect to an agent. It can pass a model and temperature and reports the model and token counts.
model-context
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
build-mcp-server
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.