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 pdf-invoice-extractorgit 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/pdf-invoice-extractor)<a href="https://agentmods.dev/skills/swih/mistral-mcp/pdf-invoice-extractor"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/pdf-invoice-extractor/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/pdf-invoice-extractor"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/pdf-invoice-extractor.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 | $0.00039 | $0.01102 |
| Opus 5 | $0.00019 | $0.00551 |
| Sonnet 5 | $0.00008 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
pdf-invoice-extractor 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF invoice extractor
Extracts structured invoice data from PDFs for accounting reconciliation and ERP import. Uses mistral_ocr for document understanding, then mistral_chat with json_schema for strict field extraction.
Profile requirements:
mistral_ocr+mistral_chat— available in core profile (default)files_upload(to upload a local PDF) — requiresMISTRAL_MCP_PROFILE=fullbatch_create(for bulk invoice processing) — requiresMISTRAL_MCP_PROFILE=full- If the user provides a public URL, this skill runs entirely on the core profile
Works with French, English, and multi-language invoices. Handles scanned PDFs, digital PDFs, and receipts.
Steps
Step 1 — Get the invoice
Ask the user for one of:
- A public URL (direct link to the PDF or image) — works with core profile
- A local file path → upload with
files_upload(requiresMISTRAL_MCP_PROFILE=full), note thefile_id
If the user has multiple invoices, offer to use batch_create (requires full profile) to process them concurrently.
Step 2 — OCR the invoice
Call mistral_ocr:
{
"document": {
"type": "document_url",
"documentUrl": "<URL>"
}
}
Use "type": "document_id", "documentId": "<file_id>" for uploaded files.
Concatenate structuredContent.pages[*].markdown for multi-page invoices.
Step 3 — Extract invoice fields
Pass the OCR text to mistral_chat with response_format: json_schema:
{
"model": "mistral-small-latest",
"temperature": 0,
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "invoice",
"strict": true,
"schema": {
"type": "object",
"properties": {
"invoice_number": { "type": "string" },
"vendor_name": { "type": "string" },
"vendor_address": { "type": "string" },
"vendor_vat_number": { "type": "string" },
"client_name": { "type": "string" },
"client_address": { "type": "string" },
"issue_date": { "type": "string", "description": "ISO 8601 if determinable" },
"due_date": { "type": "string" },
"currency": { "type": "string", "description": "ISO 4217 code, e.g. EUR" },
"line_items": {
"type": "array",
"items": {
"type": "object",
"properties": {
"description": { "type": "string" },
"quantity": { "type": "number" },
"unit_price": { "type": "number" },
"total": { "type": "number" }
},
"required": ["description", "total"]
}
},
"subtotal_ht": { "type": "number" },
"vat_rate": { "type": "number", "description": "As decimal, e.g. 0.20 for 20%" },
"vat_amount": { "type": "number" },
"total_ttc": { "type": "number" },
"payment_terms": { "type": "string" },
"iban": { "type": "string" },
"payment_reference": { "type": "string" }
},
"required": ["vendor_name", "issue_date", "total_ttc", "line_items"]
}
}
},
"messages": [
{
"role": "user",
"content": "<OCR text>\n\nExtract all invoice fields from the document above. Use null for fields not present in the invoice. Convert dates to ISO 8601 format when possible (YYYY-MM-DD). Do not invent values that are not in the document."
}
]
}
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 · 126 lines · 39 tokens per session scan A f3d3217b1cea
pdf-invoice-extractor is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 1,102 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 2026-08-30.
Other skills, from other repositories
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
receipts-to-expenses
Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.
bank-statement-parsing
Guidelines for parsing bank statements using YOLO layout detection + OCR + LLM.
financial-expense-automation
An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.