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 contract-analyzergit 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/contract-analyzer)<a href="https://agentmods.dev/skills/swih/mistral-mcp/contract-analyzer"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/contract-analyzer.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01016 |
| Opus 5 | $0.00022 | $0.00508 |
| Sonnet 5 | $0.00009 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
contract-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 7d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract analyzer
Extracts and risk-rates contract clauses from a PDF or scanned document using Mistral's native document AI. No third-party OCR dependency.
Profile requirements:
mistral_ocr+mistral_chat— available in core profile (default)files_upload(to upload a local PDF) — requiresMISTRAL_MCP_PROFILE=full- If the user provides a public URL, this skill runs entirely on the core profile
EU data residency: both mistral_ocr and mistral_chat stay within Mistral's EU infrastructure when the API key is an EU-region key.
Steps
Step 1 — Get the document
Ask the user for one of:
- A public URL (direct link to the PDF) — works with core profile
- A local file path → upload with
files_upload(requiresMISTRAL_MCP_PROFILE=full), note the returnedfile_id
Step 2 — OCR the contract
Call mistral_ocr with document_annotation_format: "markdown" for structured extraction:
{
"document": {
"type": "document_url",
"documentUrl": "<URL from step 1>"
},
"document_annotation_format": "markdown"
}
If using a file upload: "type": "document_id", "documentId": "<file_id>" instead.
Concatenate structuredContent.pages[*].markdown across all pages.
Step 3 — Extract structured clauses
Pass the concatenated OCR text to mistral_chat with mistral-large-latest and a json_schema response format:
{
"model": "mistral-large-latest",
"temperature": 0,
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "contract_analysis",
"strict": true,
"schema": {
"type": "object",
"properties": {
"parties": { "type": "array", "items": { "type": "string" } },
"effective_date": { "type": "string" },
"duration": { "type": "string" },
"governing_law": { "type": "string" },
"clauses": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": { "type": "string" },
"summary": { "type": "string" },
"risk_level": {
"type": "string",
"enum": ["low", "medium", "high", "critical"]
},
"risk_reason": { "type": "string" }
},
"required": ["title", "summary", "risk_level", "risk_reason"]
}
},
"overall_risk": {
"type": "string",
"enum": ["low", "medium", "high", "critical"]
},
"missing_protections": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["parties", "clauses", "overall_risk"]
}
}
},
"messages": [
{
"role": "user",
"content": "<OCR text>\n\nExtract all clauses from the contract above. For each clause, provide a title, one-sentence summary, and risk level (low/medium/high/critical) with the reason. Apply these risk escalation rules: termination-for-convenience → at least medium; unlimited liability → critical; IP assignment to other party → high; non-compete > 12 months → high; automatic renewal without notice → medium; governing law in foreign jurisdiction → medium."
}
]
}
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.
- 7d ago First seen · 121 lines · 44 tokens per session scan A c6573ba44088
contract-analyzer is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 9d ago), licensed MIT. It adds 44 tokens to every session and 1,016 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
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
official-doc
Produce a 31C official document (board resolution, formal notice, letter of position, certificate of authority) using the locked corporate template. Authoritative voice, declarative language, reference numbering, and official seal block. Renders to PDF + DOCX. Trigger when the user says "board resolution", "formal…
partnership-doc
Produce a 31C partnership document (MOU, Letter of Intent, or term sheet) using the locked corporate template. Legal-adjacent document defining mutual obligations, governance, territory, exclusivity, and confidentiality between 31 Concept and a counterparty. Renders to PDF + DOCX. Trigger when the user says "MOU"…
procure-quotazioni
Genera in serie procure alle liti (art. 83 c.p.c.) e lettere di quotazione compensi D.M. 55/2014 in DOCX per posizioni di recupero crediti, partendo da un Excel di posizioni o dai dati forniti, con rilevamento della fase processuale (monitorio, esecuzione forzata, opposizione a decreto ingiuntivo). Usa quando l'utente…
kamy
Generate production-ready PDFs (invoices, receipts, contracts, reports, brochures) from Handlebars templates or raw HTML using the Kamy API, and send them for e-signature with optional OTP identity verification, sender-chosen placement, auto-reminders, and a downloadable Certificate of Completion audit trail. Use…