contract-analyzer

contract-analyzer is a skill for Claude Code from Swih/mistral-mcp. It costs 38 tokens per session (727 once invoked), scanned A, original, MIT.

A document-analysis workflow for reading contracts in PDF or scanned form, extracting their clauses, and assigning risk scores. OCR means converting text in scans or images into machine-readable text.

In plain words
What is it for?
Use it when a user provides a contract PDF or public PDF URL and wants its clauses, obligations, important terms, and potential risks extracted in a structured format.
Why use it?
It removes the need to read scanned contract pages manually or connect separate text-recognition and analysis services. It returns structured information about obligations, risks, and key terms.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mistral-mcp plugin — 11 skills shipped together

Good fit Use it when a user provides a contract PDF or public PDF URL and wants its clauses, obligations, important terms, and potential risks extracted in a structured format.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swih/mistral-mcp/contract-analyzer
Install

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.

Any agent
npx skills add Swih/mistral-mcp --skill contract-analyzer
Clone the repo
git clone --depth 1 https://github.com/Swih/mistral-mcp

Made for: Claude Code.

Or install mistral-mcp, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

agentmods badge for contract-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/swih/mistral-mcp/contract-analyzer/github.svg)](https://agentmods.dev/skills/swih/mistral-mcp/contract-analyzer)
Your own site
<a href="https://agentmods.dev/skills/swih/mistral-mcp/contract-analyzer"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/contract-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.

agentmods 80×15 button for contract-analyzer

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00727
Opus 5.5 $0.00015 $0.00291
Sonnet 5.5 $0.00008 $0.00145
Haiku 4.5 $0.00004 $0.00073

Measured 24d ago against content hash a17857a4d4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 24d 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.

claude-plugin/skills/contract-analyzer/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contract analysis

Use process_document in core, metier-docs, or admin. Check mistral://capabilities for the current endpoint and tool availability.

Process the source

Prefer supplied contract text or Markdown:

{
  "source": { "type": "text", "text": "<contract text or Markdown>" },
  "kind": "contract",
  "options": { "cache": "bypass" }
}

For a PDF or image requiring OCR, replace source with { "type": "url", "url": "https://example.com/contract.pdf" } or { "type": "file_id", "fileId": "<existing Mistral file ID>" }.

For local files, use an available converter to obtain text, or upload document bytes with files_upload in admin: filename, content_base64, purpose: "ocr". Its structuredContent.id becomes source.fileId. Do not pass a filesystem path as a URL. If these routes are unavailable, request text or a provider-accessible source.

Text skips OCR and uploads, but contract extraction still sends text to the configured chat endpoint. OCR is optional and depends on account access and quota; no free-processing guarantee applies. The tool uses the configured chat default and has no model argument. Cache bypass affects the local extraction cache only; it does not establish provider retention or data residency.

Review the extraction

Check isError before consuming structuredContent. The contract payload contains:

  • parties[]: name and optional nullable role.
  • clauses[]: heading, text, and optional nullable risk (low, medium, or high).
  • risk_score: a nullable number from 0 to 1.
  • key_dates[]: label and iso.
  • summary: nullable text.
  • ocr_text, extraction_source, ocr_confidence, and page_count for provenance. The last two are null for supplied text.

Present the summary, parties, dates, and clauses with their returned risk labels. Put high-risk clauses first, then medium, low, and unassessed clauses. Ground each concern in the clause text and the user's context. Treat risk_score as a model assessment, not a calibrated legal probability. Do not add a critical level, invented missing-protection fields, or categorical rules about enforceability.

Read the full file on GitHub · 44 lines

Changes

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.

  1. 24d ago Changed · -77 lines · -6 tokens per session a17857a4d4aa
  2. 1mo ago First seen · 121 lines · 44 tokens per session scan A c6573ba44088

Subscribe to this mod's changes

contract-analyzer is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 23d ago), licensed MIT. It adds 38 tokens to every session and 727 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.