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-review-workflowgit 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-review-workflow)<a href="https://agentmods.dev/skills/swih/mistral-mcp/contract-review-workflow"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/contract-review-workflow/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/contract-review-workflow"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/contract-review-workflow.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 | $0.00061 | $0.01111 |
| Opus 5 | $0.00030 | $0.00556 |
| Sonnet 5 | $0.00012 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
contract-review-workflow 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract review workflow
Orchestrates a deployed Mistral Workflow for contract review. Detects wait_for_input() human-in-the-loop checkpoints by querying a status handler, presents findings to the user, and resumes the workflow with their decision via workflow_interact(action: "signal").
Profile note: workflow_execute, workflow_status, and workflow_interact are available in the core profile (default). files_upload (for local PDF upload) requires MISTRAL_MCP_PROFILE=full.
Why workflows vs direct API: the workflow runs durably on Mistral's infrastructure — it persists across restarts, handles retries, and can run multi-step analysis (OCR → clause extraction → legal DB lookup → risk scoring) without keeping a connection open.
Important: handler names are workflow-specific
The name field in workflow_interact calls (signal handler, query handler) is defined by the deployed workflow. Ask the user for:
- The query handler name that exposes checkpoint state (e.g.
"get_checkpoint") - The signal handler name that receives approval decisions (e.g.
"human_approval")
Defaults used in the examples below — replace with the actual names from the workflow.
Steps
Step 1 — Collect inputs
Ask the user for:
workflowIdentifier— the deployed workflow name or ID (visible inmistral://workflows)- The contract document: a
file_id(fromfiles_upload, requiresfullprofile) or a public URL - Optional:
review_type(e.g."vendor","employment","partnership") andlanguage("fr"or"en") - The query handler name and signal handler name (if not the defaults)
Step 2 — Start the workflow
Call workflow_execute:
{
"workflowIdentifier": "<workflow name or ID>",
"input": {
"document_id": "<file_id, or omit if using document_url>",
"document_url": "<URL, or omit if using file_id>",
"review_type": "<vendor|employment|partnership|other>",
"language": "fr"
}
}
Note the structuredContent.execution_id. Confirm to the user: "Workflow started — execution ID: <execution_id>."
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 · 125 lines · 61 tokens per session scan A 75dfcfa11920
contract-review-workflow is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,111 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 2026-08-30.
Other skills, from other repositories
output-meta-post-flight
Post-flight validation for Output SDK workflow operations. Systematic verification of step completion, convention compliance, quality validation, and deliverable verification.
fluent-development
This skill should be used when the user asks to "build a fluent app", "create a servicenow app in typescript", or mentions "servicenow sdk", "now-sdk", "fluent", "scoped app as code", or "pro-code development" — or when the working directory contains a now.config.json or .now.ts files.
grc-compliance
Build ServiceNow GRC — sncompliancepolicy lifecycle, sncompliancecontrol tests, snriskrisk assessment with inherent/residual scoring, audit engagements, and findings remediation.
affiliation-map
A company-affiliation map built from Russian business registry records. It links founders, managers, related companies, registration details, and bankruptcy information.
prepayment-check
A prepayment check for a company or other business partner using its tax identification number. It examines bankruptcy, court cases, licences, registration status, and the person signing the contract.
bulk-campaign
Send a bulk SMS campaign in Turkey — balance check, opt-out filter, İYS consent, delivery report.