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 research-pipeline-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/research-pipeline-workflow)<a href="https://agentmods.dev/skills/swih/mistral-mcp/research-pipeline-workflow"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/research-pipeline-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/research-pipeline-workflow"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/research-pipeline-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 | $0.00058 | $0.01372 |
| Opus 5 | $0.00029 | $0.00686 |
| Sonnet 5 | $0.00012 | $0.00274 |
| Haiku 4.5 | $0.00006 | $0.00137 |
Grade A, and why
research-pipeline-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 12d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research pipeline workflow
Orchestrates a deployed Mistral Workflow for multi-step research (literature review, competitive analysis, technical deep-dive). Queries hypotheses at each checkpoint, lets the user validate or amend them, and injects additional sources when needed — all via workflow_interact.
Profile note: workflow_execute, workflow_status, and workflow_interact are available in the core profile (default). No additional profile is required for workflow-only orchestration.
Temporal behavior: the workflow status stays RUNNING even when the pipeline is blocked waiting for hypothesis validation (a wait_for_input() pause in the workflow). Detect this state by querying a status handler — do not wait for a PAUSED status, which does not exist in this API.
Important: handler names are workflow-specific
Ask the user (or consult mistral://workflows) for:
- Query handler for progress: e.g.
"get_progress" - Query handler for hypotheses: e.g.
"get_hypotheses" - Signal handler for hypothesis decisions: e.g.
"hypothesis_decision"
Steps
Step 1 — Define the research mission
Ask the user for:
workflowIdentifier— the deployed research workflow name or IDtopic— the research question (be specific)depth—"shallow"(quick scan),"medium"(balanced),"deep"(comprehensive)output_format—"bullets","report", or"json"- Optional: initial source URLs or
file_ids to seed the pipeline - Handler names (if non-default)
Step 2 — Launch the pipeline
Call workflow_execute:
{
"workflowIdentifier": "<workflow name or ID>",
"input": {
"topic": "<research question>",
"depth": "medium",
"output_format": "report",
"sources": ["<url_or_file_id>"]
}
}
Note structuredContent.execution_id. Confirm: "Research pipeline started — execution ID: <execution_id>."
Step 3 — Poll and query progress
Loop:
- Call
workflow_statuswith{ "executionId": "<execution_id>" } - Check
structuredContent.status:COMPLETED→ go to Step 5FAILED/TIMED_OUT/CANCELED→ surface error and stopRUNNING→ continue
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.
- 12d ago First seen · 186 lines · 58 tokens per session scan A d862826d4868
research-pipeline-workflow is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,372 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
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.
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.
before-spend
Use this before any purchase, subscription, money transfer, or API credit top-up. Call sanctionauthorize first; never proceed when it returns false; if status is escalated, wait and follow handle-escalation.
handle-escalation
Use this when any sanctionauthorize, sanctionauthorizetool, sanctionauthorizecapability, or sanctionauthorizeprovision call returns status escalated. Poll sanctioncheckauthorization with requestid; on approved, retry the original call with grantid; on denied, stop.
wallet-status
Use this at the start of long or expensive agentic work, or after a budget error from authorize or logtokens. Call sanctionwalletstatus to check spend and token headroom before continuing.