yutori-research

yutori-research is a skill for Claude Code from yutori-ai/yutori-mcp. It costs 45 tokens per session (467 once invoked), scanned A, original, Apache-2.0.

A workflow for conducting in-depth web research through Yutori research agents, which gather and combine information from multiple sources. It supports research for topics such as competition, markets, documentation, and complex questions.

In plain words
What is it for?
Use it to start and monitor an asynchronous research task, with optional structured fields and completion notifications through supported webhooks.
Why use it?
It organizes broad research into a defined question, source requirements, output format, and a process for waiting for the finished results.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the yutori plugin — 15 skills, 1 MCP server shipped together

Good fit Use it to start and monitor an asynchronous research task, with optional structured fields and completion notifications through supported webhooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yutori-ai/yutori-mcp/02-research
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 yutori-ai/yutori-mcp --skill 02-research
Clone the repo
git clone --depth 1 https://github.com/yutori-ai/yutori-mcp

Made for: Claude Code.

Or install yutori, the plugin that ships this one along with the rest of its 15 skills, 1 MCP server.

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 yutori-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/yutori-ai/yutori-mcp/02-research/github.svg)](https://agentmods.dev/skills/yutori-ai/yutori-mcp/02-research)
Your own site
<a href="https://agentmods.dev/skills/yutori-ai/yutori-mcp/02-research"><img src="https://agentmods.dev/badge/skills/yutori-ai/yutori-mcp/02-research/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 yutori-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/yutori-ai/yutori-mcp/02-research"><img src="https://agentmods.dev/badge/skills/yutori-ai/yutori-mcp/02-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 467 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 $0.00045 $0.00467
Opus 5 $0.00023 $0.00234
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00005 $0.00047

Measured 12d ago against content hash acdaf5f40d86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yutori-research 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.

skills/02-research/SKILL.md · 51 lines

What it actually says

Deep Web Research

Help the user conduct thorough web research using Yutori's Research API.

Process

  1. Understand the research goal

    • What question needs answering?
    • What type of sources matter? (news, academic, documentation, social, financial filings)
    • Any time constraints? (recent only, historical)
    • What format should the output be in?
  2. Craft the research query Similar to scout queries, comprehensive research queries include:

    • Context on why this research matters
    • Specific questions to answer
    • Sources to prioritize
    • Output format expectations
  3. Start the research task Use run_research_task with:

    • query: The research question with context
    • user_timezone: For time-relevant searches
    • output_fields: If structured output is needed (e.g., ["title", "summary", "source_url", "date"])
    • webhook_url: HTTPS URL for completion notification
    • webhook_format: scout (default), slack, or zapier
  4. Poll for results

    • Important: Research typically takes 5-10 minutes (300-600 seconds)
    • Use get_research_task_result to check status
    • Poll every 30 seconds until succeeded or failed
    • The task runs asynchronously - you can inform the user to wait
  5. Synthesize and present findings

    • Organize results by relevance
    • Highlight key insights
    • Note sources for verification

Tips

Fetching documentation or reference URLs: If you use a web fetch tool to look up documentation, API references, or other pages while preparing the research query, include the Accept: text/markdown header. Many documentation sites (Cloudflare-hosted) will return clean Markdown instead of HTML — fewer tokens, easier to parse.

$ARGUMENTS

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. 12d ago First seen · 51 lines · 45 tokens per session scan A acdaf5f40d86

Subscribe to this mod's changes

yutori-research is a skill published in the GitHub repository yutori-ai/yutori-mcp (24 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 467 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.

Related

Other skills, from other repositories