agentmods.dev

research

research is a skill for Claude Code from krishagel/geoffrey. It costs 13 tokens per session (2,605 once invoked), scanned A, original, MIT.

A research workflow that breaks a question into smaller searches, runs research with multiple language-model agents, and combines the results with citations.

In plain words
What is it for?
Use it for current, detailed research across articles, videos, podcasts, forums, and other sources, with cited claims and noted disagreements.
Why use it?
It helps handle broad topics by exploring more sources and organizing the findings instead of relying on one search or one answer.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bun docs/create_doc.js <account> --title "<Research Topic>" --folder Research --content "<markdown>".

Part of the geoffrey plugin — 33 skills, 2 commands, 4 hooks shipped together

not rated 7repo 7mo ago A scan 13 tokens original MIT

Good fit Use it for current, detailed research across articles, videos, podcasts, forums, and other sources, with cited claims and noted disagreements.

Compare 6 skills from other repositories ↓
View source ↗ krishagel/geoffrey
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/krishagel/geoffrey
agentmods
npx agentmods add skills/krishagel/geoffrey/research

Made for: Claude Code.

Or install geoffrey, the plugin that ships this one along with the rest of its 33 skills, 2 commands, 4 hooks.

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 research

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/krishagel/geoffrey/research"><img src="https://agentmods.dev/badge/skills/krishagel/geoffrey/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,605 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.
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 $0.00013 $0.02605
Opus 5.5 $0.00005 $0.01042
Sonnet 5.5 $0.00003 $0.00521
Haiku 4.5 $0.00001 $0.00261

Measured 2mo ago against content hash 6419fbbeabcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/context-loader.js, scripts/orchestrator.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • research — 100% identical, 0 lines differ
skills/research/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Skill

Discovery-driven, exhaustive research using parallel LLM agents for comprehensive, current information gathering.

Core Principles

CRITICAL: These principles define how research works.

1. Discovery-Driven, Not List-Driven

  • Find the BEST sources, not just known sources
  • Don't limit to predefined source lists
  • The internet is huge - explore it
  • Value is in finding what user doesn't already know

2. Context-Aware

  • Load user's domain context from preferences
  • Research is RELEVANT to their specific situation
  • But context doesn't limit WHERE you search

3. Exhaustive

  • No time limits - can take 30 minutes to 3 hours
  • Don't stop at first page of results
  • Keep going until topic is exhausted
  • Follow promising links deeper

4. Multimedia

  • Not just text articles
  • Videos (YouTube), TikTok, podcasts
  • Real user experiences from forums

5. Highly Cited

  • Every claim must have a citation
  • Multiple sources for important claims
  • Note when sources conflict

6. Clarifying Questions First

Before diving into research, ask deep, thought-provoking questions to understand:

  • What's the actual goal? (not just the surface request)
  • What constraints exist? (budget, time, preferences)
  • What would success look like?
  • What have they already tried or considered?
  • Are there hidden requirements?

Example: "Research Japan ski trip" should prompt:

  • "What skill level are you and Carrie? Blue runs, black diamonds?"
  • "Is après-ski culture important, or pure skiing focus?"
  • "Do you need English-friendly areas, or comfortable with Japanese-only?"
  • "Any specific dates that are fixed vs flexible?"
  • "Besides skiing, anything else you want to do (onsen, food tours)?"

Domain Context Loading

Research automatically loads relevant context from preferences based on detected domain.

How It Works

  1. Detect domain from query (travel, shopping, work, etc.)
  2. Load research_domains.[domain] from preferences
  3. Load referenced context keys
  4. Fetch any dynamic data (point balances, etc.)
  5. Apply domain-specific research patterns

Read the full file on GitHub · 365 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 365 lines · 13 tokens per session scan A 6419fbbeabcc

Subscribe to this mod's changes

research is a skill published in the GitHub repository krishagel/geoffrey (7 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 2,605 once invoked, about $0.0001 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 2026-08-31.

Research
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens