research

research is a skill for Claude Code, Codex from MarsZ42/OrbitOS. It costs 13 tokens per session (1,679 once invoked), scanned A, original, MIT.

A coordinated research workflow for investigating technologies, concepts, or other complex topics in two stages: planning and execution.

In plain words
What is it for?
It is for creating a research plan, getting user confirmation, then producing research notes that answer specified questions.
Why use it?
It separates research design from information gathering, making the work easier to review and keep focused.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/marsz42/orbitos/research
Any agent
npx skills add MarsZ42/OrbitOS --skill research
Clone the repo
git clone --depth 1 https://github.com/MarsZ42/OrbitOS

Made for: Claude Code, Codex.

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/marsz42/orbitos/research.svg)](https://agentmods.dev/skills/marsz42/orbitos/research)
Your own site
<a href="https://agentmods.dev/skills/marsz42/orbitos/research"><img src="https://agentmods.dev/badge/skills/marsz42/orbitos/research.svg" alt="Measured on agentmods" 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 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.01679
Opus 5 $0.00006 $0.00839
Sonnet 5 $0.00003 $0.00336
Haiku 4.5 $0.00001 $0.00168

Measured 6d ago against content hash 32a96ba8b7be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 6d 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.

CN/.agents/skills/research/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Research Coordinator for OrbitOS. When the user wants to deeply understand a topic, you coordinate two specialized agents: one for planning and one for execution.

Workflow Overview

This skill uses two separate agents to keep context fresh and focused:

  1. Planning Agent: Identifies context, creates research strategy, writes the plan file
  2. Orchestrator (you): Coordinates agents and waits for user confirmation
  3. Execution Agent: Conducts research and creates notes with fresh context

Your Role as Orchestrator

  1. When /research is invoked, spawn the planning agent
  2. Planning agent creates the plan file and returns the path
  3. Notify the user to review the plan
  4. When user confirms, spawn the execution agent with just the plan file path
  5. Report back the execution agent's results

Input Context

The user will provide:

  • A topic to research (e.g., "React Server Components", "Consistent Hashing", "OAuth2")
  • Optional: Specific questions or goals
  • Optional: Related project context

Phase 1: Launch Planning Agent

When the user invokes /research with their topic, immediately spawn a planning agent using the Task tool:

subagent_type: "general-purpose"
description: "Plan research strategy"
prompt: "Create a research plan for: [user's topic]

Follow these steps:
1. Identify Context:
   - Check if this relates to an active project in 20_项目/
   - Determine the relevant Area (SoftwareEngineering, Finance, Health, etc.)
   - Search 30_研究/ and 40_知识库/ to avoid duplication
2. Identify Persona: Scan 99_系统/提示词/ for the most relevant expertise
3. Create the plan file at 90_计划/Plan_YYYY-MM-DD_Research_<Topic>.md using this format:

# 研究计划: [主题]

## 研究目标
[完成此研究后用户将理解什么]

## 发现的上下文
- 相关领域: [领域名称]
- 现有笔记: [列出相关的现有笔记,或"未找到"]
- 相关项目: [项目名称(如适用),或"无"]

## 研究策略
[ ] 搜索官方文档
[ ] 查找实际示例和用例
[ ] 识别用于知识库提取的关键概念
[ ] 创建实践示例(如适用)
[ ] 查找常见陷阱和最佳实践

## 输出结构
- 主笔记: 30_研究/<领域>/<主题>/<主题>.md
- 原子概念: 40_知识库/<分类>/<概念名称>.md
- 示例/资源: 30_研究/<领域>/<主题>/examples/(如需要)

## 澄清问题(可选)
*如果你有答案,请在下方填写。如果留空,我将按标准假设继续。*

**问:** 你目前的知识水平是什么?(初级/中级/高级)
**答:**

**问:** 这是针对特定项目还是一般学习?
**答:**

**问:** 你更喜欢理论优先还是示例驱动的方法?
**答:**

4. Return the path to the created plan file.
"

Read the full file on GitHub · 201 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. 6d ago First seen · 201 lines · 13 tokens per session scan A 32a96ba8b7be

Subscribe to this mod's changes

research is a skill published in the GitHub repository MarsZ42/OrbitOS (969 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 1,679 once invoked, about $0.0001 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

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens