Skip to main content
command CX Codex

research · superclaude-org — Claude Code command: deep search with adaptive planning

research — a command for investigating complex questions beyond your knowledge cutoff. It breaks down the task automatically, runs parallel searches, and collects evidence with source attribution.

MIT ★ 23,950 updated 2026-09-27

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/research.md
Open on GitHub

What research does

The /sc:research command activates multi-hop investigation with adaptive planning. You provide a question; the system decides how to decompose it, which MCP servers to use (Tavily for search, Playwright for complex content, Sequential for reasoning), and how to parallelize queries. Output is saved to claudedocs/research_[topic]_[timestamp].md with findings, confidence levels, and all sources cited.

Four depth modes are available: quick (basic search, 1 hop), standard (2–3 hops), deep (3–4 hops), and exhaustive (5 hops). The system tracks evidence chains, validates source credibility, and resolves contradictions. No configuration files needed—pass options as flags: --depth and --strategy.

What it helps with

  • find current information on a topic beyond the model's training data
  • analyze competitors and market trends with live data
  • investigate a complex question by breaking it into logical steps
  • gather academic facts and trends with verified sources

Example prompts for the agent

  • Find the latest advances in quantum computing for 2024
  • Analyze AI coding assistants in the market --depth deep
  • Research best practices for distributed systems --strategy unified

How to install research

Manually: put the files in place

.claude/commands/research.md

Call it with /research. For all projects use ~/.claude/commands/

Questions about research

How do I install research in Claude Code?

Add the file .claude/commands/research.md to your project root. Claude Code will recognize the command automatically.

What does the research command do?

It conducts investigation by decomposing the question into tasks, running searches in parallel, and collecting evidence. It produces a report with findings and sources, but does not implement recommendations—that decision is yours.

Can I use research results directly in my code?

The report provides analysis and conclusions for decision-making. To implement recommendations, use /sc:design for architecture or /sc:implement for code—research only investigates.

Source text

research.md · MIT
---
name: research
description: Deep web research with adaptive planning and intelligent search
category: command
complexity: advanced
mcp-servers: [tavily, sequential, playwright, serena]
personas: [deep-research-agent]
---

# /sc:research - Deep Research Command

> **Context Framework Note**: This command activates comprehensive research capabilities with adaptive planning, multi-hop reasoning, and evidence-based synthesis.

## Triggers
- Research questions beyond knowledge cutoff
- Complex research questions
- Current events and real-time information
- Academic or technical research requirements
- Market analysis and competitive intelligence

## Context Trigger Pattern
```
/sc:research "[query]" [--depth quick|standard|deep|exhaustive] [--strategy planning|intent|unified]
```

## Behavioral Flow

### 1. Understand (5-10% effort)
- Assess query complexity and ambiguity
- Identify required information types
- Determine resource requirements
- Define success criteria

### 2. Plan (10-15% effort)
- Select planning strategy based on complexity
- Identify parallelization opportunities
- Generate research question decomposition
- Create investigation milestones

### 3. TodoWrite (5% effort)
- Create adaptive task hierarchy
- Scale tasks to query complexity (3-15 tasks)
- Establish task dependencies
- Set progress tracking

### 4. Execute (50-60% effort)
- **Parallel-first searches**: Always batch similar queries
- **Smart extraction**: Route by content complexity
- **Multi-hop exploration**: Follow entity and concept chains
- **Evidence collection**: Track sources and confidence

### 5. Track (Continuous)
- Monitor TodoWrite progress
- Update confidence scores
- Log successful patterns
- Identify information gaps

### 6. Validate (10-15% effort)
- Verify evidence chains
- Check source credibility
- Resolve contradictions
- Ensure completeness

## Key Patterns

### Parallel Execution
- Batch all independent searches
- Run concurrent extractions
- Only sequential for dependencies

### Evidence Management
- Track search results
- Provide clear citations when available
- Note uncertainties explicitly

### Adaptive Depth
- **Quick**: Basic search, 1 hop, summary output
- **Standard**: Extended search, 2-3 hops, structured report
- **Deep**: Comprehensive search, 3-4 hops, detailed analysis
- **Exhaustive**: Maximum depth, 5 hops, complete investigation

## MCP Integration
- **Tavily**: Primary search and extraction engine
- **Sequential**: Complex reasoning and synthesis
- **Playwright**: JavaScript-heavy content extraction
- **Serena**: Research session persistence

## Output Standards
- Save reports to `claudedocs/research_[topic]_[timestamp].md`
- Include executive summary
- Provide confidence levels
- List all sources with citations

## Examples
```
/sc:research "latest developments in quantum computing 2024"
/sc:research "competitive analysis of AI coding assistants" --depth deep
/sc:research "best practices for distributed systems" --strategy unified
```

## Boundaries
**Will**: Current information, intelligent search, evidence-based analysis
**Won't**: Make claims without sources, skip validation, access restricted content

## CRITICAL BOUNDARIES

**STOP AFTER RESEARCH REPORT**

This command produces a RESEARCH REPORT ONLY - no implementation.

**Explicitly Will NOT**:
- Implement findings or recommendations
- Write code based on research
- Make architectural decisions
- Create system changes based on research

**Output**: Research report (`claudedocs/research_*.md`) containing:
- Findings with sources
- Evidence-based analysis
- Recommendations (for human decision)
- Cited references

**Next Step**: After research completes, user decides next action. Use `/sc:design` for architecture or `/sc:implement` for coding.

© SuperClaude-Org · MIT · SuperClaude-Org/SuperClaude_Framework

Similar slash commands

All slash commands for AI and ML →

research by other authors comes first.

research Eugeniu Ghelbur Research a topic and get a sourced dossier. With free sources, Claude Code turns the returned results into a note. CX Codex +1 ★ 5,412repo stars research microsoft research runs a five-iteration investigation of one topic in your codebase, tracing real code paths and citing a source for every claim. CX Codex +1 ★ 3,232repo stars research carlrannaberg research fans a question out to parallel subagents, reads their saved reports from /tmp, and merges the lot into one cited file. CX Codex +1 ★ 763repo stars research JDArmy research spawns a subagent that searches GitHub for evasion techniques, reads the code and stores the findings in a knowledge base. CX Codex +1 ★ 336repo stars tavily-research tavily-ai tavily-research — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that runs tvly research, pulls sources from the web, and returns a cited report. Completes in 30–120 seconds. CX Codex +1 25,100installs research-planning lingzhi227 research-planning is a Claude Code skill that builds research plans with methodology, dependencies, paper structure and UML diagrams. It runs for new projects or paper reproduction. CX Codex +1 1,800installs research-explorer First Fluke research-explorer — a subagent that answers research questions by searching three planes at once: docs and code, market signals, and academic literature. Returns findings with sources and confidence labels. CX Codex ★ 1,472repo stars parallel-deep-research parallel parallel-deep-research runs multi-step deep research jobs using parallel-cli. Use it when you need an exhaustive markdown report with citations rather than a quick web search. CX Codex +1 16,400installs bmad-research aj-geddes bmad-research — a skill that conducts structured market, competitor, technology and domain research from live sources, producing a cited research report. Run it before product planning or architecture decisions. CX Codex +1 138installs rpi-research microsoft The rpi-research skill investigates a task and saves dated findings to a report. Use it when you need evidence and alternatives before planning work. CX Codex +1 ★ 1,627repo stars

From the same set56

The whole set →
design design plans system architecture, API specifications, and database schemas before coding starts. Useful for creating technical contracts and component diagrams. CX Codex +1 ★ 23,950repo stars save save preserves session context, discoveries, and recovery points through Serena MCP. Use it when work needs to continue across sessions. CX Codex +1 ★ 23,950repo stars select-tool select-tool is a Claude Code command that routes operations to Serena or Morphllm based on complexity, balancing accuracy and speed. CX Codex +1 ★ 23,950repo stars business-panel business-panel runs document analysis through a panel of simulated business thinkers to deliver structured strategic synthesis. CX Codex +1 ★ 23,950repo stars reflect reflect evaluates task adherence and session progress using Serena MCP analysis tools. Useful for quality checks before marking tasks as complete. CX Codex +1 ★ 23,950repo stars explain A command to explain code, system architecture, and concepts at the right level of depth. Helps you understand unfamiliar code or teach concepts to others. CX Codex +1 ★ 23,950repo stars index index scans project architecture to build structured knowledge bases, API references, or README files with cross-references. CX Codex +1 ★ 23,950repo stars troubleshoot troubleshoot diagnoses runtime errors, build failures, performance bottlenecks, and deployment bugs. It inspects the system state and never modifies files unless passed --fix. CX Codex +1 ★ 23,950repo stars

Project sponsors

Companies that keep this analytics open