Skip to main content
subagent CX Codex

deep-research — Claude Code subagent: what it does, how to install

deep-research gathers authoritative external information outside the repository and compiles structured findings with a citation table.

MIT ★ 23,950 updated 2026-09-27

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

What deep-research does

The agent handles external research whenever local project files lack needed context. It clarifies the scope, picks a depth mode (quick, standard, deep, or exhaustive), and breaks work into search steps.

Searches run concurrently across supported tools: Tavily, WebFetch, Context7, and Sequential. The agent cross-checks claims against official documentation, flags contradictions, and logs timestamps. Results arrive as a structured response: a bulleted findings list, a citation table with credibility scores, and remaining open questions.

Without configured tools like Tavily or WebFetch, the agent cannot fetch remote pages. If authoritative sources remain unavailable, it delegates the issue back to the parent SuperClaude agent.

What it helps with

  • gather technical data from outside the local codebase
  • run concurrent web searches via Tavily and WebFetch
  • verify contradictory claims against official technical docs
  • generate citation tables with source credibility scores

Example prompts for the agent

  • Research breaking changes in the latest library release using deep mode and provide citations
  • Check official docs to verify if the external API endpoint requires authentication

How to install deep-research

Manually: put the files in place

.claude/agents/deep-research.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about deep-research

How to install deep-research in Claude Code?

Place the subagent definition file at .claude/agents/deep-research.md.

What does deep-research do?

It conducts structured web research outside the repository and returns verified findings alongside a scored citation table.

Which search tools does deep-research support?

It performs concurrent lookups using Tavily, WebFetch, Context7, and Sequential.

Source text

deep-research.md · MIT
---
name: deep-research
description: Adaptive research specialist for external knowledge gathering
category: analysis
---

# Deep Research Agent

Deploy this agent whenever the SuperClaude Agent needs authoritative information from outside the repository.

## Responsibilities
- Clarify the research question, depth (`quick`, `standard`, `deep`, `exhaustive`), and deadlines.
- Draft a lightweight plan (goals, search pivots, likely sources).
- Execute searches in parallel using approved tools (Tavily, WebFetch, Context7, Sequential).
- Track sources with credibility notes and timestamps.
- Deliver a concise synthesis plus a citation table.

## Workflow
1. **Understand** — restate the question, list unknowns, determine blocking assumptions.
2. **Plan** — choose depth, divide work into hops, and mark tasks that can run concurrently.
3. **Execute** — run searches, capture key facts, and highlight contradictions or gaps.
4. **Validate** — cross-check claims, verify official documentation, and flag remaining uncertainty.
5. **Report** — respond with:
   ```
   🧭 Goal:
   📊 Findings summary (bullets)
   🔗 Sources table (URL, title, credibility score, note)
   🚧 Open questions / suggested follow-up
   ```

Escalate back to the SuperClaude Agent if authoritative sources are unavailable or if further clarification from the user is required.

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

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set56

The whole set →
self-review self-review reviews a completed implementation by checking test evidence, edge cases, requirements, and residual risks before the final response. CX Codex ★ 23,950repo stars repo-index repo-index — a subagent that scans your project structure, flags critical files, and generates PROJECT_INDEX.md to compress context for efficient development. Run at the start of a session or after major code changes. CX Codex ★ 23,950repo stars backend-architect backend-architect is a Claude Code subagent for planning backend systems and APIs. It activates on requests about database design, security, and system reliability. CX Codex ★ 23,950repo stars frontend-architect frontend-architect — a subagent for building accessible, performant interfaces with WCAG 2.1 AA compliance. Optimizes Core Web Vitals, designs responsive layouts, and works with modern frameworks. CX Codex ★ 23,950repo stars git Command for managing Git repositories directly in Claude Code. Generates conventional commit messages, guides merge conflict resolution, and streamlines version control workflows. CX Codex +1 ★ 23,950repo stars devops-architect devops-architect automates infrastructure and CI/CD pipelines. Useful when planning zero-downtime releases and disaster recovery. CX Codex ★ 23,950repo stars system-architect The system-architect subagent reviews system structure, component boundaries, and growth plans. Use it when choosing patterns, technologies, or a migration path. CX Codex ★ 23,950repo stars sc The /sc command launches all SuperClaude Framework features from Claude Code: web research, repository indexing, specialized agents, and command recommendations. CX Codex +1 ★ 23,950repo stars

More in the catalog

Project sponsors

Companies that keep this analytics open