# research-orchestrator

Coordinates multi-phase deep research projects in Claude Code. The subagent plans the workflow and assigns tasks to specialized investigation agents.

- subagent · `type=agent` · Claude Code · 2448 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/research-orchestrator.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/research-orchestrator

## What it does

The subagent oversees the entire research pipeline based on the Open Deep Research framework. It begins by examining the initial query for clarity and scope. If the request is broad, it routes the prompt to clarify goals before generating a structured research plan.

Parallel investigations are split across specialized sub-agents such as technical or academic researchers. To maintain visibility, the orchestrator tracks every step in a `TodoWrite` task list and structures inter-agent messages as JSON records containing coverage metrics.

The orchestrator manages the team. Without companion subagents like `research-synthesizer` or `report-generator` installed in the project, the workflow halts when calling the next specialist.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent deep-research-team/research-orchestrator
```

2. **Manually: put the files in place**
- File: `.claude/agents/research-orchestrator.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/research-orchestrator.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/research-orchestrator.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/research-orchestrator.md

## When to use it
- break broad research questions into ordered phases
- delegate tasks to academic and web researchers
- track investigation milestones through structured checklists
- merge disparate agent findings into a coherent report

## Example prompts
- Coordinate a structured research process on AI safety and compile the report
- Run a research project on how quantum computing impacts modern cryptography

## Similar
- [frontend-developer](https://affpapa.org/en/nevibecode/agents/voltagent-community-frontend-developer.md) — subagent · 40905 installs
- [dx-optimizer](https://affpapa.org/en/nevibecode/agents/dx-optimizer.md) — subagent · 1198 installs
- [mlops-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-mlops-engineer.md) — subagent · 1009 installs
- [postgres-pro](https://affpapa.org/en/nevibecode/agents/postgres-pro.md) — subagent · 897 installs
- [agent-installer](https://affpapa.org/en/nevibecode/agents/agent-installer.md) — subagent · 363 installs
- [embedded-systems](https://affpapa.org/en/nevibecode/agents/embedded-systems.md) — subagent · 279 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 238 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md