# agent-overview

Multi-agent architecture mapping nine specialized research roles in Claude Code. Coordinates literature reviews, GitHub analysis, and data synthesis.

- subagent · `type=agent` · Claude Code · 1011 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/agent-overview.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/agent-overview

## What it does

This blueprint defines the Open Deep Research Team workflow. It organizes nine dedicated roles under a central orchestrator. The lead agent routes tasks, enforces quality checkpoints, and logs milestones with `TodoWrite`. Before work starts, a clarifier scores query ambiguity on a 0.0 to 1.0 scale and asks multiple-choice follow-ups.

Downstream agents handle distinct source types. The academic researcher extracts papers from ArXiv, PubMed, and Google Scholar while tracking DOIs. Meanwhile, the technical researcher inspects GitHub repositories and documentation. Without configuring the companion subagents, this file serves primarily as an operational blueprint.

## Install

### Claude Code (native platform)

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

2. **Manually: put the files in place**
- File: `.claude/agents/agent-overview.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/agent-overview.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/agent-overview.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/agent-overview.md

## When to use it
- structure a multi-agent research workflow
- clarify ambiguous user queries with confidence scoring
- gather academic citations across ArXiv and PubMed
- coordinate technical reviews of GitHub repositories

## Example prompts
- Show the multi-agent workflow for researching distributed consensus algorithms
- Use the agent-overview blueprint to plan an analysis of our repository stack

## 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) — 495 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