# report-generator

Converts collected research notes into an organized Markdown document with numbered citations. It takes over at the final stage once all investigation data is ready.

- subagent · `type=agent` · Claude Code · 1930 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/report-generator.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/report-generator

## What it does

This subagent organizes scattered research notes into a structured document. It handles the final drafting. For texts exceeding 1000 words, it writes an executive summary with 3–5 bullet points. The body text receives sequential reference tags like `[1]`, while opposing arguments stay balanced without picking sides.

Under the hood, the agent relies on `Read`, `Write`, and `Edit` tools to process local files. It outputs clean Markdown. Depending on your instructions, the layout adapts to technical papers or policy reviews.

The subagent does not browse the web. It needs existing research notes to function. Running it without input data produces weak results, because the narrative requires verified facts.

## Install

### Claude Code (native platform)

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

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

## When to use it
- convert raw research notes into a structured Markdown document
- format source citations with sequential brackets such as `[1]`
- generate an executive summary with 3–5 highlights for lengthy texts
- present conflicting arguments fairly without unsupported bias

## Example prompts
- Take the raw findings in `climate-notes.md` and use the report-generator subagent to write a structured final report.
- Run report-generator on `findings/` to assemble a technical document with methodology details and numbered references.
- Use report-generator to turn the research notes in `ai-safety.txt` into an executive brief with a 4-point summary.

## Similar
- [prompt-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-prompt-engineer.md) — subagent · 16078 installs
- [context-manager](https://affpapa.org/en/nevibecode/agents/context-manager.md) — subagent · 10638 installs
- [code-explorer](https://affpapa.org/en/nevibecode/agents/code-explorer.md) — subagent · 1172 installs
- [search-specialist](https://affpapa.org/en/nevibecode/agents/search-specialist.md) — subagent · 6886 installs
- [api-documenter](https://affpapa.org/en/nevibecode/agents/api-documenter.md) — subagent · 6451 installs
- [technical-writer](https://affpapa.org/en/nevibecode/agents/technical-writer.md) — subagent · 4345 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 224 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