# 10x-research

10x-research spawns parallel sub-agents to investigate your codebase comprehensively. Finds architectural patterns, component connections, and generates a markdown research report with code references.

- command · `type=command` · Claude Code, Codex, GitHub Copilot, Gemini CLI · ★ 267 repo stars
- Author: przeprogramowani
- License: AGPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/przeprogramowani/ai-rules-builder/tree/HEAD/.claude/commands/10x-research.md
- Updated: 2026-02-20
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/10x-research

## What it does

The command breaks your research question into subtasks and runs multiple agents simultaneously across different parts of the codebase. Each agent specializes in a specific job—locating files, analyzing dependencies, tracing data flows. Results are synthesized into a single report with file paths, line numbers, and GitHub permalinks.

You start by describing what to investigate. If you mention specific files, they're read in full before sub-agents spawn. The command then builds a research plan, waits for all agents to complete, and compiles findings with exact code references. The report saves to `thoughts/shared/research/` with a timestamp and optional ticket number in the filename.

Follow-up questions can be added to the same document—the command updates the metadata and appends a new investigation section, spawning fresh sub-agents as needed.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/10x-research.md` — Call it with /10x-research. For all projects use ~/.claude/commands/

### Codex

**Manually: put the files in place**
- File: `~/.codex/prompts/10x-research.md` — Call it with /prompts:10x-research. Codex marks this format deprecated in favour of skills

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/10x-research.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/10x-research.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/przeprogramowani/ai-rules-builder/tree/HEAD/.claude/commands/10x-research.md

## When to use it
- explore an unfamiliar codebase architecture in a single query
- locate all files connected to a specific feature or component
- identify design patterns and architectural principles across the project
- trace how data flows and dependencies connect different modules
- preserve research findings with full code references for team sharing

## Example prompts
- How is authentication structured in our app and where are permissions checked?
- Find all React components using Redux and show how they connect.
- Trace the data flow from API endpoints to the database in the payments module.

## Similar
- [research-codebase](https://affpapa.org/en/nevibecode/agents/research-codebase.md) — subagent · ★ 3951 repo stars
- [research](https://affpapa.org/en/nevibecode/skills/hyperb1iss-research.md) — skill · 646 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/zernie-deep-research.md) — skill · 762 installs
- [notion-research-documentation](https://affpapa.org/en/nevibecode/skills/notion-research-documentation-2.md) — skill · 390 installs
- [research-with-sources](https://affpapa.org/en/nevibecode/skills/research-with-sources.md) — skill · 864 installs
- [context7-auto-research](https://affpapa.org/en/nevibecode/skills/context7-auto-research.md) — skill · 709 installs

From the same set: [przeprogramowani/ai-rules-builder](https://affpapa.org/en/nevibecode/by/przeprogramowani/ai-rules-builder.md) — 24 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
