# parallel-execution-guide

The parallel-execution-guide prompt guides Claude Code through splitting work into independent tasks, spawning CLI subagents, and combining their results. Use it for parallel research or code review.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/agentic-flow/src/prompts/parallel-execution-guide.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/parallel-execution-guide

## What it does

The guide starts by checking which tasks depend on one another. Independent work can run concurrently through `npx agentic-flow`; dependent work can proceed in stages, with parallel calls grouped using `Promise.all`. Its examples cover research across several domains, batch code review, and a multi-level team of agents.

For coordination, the guide uses ReasoningBank: subagents save their findings, then the parent agent retrieves them and prepares a combined report. Example namespaces follow the pattern `swarm/{TASK_ID}/{AGENT_ID}`. The described launch method relies on the `agentic-flow` CLI, so it will not run as shown without that CLI. For Claude Code, place the command file at `.claude/commands/parallel-execution-guide.md`.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/parallel-execution-guide.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/agentic-flow/src/prompts/parallel-execution-guide.md

## When to use it
- split research across separate domains
- run independent subtasks concurrently from the CLI
- combine subagent findings into one report
- review separate code batches and gather their issues

## Example prompts
- Split this research into independent areas and launch CLI subagents for them.
- Review the code in parallel batches, then combine the findings into one report.
- Check task dependencies and run the independent stages concurrently.

## Similar
- [do-in-parallel](https://affpapa.org/en/nevibecode/skills/do-in-parallel.md) — skill · 1300 installs
- [parallel-execution](https://affpapa.org/en/nevibecode/skills/parallel-execution.md) — skill · ★ 1424 repo stars
- [Swarm Orchestration](https://affpapa.org/en/nevibecode/skills/swarm-orchestration.md) — skill · 2100 installs
- [gsd-execute-phase](https://affpapa.org/en/nevibecode/skills/gsd-execute-phase.md) — skill · 595 installs
- [codeagent](https://affpapa.org/en/nevibecode/skills/codeagent.md) — skill · 216 installs
- [principle-outcome-oriented-execution](https://affpapa.org/en/nevibecode/skills/principle-outcome-oriented-execution.md) — skill · 10100 installs

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 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
