parallel-execution-guide — Claude Code prompt for parallel tasks
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.
no license ★ 850 updated 2026-10-26
.claude/commands/parallel-execution-guide.mdWhat parallel-execution-guide 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.
What it helps with
- 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 for the agent
- 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.
How to install parallel-execution-guide
Manually: put the files in place
.claude/commands/parallel-execution-guide.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about parallel-execution-guide
How do I install parallel-execution-guide in Claude Code?
Place the command file at .claude/commands/parallel-execution-guide.md.
What does parallel-execution-guide do?
It describes how to assign work to CLI subagents, run independent tasks concurrently, and collect their results through ReasoningBank.
How does the guide handle task dependencies?
It recommends concurrent execution for independent tasks and staged execution for dependent ones, using sequential Promise.all blocks.