# prompt-engineer

The prompt-engineer subagent for Claude Code designs prompts, agent workflows, and structured outputs. It helps clarify instructions and safety constraints.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 1357 repo stars
- Author: qdhenry
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/prompt-engineer.md
- Updated: 2026-03-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/qdhenry-prompt-engineer

## What it does

The subagent breaks down a goal, selects a prompting approach, and shapes instructions around context, output format, and examples. It can also help plan tool use, review model responses, and coordinate work across multiple agents.

Its tools cover file reading and editing, search, and terminal work, alongside `context7` and `sequential-thinking` integrations. These can support documentation research and multi-step reasoning tasks. For Claude Code, place the agent file at `.claude/agents/prompt-engineer.md`; MCP features depend on those integrations being connected.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/prompt-engineer.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/prompt-engineer.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/prompt-engineer.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/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/prompt-engineer.md

## When to use it
- design a prompt that returns structured output
- turn a complex goal into agent tasks
- plan how an agent should use tools
- add safeguards against malicious prompt instructions

## Example prompts
- Design a prompt for an agent that accepts a request and returns JSON.
- Break this task into steps and specify which tools the agent should use.
- Review my prompt for ambiguity and add safeguards against malicious instructions.

## Similar
- [test-engineer](https://affpapa.org/en/nevibecode/agents/test-engineer.md) — subagent · 9715 installs
- [ai-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-ai-engineer.md) — subagent · 7687 installs
- [devops-engineer](https://affpapa.org/en/nevibecode/agents/devops-engineer.md) — subagent · 7392 installs
- [data-engineer](https://affpapa.org/en/nevibecode/agents/data-engineer.md) — subagent · 3194 installs
- [ml-engineer](https://affpapa.org/en/nevibecode/agents/ml-engineer.md) — subagent · 1971 installs
- [computer-vision-engineer](https://affpapa.org/en/nevibecode/agents/computer-vision-engineer.md) — subagent · 1248 installs

## Other versions with the same name
- [prompt-engineer · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-community-prompt-engineer.md) — 16078 installs
- [prompt-engineer · wshobson](https://affpapa.org/en/nevibecode/agents/prompt-engineer.md) — 16078 installs
- [prompt-engineer · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-prompt-engineer.md) — ★ 6505 repo stars
- [prompt-engineer · josstei](https://affpapa.org/en/nevibecode/agents/josstei-prompt-engineer.md) — ★ 489 repo stars

From the same set: [qdhenry/claude-command-suite](https://affpapa.org/en/nevibecode/by/qdhenry/claude-command-suite.md) — 112 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
