Skip to main content
subagent CX Codex

prompt-engineer · qdhenry — Claude Code subagent: features and setup

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

no license ★ 1,357 updated 2026-03-01

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/prompt-engineer.md
Open on GitHub

What prompt-engineer 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.

What it helps with

  • 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 for the agent

  • 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.

How to install prompt-engineer

Manually: put the files in place

.claude/agents/prompt-engineer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about prompt-engineer

How do I install prompt-engineer in Claude Code?

Place the agent file at .claude/agents/prompt-engineer.md.

What does prompt-engineer do?

It helps design prompts, agent workflows, and output formats. It can also plan tool use and safety constraints.

Which integrations does prompt-engineer use?

It uses context7 for documentation research and sequential-thinking for multi-step reasoning. The MCP integrations need to be connected in Claude Code.

Similar subagents

Subagents catalog →

prompt-engineer by other authors comes first.

prompt-engineer VoltAgent Community The prompt-engineer subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. CX Codex 16,078installs prompt-engineer Seth Hobson The prompt-engineer subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work. CX Codex 16,078installs prompt-engineer VoltAgent The prompt-engineer subagent treats prompts as behavior contracts, finds unclear instructions, and compares revisions against normal, edge, and failure scenarios. CX Codex ★ 6,505repo stars prompt-engineer josstei prompt-engineer — a subagent for designing and testing LLM prompts. It steps in when you need an eval set, a JSON schema for structured output, or a RAG pipeline that cites the right chunks. CX Codex ★ 489repo stars test-engineer official Anthropic The test-engineer subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. CX Codex 9,715installs ai-engineer VoltAgent Community The ai-engineer subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production. CX Codex 7,687installs devops-engineer VoltAgent Community The devops-engineer subagent reviews infrastructure and helps with CI/CD, containers, and deployment workflows. Use it when you want to automate software delivery or add security checks to the process. CX Codex 7,392installs data-engineer Seth Hobson data-engineer — a subagent for data pipelines, warehouses, and streaming architectures. Use it for Apache Spark, dbt, Airflow, and cloud data platform work. CX Codex 3,194installs ml-engineer Seth Hobson ml-engineer — a subagent for production ML: training, model serving, feature engineering, A/B testing and monitoring. Useful when a model needs to leave the notebook. CX Codex 1,971installs computer-vision-engineer davila7 computer-vision-engineer is a Claude Code subagent for building image and video analysis systems, from object detection to OCR. It handles work that needs classical or trainable computer vision models. CX Codex 1,248installs

From the same set112

The whole set →
security-auditor security-auditor is a Claude Code subagent that finds application vulnerabilities and reviews security controls. It can assess source code, authentication flows, or a running application. CX Codex ★ 1,357repo stars migration-assistant migration-assistant — a Claude Code command that migrates issues, PRs and projects between GitHub and Linear. Works via GitHub CLI and Linear MCP server, preserves relationships and creates rollback points. CX Codex +1 ★ 1,357repo stars deployment-engineer deployment-engineer — a Claude subagent that drafts CI/CD pipelines, container builds and cloud infrastructure, then hands over a deployment runbook. CX Codex ★ 1,357repo stars architecture-auditor architecture-auditor audits software structure, design patterns, and layer separation. Helps spot circular imports and god objects before major refactoring. CX Codex ★ 1,357repo stars quickstart quickstart is a command that guides a first run of the skill builder, from task questions to a validated skill with examples. CX Codex +1 ★ 1,357repo stars issue-to-linear-task issue-to-linear-task exports individual GitHub issues into Linear tasks while keeping descriptions, comment threads, milestones, and assignees intact. CX Codex +1 ★ 1,357repo stars ml-engineer The ml-engineer subagent designs and runs the full ML model lifecycle, from data pipelines to deployment and monitoring. Use it for production MLOps work. CX Codex ★ 1,357repo stars python-pro python-pro is a Claude Code subagent for Python refactoring, performance work, and complex features. It joins these coding tasks and includes tests with its changes. CX Codex ★ 1,357repo stars

Project sponsors

Companies that keep this analytics open