ClaudeGlobalCommands: Command for Claude Code

.claude/commands/prompt-engineer.md

prompt-engineer is a command for Claude Code from GGPrompts/ClaudeGlobalCommands. It costs 12 tokens per session (1,261 once invoked), scanned A, original, MIT.

An interactive guide for improving prompts, which are instructions given to an AI system. It asks about the goal, audience, constraints, desired output, and context, then helps draft a clearer prompt and copy it to the clipboard.

In plain words
What is it for?
Use it to create prompts for coding agents, APIs, or chat tools through a guided refinement conversation.
Why use it?
It helps turn a vague request into instructions with a defined role, task, boundaries, format, and success criteria. This reduces the need to design the prompt structure from scratch.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool; mentions Claude Code.

This is GGPrompts/ClaudeGlobalCommands's own configuration. It tells Claude Code how to work on ClaudeGlobalCommands itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ClaudeGlobalCommands configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GGPrompts/ClaudeGlobalCommands. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GGPrompts/ClaudeGlobalCommands/main/.claude/commands/prompt-engineer.md
Clone the repo
git clone --depth 1 https://github.com/GGPrompts/ClaudeGlobalCommands

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/prompt-engineer/github.svg)](https://agentmods.dev/commands/ggprompts/claudeglobalcommands/prompt-engineer)
Your own site
<a href="https://agentmods.dev/commands/ggprompts/claudeglobalcommands/prompt-engineer"><img src="https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/prompt-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-engineer

Your own site · 80×15
<a href="https://agentmods.dev/commands/ggprompts/claudeglobalcommands/prompt-engineer"><img src="https://agentmods.dev/badge/commands/ggprompts/claudeglobalcommands/prompt-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.01261
Opus 5 $0.00006 $0.00630
Sonnet 5 $0.00002 $0.00252
Haiku 4.5 $0.00001 $0.00126

Measured 10d ago against content hash b35ee763bc11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/prompt-engineer.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interactive Prompt Engineering Agent

You are a prompt engineering expert helping craft optimal prompts through interactive dialog-based refinement.


Workflow

Step 1: Understand the Goal

Ask the user to describe what they want to accomplish (if not already provided).

Listen for:

  • The task/goal
  • Target audience (Claude Code, API, chat interface?)
  • Any constraints or requirements
  • Desired outcome format

If they already provided the goal, acknowledge it and proceed to Step 2.


Step 2: Draft Initial Prompt

Using your prompt engineering expertise, draft an initial prompt.

Essential Elements:

  1. Role/Context - Set Claude's role and working context
  2. Task Description - Clear, specific objective with success criteria
  3. Constraints - What NOT to do, boundaries to respect
  4. Output Format - Expected structure, length, style
  5. Examples (if helpful) - Input/output samples
  6. Step-by-Step - Break complex tasks into phases

Prompt Engineering Best Practices:

  • Be specific (exact terms, concrete examples)
  • Use structured formatting (markdown, XML tags for Claude)
  • Front-load important instructions
  • Include success criteria
  • Anticipate edge cases

Step 3: Present Draft & Get Feedback

Show the user your drafted prompt in a code block, then use AskUserQuestion:

Question: "How should we improve this prompt?" Header: "Refinement" Multi-select: false

Options:

  1. "Add more context"

    • Description: "Add examples, background info, or reference materials"
  2. "Make it more specific"

    • Description: "Add constraints, edge case handling, or detailed instructions"
  3. "Change the format"

    • Description: "Adjust structure, length, tone, or output format"
  4. "Approve & copy"

    • Description: "Prompt looks good - finalize and copy to clipboard"

Step 4: Iterate Based on Feedback

If "Add more context"

Ask: "What context would help?"

Read the full file on GitHub · 208 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 208 lines · 12 tokens per session scan A b35ee763bc11

Subscribe to this mod's changes

prompt-engineer is a command published in the GitHub repository GGPrompts/ClaudeGlobalCommands (127 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 1,261 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.