mcp-prompt-server: Command for Claude Code

.claude/commands/create-prompt-issue-request.md

create-prompt-issue-request is a command for Claude Code from marcmodin/mcp-prompt-server. It costs 22 tokens per session (3,575 once invoked), scanned A, original, MIT.

A command that guides someone through creating a Prompt Request issue on GitHub, a tracked request for a new prompt or prompt change. It reads the repository's issue template, asks for the required information, and submits the issue with GitHub CLI.

In plain words
What is it for?
Use it to gather prompt-request details conversationally and create the completed GitHub issue.
Why use it?
It turns an incomplete idea into an issue containing the fields the repository expects. This reduces back-and-forth when requesting prompt work.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is marcmodin/mcp-prompt-server's own configuration. It tells Claude Code how to work on mcp-prompt-server 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 mcp-prompt-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to marcmodin/mcp-prompt-server. 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/marcmodin/mcp-prompt-server/main/.claude/commands/create-prompt-issue-request.md
Clone the repo
git clone --depth 1 https://github.com/marcmodin/mcp-prompt-server

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 create-prompt-issue-request

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcmodin/mcp-prompt-server/create-prompt-issue-request.svg)](https://agentmods.dev/commands/marcmodin/mcp-prompt-server/create-prompt-issue-request)
Your own site
<a href="https://agentmods.dev/commands/marcmodin/mcp-prompt-server/create-prompt-issue-request"><img src="https://agentmods.dev/badge/commands/marcmodin/mcp-prompt-server/create-prompt-issue-request.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,575 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 $0.00022 $0.03575
Opus 5 $0.00011 $0.01788
Sonnet 5 $0.00004 $0.00715
Haiku 4.5 $0.00002 $0.00358

Measured 7d ago against content hash 8d92e8e99624, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-prompt-issue-request 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 7d 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/create-prompt-issue-request.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Prompt Request Issue

Context

You are a helpful assistant that guides users through creating a Prompt Request issue on GitHub. You follow the prompt request template defined in .github/ISSUE_TEMPLATE/prompt_request.yml to gather all necessary information about the desired prompt, then create and submit the issue using the GitHub CLI (gh command).

Your goal is to make it easy for users to request new prompts by asking conversational questions based on the template fields.

Instructions

Follow this conversational workflow to create a Prompt Request issue:

1. Introduction

Explain that you'll help create a prompt request issue and gather the necessary information through a series of questions.

2. Read the Template

Read the prompt request template at .github/ISSUE_TEMPLATE/prompt_request.yml to understand all required and optional fields.

3. Gather Information in Chunks

Ask the user questions in three groups to make the process faster and more efficient. Use the XML structure below to organize the data collection:

Read the full file on GitHub · 413 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. 7d ago First seen · 413 lines · 22 tokens per session scan A 8d92e8e99624

Subscribe to this mod's changes

create-prompt-issue-request is a command published in the GitHub repository marcmodin/mcp-prompt-server (1 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 3,575 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 2026-08-31.