agentmods.dev

markdown-vdb: Command for Claude Code

.claude/commands/generate-prd.md

generate-prd is a command for Claude Code from geckse/markdown-vdb. It costs 0 tokens per session (414 once invoked), scanned A, original, MIT.

A command that creates a detailed Product Requirements Document, or PRD, for a proposed feature. A PRD describes what a feature should do, who it serves, its constraints, and how it should be tested.

In plain words
What is it for?
Use it to prepare a PRD after reviewing the project and asking about scope, users, behavior, technical limits, data, compatibility, and testing.
Why use it?
It gives feature planning a defined process that includes templates, codebase research, external research when needed, and user questions before drafting.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is geckse/markdown-vdb's own configuration. It tells Claude Code how to work on markdown-vdb 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 markdown-vdb configures →

not rated 29repo 2mo ago A scan 0 tokens original MIT
View source ↗ geckse/markdown-vdb
Reuse

Borrowing it

Nothing to install: this file belongs to geckse/markdown-vdb. 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/geckse/markdown-vdb/main/.claude/commands/generate-prd.md
Clone the repo
git clone --depth 1 https://github.com/geckse/markdown-vdb

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 generate-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/geckse/markdown-vdb/generate-prd/github.svg)](https://agentmods.dev/commands/geckse/markdown-vdb/generate-prd)
Your own site
<a href="https://agentmods.dev/commands/geckse/markdown-vdb/generate-prd"><img src="https://agentmods.dev/badge/commands/geckse/markdown-vdb/generate-prd/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 generate-prd

Your own site · 80×15
<a href="https://agentmods.dev/commands/geckse/markdown-vdb/generate-prd"><img src="https://agentmods.dev/badge/commands/geckse/markdown-vdb/generate-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 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 $0.00000 $0.00414
Opus 5.5 $0.00000 $0.00166
Sonnet 5.5 $0.00000 $0.00083
Haiku 4.5 $0.00000 $0.00041

Measured 2mo ago against content hash 45212a3619c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate-prd 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 2mo 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/generate-prd.md · 31 lines

What it actually says

Generate PRD

Generate a comprehensive Product Requirements Document for the following feature.

Feature: $ARGUMENTS

Instructions

  1. Read the base template — Read docs/prds/base-template.md to understand the required PRD structure. Read docs/prds/example-prd.md to see the quality bar.

  2. Research the codebase — Explore the project to understand the existing architecture, conventions, data models, and patterns. Read CLAUDE.md for project context.

  3. Research externally (if needed) — If the feature involves third-party libraries, APIs, or platforms, search the web for current documentation and best practices.

  4. Interview the user — IMPORTANT: You MUST ask clarifying questions before writing the PRD. The goal is to reduce assumptions to near zero. Use the AskUserQuestion tool to ask at least 8-10 questions in batches of 3-4, covering:

    • Scope: What is in scope vs explicitly out of scope?
    • Users: Who is this for? What is their workflow?
    • Behavior: What should happen in edge cases?
    • Technical: Are there constraints on implementation approach?
    • Data: What data model changes are needed?
    • Compatibility: Must this be backward compatible?
    • Testing: What validation criteria matter most?
    • Priority: Which parts are must-have vs nice-to-have?
    • Anti-patterns: What mistakes should be explicitly avoided?

    Provide recommended answers based on your research. Wait for responses before asking the next batch. After all questions, ask: "Is there anything else I should know that I haven't asked about?"

  5. Generate the PRD — Write the full PRD following the base template structure. Every section must be filled in with specific, actionable content. No placeholders, no vague language.

  6. Save — Write the PRD to docs/prds/<feature-name>.md (kebab-case). Present a summary to the user.

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. 2mo ago First seen · 31 lines · 0 tokens per session scan A 45212a3619c5

Subscribe to this mod's changes

generate-prd is a command published in the GitHub repository geckse/markdown-vdb (29 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 414 tokens. 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.

PlanningWriting and docsclifilesystemmarkdownvector-database
Related

generate-prd compared with commands from other repositories

generate-prd next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
generate-prdgeckse/markdown-vdbCommand292mo agoMITA0Claude Code
landing-publishseite-sh/seiteCommand28yesterdayMITA0Claude Code
searchedochi/mdvsCommand2717d agoMITA0Claude Code
infoedochi/mdvsCommand2717d agoMITA0Claude Code
updateedochi/mdvsCommand2717d agoMITA0Claude Code
cleanedochi/mdvsCommand2717d agoMITA0Claude Code
export-jsonschemaedochi/mdvsCommand2717d agoMITA0Claude Code