generate-prd

Generate PRD with high-level technical spec in spec folder structure.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/jnarowski/agentcmd/generate-prd
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

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 2,536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00012 $0.02536
Opus 5 $0.00006 $0.01268
Sonnet 5 $0.00002 $0.00507
Haiku 4.5 $0.00001 $0.00254

Measured today against content hash 9737d99d6aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 today.

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/cmd/generate-prd.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Requirements Document (PRD)

Generate high-level PRD focusing on "what" and "why" before implementation. Creates folder at .agent/specs/todo/[id]-[feature]/prd.md with timestamp-based ID.

Variables

  • $param1: $1 (optional) - Feature context or description (infers from conversation if omitted)

Instructions

  • IMPORTANT: Use your reasoning model - THINK HARD about feature requirements, user needs, and business value
  • IMPORTANT: This command ONLY generates the PRD - do NOT implement any code or make file changes beyond creating the folder/file and updating index.json
  • Normalize feature name to kebab-case for the folder name
  • Replace ALL <placeholders> with specific details relevant to that section
  • Focus on WHAT and WHY, not HOW (save implementation details for spec)
  • Keep it high-level but comprehensive
  • DO NOT include implementation tasks or complexity scores - this is for planning only

Workflow

  1. Determine Context:

    • If $param1 provided: Use as context
    • If $param1 empty: Infer from conversation history
  2. Generate Spec ID:

    • Generate timestamp-based ID in format YYMMDDHHmm using current local time
    • Example: November 13, 2025 at 3:22pm local → 2511131522
    • Read .agent/specs/index.json (will be updated in step 8)
  3. Generate Feature Name:

    • Generate concise kebab-case name from context (max 4 words)
    • Examples: "Add OAuth support" → "oauth-support", "Dashboard redesign" → "dashboard-redesign"
  4. Research Phase:

    • Research codebase for existing patterns relevant to the feature
    • Gather context about architecture, file structure, and conventions
    • Look for similar features for inspiration
  5. Clarification (conditional):

    • If explicit context provided: Resolve ambiguities autonomously using recommended best practices
    • If inferring from conversation: Ask clarifying questions ONE AT A TIME if requirements are unclear:
      • Don't use the Question tool
      • Use this template:

Read the full file on GitHub · 312 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. today First seen · 312 lines · 12 tokens per session scan A 9737d99d6aae

Subscribe to this mod's changes

generate-prd is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 2,536 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 2026-09-01.