prd

A guided document for describing a software feature before it is built. It combines questions about the feature with an analysis of the existing codebase, then records requirements, success measures, and an implementation plan.

In plain words
What is it for?
Use it to plan complex features, define how success will be measured, and prepare work for an implementation-planning workflow. A minimal version is available for simpler features.
Why use it?
It helps resolve unclear requirements and technical constraints before coding begins. This reduces the risk of building the wrong feature or missing important project details.

Skill for Claude CodeCodex

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 skills/makigjuro/cloudstack-ai-plugins/prd
Any agent
npx skills add makigjuro/cloudstack-ai-plugins --skill prd
Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,010 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.02010
Opus 5 $0.00017 $0.01005
Sonnet 5 $0.00007 $0.00402
Haiku 4.5 $0.00003 $0.00201

Measured 2d ago against content hash d787a2b41c78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

plugins/dev-workflow/skills/prd/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Generator

Create a detailed, engineer-focused Product Requirements Document through structured discovery. The PRD is optimized for AI-assisted development and integrates with the /plan-feature workflow.

Configuration

Read cloudstack.json from the project root at the start of execution. Extract relevant fields:

  • SERVICES = backend.services[] (default: discover from project structure)

If cloudstack.json does not exist, auto-detect by scanning the project structure.

Arguments

  • {name} -- Short feature name for the file (optional, will prompt if not provided)
  • --minimal -- Use minimal template for simple features
  • --skip-analysis -- Skip codebase analysis (faster, for greenfield features)

Process

Phase 0: Enter Plan Mode

Always start by calling EnterPlanMode before doing anything else. PRD generation is a planning activity -- it requires codebase exploration, discovery questions, and user alignment before producing output. Plan mode ensures you can explore freely and get user sign-off on the approach before writing the PRD file. Exit plan mode with ExitPlanMode only after Phase 4 validation is complete and the user has approved the PRD content.

Phase 1: Discovery Questions

Ask the user these questions using AskUserQuestion. Group related questions together.

Problem & Users

  1. What problem are we solving? What's the business impact if we don't solve it?
  2. Who are the primary users?
  3. What's their current workaround, if any?

Success & Scope 4. How will we measure success? What metrics matter? 5. What's explicitly OUT of scope for this feature? 6. Are there related features we should be aware of but not implement now?

Technical Context 7. Which services will this touch? (list from SERVICES config or discovered services) 8. Are there external system integrations? 9. Any specific performance requirements? (latency, throughput, scale)

Constraints 10. Timeline or deadline constraints? 11. Backward compatibility requirements? 12. Security or compliance considerations?

Read the full file on GitHub · 309 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. 2d ago First seen · 309 lines · 34 tokens per session scan A d787a2b41c78

Subscribe to this mod's changes

prd is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 2,010 once invoked, about $0.0002 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.