prd-construction

prd-construction is a skill for Claude Code, Codex from metaschema-framework/claude-plugins. It costs 42 tokens per session (1,894 once invoked), scanned A, original, CC0-1.0.

A planning guide for writing a Product Requirements Document, a document that describes what a new feature or change should do. It provides a structure for requirements, implementation steps, and acceptance checks.

In plain words
What is it for?
Use it to plan new features, major refactoring, or complex bug fixes, including success measures, file paths, dependencies, and review checkpoints.
Why use it?
It helps turn a large or unclear change into an agreed plan before coding begins.

Skill for Claude CodeCodex

Part of the dev-metaschema plugin — 7 skills, 3 commands shipped together

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/metaschema-framework/claude-plugins/prd-construction
Any agent
npx skills add metaschema-framework/claude-plugins --skill prd-construction
Clone the repo
git clone --depth 1 https://github.com/metaschema-framework/claude-plugins

Made for: Claude Code, Codex.

Or install dev-metaschema, the plugin that ships this one along with the rest of its 7 skills, 3 commands.

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 prd-construction

README.md
[![agentmods](https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/prd-construction.svg)](https://agentmods.dev/skills/metaschema-framework/claude-plugins/prd-construction)
Your own site
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/prd-construction"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/prd-construction.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,894 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 $0.00042 $0.01894
Opus 5 $0.00021 $0.00947
Sonnet 5 $0.00008 $0.00379
Haiku 4.5 $0.00004 $0.00189

Measured 4d ago against content hash 185b0a994579, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-construction 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 4d 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-metaschema/skills/prd-construction/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD Construction Skill

Use this skill when planning work that requires structured documentation before implementation.

When to Use This Skill

  • New features
  • Significant refactoring efforts
  • Complex bug fixes requiring architectural changes
  • Any work benefiting from upfront planning and user approval

DOs and DONTs

DO

  • DO use the superpowers:brainstorming skill first to refine requirements before writing the PRD
  • DO create a dedicated directory for each PRD with all related documents
  • DO include measurable success metrics with current vs. target values
  • DO group related changes into logical, cohesive PRs
  • DO include acceptance criteria as checkboxes that can be marked complete
  • DO list exact file paths to create/modify in the implementation plan
  • DO specify dependencies between PRs when they exist
  • DO update the PRD as work progresses (mark checkboxes, add notes)
  • DO get user approval before starting implementation

DON'T

  • DON'T include AI-specific instructions in PRD documents (e.g., "For Claude:", "AI should...")
  • DON'T include meta-commentary about the document itself
  • DON'T skip the brainstorming phase - requirements need refinement
  • DON'T create one PR per commit - group related commits into cohesive PRs
  • DON'T split logically related changes across multiple PRs unnecessarily
  • DON'T start implementation before user approves the PRD
  • DON'T leave acceptance criteria vague - make them verifiable
  • DON'T forget to update status as work completes

PRD Template

# PRD: [Feature/Initiative Name]

## Document Information

| Field | Value |
|-------|-------|
| **PRD ID** | [SHORT-ID-001] |
| **Status** | Draft / In Review / Approved / In Progress / Completed |
| **Author** | [Author Name] |
| **Created** | YYYY-MM-DD |
| **Last Updated** | YYYY-MM-DD |

---

## 1. Overview

### 1.1 Problem Statement

[Describe the problem being solved. What pain points exist? Why does this matter?]

### 1.2 Goals

[Numbered list of specific, measurable goals]

1. [Goal 1]
2. [Goal 2]
3. [Goal 3]

### 1.3 Non-Goals

[What is explicitly out of scope for this initiative?]

- [Non-goal 1]
- [Non-goal 2]

### 1.4 Success Metrics

| Metric | Current | Target |
|--------|---------|--------|
| [Metric 1] | [value] | [value] |
| [Metric 2] | [value] | [value] |

---

## 2. Background

### 2.1 Current State

[Describe the current system/behavior that will be changed]

### 2.2 Technical Context

[Relevant technical details: architecture, dependencies, constraints]

---

## 3. Requirements

### 3.1 Functional Requirements

#### FR-1: [Requirement Name]
[Description of the requirement]

#### FR-2: [Requirement Name]
[Description of the requirement]

### 3.2 Non-Functional Requirements

#### NFR-1: [Requirement Name]
[Description: performance, security, maintainability, etc.]

---

## 4. Implementation Phases

[High-level overview of implementation phases]

### Phase 1: [Phase Name]
[Brief description, reference to implementation-plan.md for details]

### Phase 2: [Phase Name]
[Brief description]

---

## 5. Testing Strategy

### 5.1 Test Approach
[How will changes be tested? TDD requirements, test types]

### 5.2 Verification Checklist
- [ ] [Verification item 1]
- [ ] [Verification item 2]

---

## 6. Risks and Mitigations

| Risk | Impact | Likelihood | Mitigation |
|------|--------|------------|------------|
| [Risk 1] | High/Medium/Low | High/Medium/Low | [Mitigation strategy] |

---

## 7. Open Questions

[List any unresolved questions that need answers before or during implementation]

1. [Question 1]
2. [Question 2]

---

## 8. Related Documents

- [Implementation Plan](./implementation-plan.md)
- [Other supporting documents]

Read the full file on GitHub · 310 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. 4d ago First seen · 310 lines · 42 tokens per session scan A 185b0a994579

Subscribe to this mod's changes

prd-construction is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 42 tokens to every session and 1,894 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens