agentmods.dev

prd-to-engineering-spec

prd-to-engineering-spec is a skill for Claude Code, Codex from okwinds/miscellany. It costs 113 tokens per session (3,615 once invoked), scanned A, original, MIT.

A method for turning a PRD, or Product Requirements Document, into a detailed engineering specification that developers can implement step by step.

In plain words
What is it for?
Use it to specify data models, APIs, business logic, security, deployment, and AI-agent systems from an existing PRD.
Why use it?
It exposes incomplete requirements before technical design and documents how the system should work without leaving key decisions ambiguous.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 50repo 5mo ago A scan 113 tokens original MIT

Good fit Use it to specify data models, APIs, business logic, security, deployment, and AI-agent systems from an existing PRD.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/okwinds/miscellany/prd-to-engineering-spec
View source ↗ okwinds/miscellany
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.

Any agent
npx skills add okwinds/miscellany --skill prd-to-engineering-spec
Clone the repo
git clone --depth 1 https://github.com/okwinds/miscellany

Made for: Claude Code, Codex.

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-to-engineering-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/okwinds/miscellany/prd-to-engineering-spec/github.svg)](https://agentmods.dev/skills/okwinds/miscellany/prd-to-engineering-spec)
Your own site
<a href="https://agentmods.dev/skills/okwinds/miscellany/prd-to-engineering-spec"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/prd-to-engineering-spec/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 prd-to-engineering-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/okwinds/miscellany/prd-to-engineering-spec"><img src="https://agentmods.dev/badge/skills/okwinds/miscellany/prd-to-engineering-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,615 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 $0.00113 $0.03615
Opus 5.5 $0.00045 $0.01446
Sonnet 5.5 $0.00023 $0.00723
Haiku 4.5 $0.00011 $0.00362

Measured 2mo ago against content hash b109dff01f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prd-to-engineering-spec 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/generate_spec_skeleton.sh, scripts/validate_spec.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

agent/skills/prd-to-engineering-spec/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRD to Engineering Spec

Overview

Transform product requirements into engineering specifications so complete that developers can implement the entire system step-by-step without ambiguity, and the resulting system can be replicated or migrated without information loss.

Skill Workflow Context

┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│ prd-writing-    │────►│ prd-to-         │     │ reverse-        │
│ guide           │     │ engineering-    │     │ engineering-    │
│ Write PRD       │     │ spec            │     │ spec            │
│                 │     │ [THIS SKILL]   │     │ Code→Spec       │
└─────────────────┘     └─────────────────┘     └─────────────────┘
         │
         ▼  For AI Agent products:
┌─────────────────┐
│ ai-agent-prd    │────► This skill handles Agent PRD conversion too
└─────────────────┘

Input: Complete PRD (from prd-writing-guide or ai-agent-prd) Output: Engineering specifications at replicability-grade detail

Core Principle: Validate PRD first, design second. Incomplete requirements → incomplete specs.

Quick Start

  1. Validate PRD against prd-validation-checklist.md
  2. For Agent systems, also validate with agent-system-spec.md
  3. Generate defect report; do NOT proceed until all ❌ resolved
  4. Run bash scripts/generate_spec_skeleton.sh
  5. Apply the Engineering Lenses to every component
  6. Fill specs using spec-templates.md
  7. Validate with bash scripts/validate_spec.sh

The Engineering Lenses

Apply these seven lenses to every component during Phases 2-3. They are the engineering equivalent of prd-writing-guide's Seven Lenses.

┌──────────────────────────────────────────────────────────────────┐
│                    The Engineering Lenses                         │
├──────────────────────────────────────────────────────────────────┤
│                                                                  │
│  1. ARCHITECTURE  How does it fit? Layers, modules, comms.       │
│  2. DATA          How modeled, validated, stored, migrated?      │
│  3. CONTRACT      Interfaces? Versioning? What breaks?           │
│  4. FAILURE       How does it fail? Detect, recover, cascade?    │
│  5. SECURITY      Auth, authz, encryption, audit, secrets?       │
│  6. OPERATIONS    Deploy, configure, monitor, scale, rollback?   │
│  7. REPLICABILITY All configs, deps, assumptions documented?     │
│                                                                  │
└──────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 383 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 383 lines · 113 tokens per session scan A b109dff01f77

Subscribe to this mod's changes

prd-to-engineering-spec is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 3,615 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.

PlanningProject management
Related

prd-to-engineering-spec compared with skills from other repositories

prd-to-engineering-spec next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prd-to-engineering-specokwinds/miscellanySkill505mo agoMITA113Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code