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.
npx agentmods add skills/okwinds/miscellany/prd-to-engineering-specnpx skills add okwinds/miscellany --skill prd-to-engineering-specgit clone --depth 1 https://github.com/okwinds/miscellanyWrote 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.
[](https://agentmods.dev/skills/okwinds/miscellany/prd-to-engineering-spec)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.03615 |
| Opus 5 | $0.00056 | $0.01808 |
| Sonnet 5 | $0.00023 | $0.00723 |
| Haiku 4.5 | $0.00011 | $0.00362 |
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 6d 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.
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
- Validate PRD against prd-validation-checklist.md
- For Agent systems, also validate with agent-system-spec.md
- Generate defect report; do NOT proceed until all ❌ resolved
- Run
bash scripts/generate_spec_skeleton.sh - Apply the Engineering Lenses to every component
- Fill specs using spec-templates.md
- 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? │
│ │
└──────────────────────────────────────────────────────────────────┘
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.
- LICENSE 1.0 KB
- README.md 2.7 KB
- README.zh-CN.md 2.8 KB
- references/agent-system-spec.md 11 KB
- references/ai-agent-prd-worked-example.md 19 KB
- references/ai-feature-spec.md 9.4 KB
- references/feature-spec-template.md 9.5 KB
- references/operations-spec.md 9.7 KB
- references/prd-validation-checklist.md 9.1 KB
- references/prd-writing-guide-worked-example.md 9.4 KB
- references/security-spec-guide.md 7.5 KB
- references/spec-templates.md 13 KB
- references/worked-example.md 24 KB
- scripts/generate_spec_skeleton.sh 22 KB runs code
- scripts/validate_spec.sh 9.4 KB runs code
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.
- 6d ago First seen · 383 lines · 113 tokens per session scan A b109dff01f77
prd-to-engineering-spec is a skill published in the GitHub repository okwinds/miscellany (50 stars, last pushed 3mo ago), licensed MIT. It adds 113 tokens to every session and 3,615 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.