prd

A command for writing a 15-section product requirements document, or PRD, covering users, their jobs, decisions, scope, agent details, metrics, hypotheses, and quality checks. It can also create roadmaps and design variants from an existing PRD.

In plain words
What is it for?
Use it to create a PRD, generate a Now/Next/Later roadmap, calculate RICE scores—a prioritization method based on reach, impact, confidence, and effort—or produce four design variants.
Why use it?
It puts product and implementation decisions into one documented structure and produces a separate pool of quality-assurance questions. Roadmap modes help organize timing or compare priorities.

Command

Part of the deliver plugin — 10 skills, 1 command 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 commands/kimsanguine/hplan/prd
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Or install deliver, the plugin that ships this one along with the rest of its 10 skills, 1 command.

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 593 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 $0.00059 $0.00593
Opus 5 $0.00030 $0.00296
Sonnet 5 $0.00012 $0.00119
Haiku 4.5 $0.00006 $0.00059

Measured 2d ago against content hash 24b39b9a7d0f, 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.

deliver/commands/prd.md · 40 lines

What it actually says

/prd — Unified 15-section PRD Writer

Running for: $ARGUMENTS

이 커맨드는 deliver/skills/prd/SKILL.md 스킬을 즉시 호출합니다.

Instructions

  1. deliver/prd 스킬을 $ARGUMENTS로 invoke.
  2. 스킬이 Phase 1~5(Section 1-15)를 순차 작성.
  3. 결과 산출물:
    • docs/PRD.md — 15-section PRD
    • harness/QA_POOL.json — §15 QA Pool (dev_roles 결정론 매핑)

모드 (sub-mode)

  • 기본: 15-section PRD 작성.
  • --mode design-shotgun: 기존 PRD의 §1+§11을 읽어 harness/design-variants/에 HTML 변형 4개 + comparison.md 생성.
  • --mode roadmap [generate|rice|prioritize]: §6 Now/Next/Later 기반 로드맵. prd가 §6 canonical 소유자이며 roadmap은 그 sub-mode 다. generate=Mermaid gantt(docs/ROADMAP.md), rice=RICE 결정론 계산(docs/rice-scores.md), prioritize=Now/Next/Later 재분류 제안.

입력 가이드

  • $ARGUMENTS 가 없으면 스킬이 product name을 묻습니다.
  • interview-synthesis audit 결과로 harness/PERSONA_SPECS.json 이 있으면 §15 QA Pool 작성에 자동 활용됩니다.

후속

  • harness/QA_POOL.json 생성 후 qa-checklist --mode adversarial 실행 가능.
  • §15 QA Pool 생성을 다음 단계로 미루고 PRD 본문(Section 1-14)만 빨리 작성하려면 harness-build --step prd 단축 경로 사용. (단, qa-checklist --mode adversarial은 §15가 있어야 진입 가능 — 사후 /prd 재호출 필요)

Output Format

기본 모드는 docs/PRD.md와 필요한 경우 harness/QA_POOL.json을 생성합니다. sub-mode는 해당 roadmap 또는 design-variant artifact와 다음 실행 경로를 반환합니다.

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 · 40 lines · 59 tokens per session scan A 24b39b9a7d0f

Subscribe to this mod's changes

prd is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 593 once invoked, about $0.0003 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.