A command that turns a vague product or software idea into a structured PRD, or product requirements document. It checks the existing project context, defines requirements and acceptance criteria, and prepares a related implementation plan.

Use it to plan product features, internal backend work, or refactors, then connect the PRD to review, screen specification, implementation, and commit steps. It can also define APIs with requests, responses, and errors.

It gives an unclear feature request a concrete scope, document type, technical context, and verifiable requirements before implementation begins.

prd — Command by wigtn

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/wigtn/wigtn-plugins/prd

Clone the repo

git clone --depth 1 https://github.com/wigtn/wigtn-plugins

Per session 130 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 920 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.

Model	Per session	Once invoked
Fable 5	$0.00130	$0.00920
Opus 5	$0.00065	$0.00460
Sonnet 5	$0.00026	$0.00184
Haiku 4.5	$0.00013	$0.00092

Measured 2d ago against content hash 0d786c8fb931, 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/wigtn-plugins/commands/prd.md · 73 lines

What it actually says

PRD Generation

모호한 기능 요청을 구조화된 PRD 문서로 변환한다.

파이프라인: /prd → prd-reviewer → (FE 페이지 있으면) /screen-spec → /implement → /auto-commit

Step 1 — 계약을 먼저 읽는다 (건너뛰지 않는다)

${CLAUDE_PLUGIN_ROOT}/contracts/PRD-CONTRACT.md를 Read한다. PRD 골격·섹션 조건·Critical 항목은 전부 그 파일에 있다. 이 커맨드는 그것을 재진술하지 않는다.

Step 2 — 문서 유형과 규모

문서 유형 판정: product-feature | internal-backend | refactor (섹션 활성 규칙은 계약 §문서 유형). 모호하면 AskUserQuestion. 판정 결과를 PRD 헤더 > **Type**: 에 쓴다.
Scale Grade: AskUserQuestion으로 Hobby | Startup | Growth | Enterprise 중 선택받는다 (refactor는 생략). 등급 경계는 계약 §4.0.

Step 3 — 프로젝트 컨텍스트

기존 PRD(prd/, docs/prd/), 기술 스택(package.json 등), API·컴포넌트·스키마 구조를 확인해 PRD가 실제 코드베이스와 어긋나지 않게 한다.

Step 4 — 작성

계약의 골격대로 PRD를 쓴다. 문장 규칙:

구체적으로 — "카테고리별 필터링" (O) / "검색 가능" (X)
측정 가능하게 — "p95 < 200ms" (O) / "빠른 응답" (X)
검증 가능하게 — 모든 스토리에 수용 기준
API 명세는 Request / Response / Error를 모두 정의한다. REST 외(GraphQL / gRPC / WebSocket / OpenAPI) 템플릿이 필요하면 ${CLAUDE_PLUGIN_ROOT}/commands/references/prd-api-templates.md를 읽는다.

Step 5 — 저장

AskUserQuestion으로 위치 확인: docs/prd/ (권장) | prd/ | 루트.

이어서 실행 계획을 docs/todo_plan/PLAN_{feature-name}.md로 생성한다. PRD의 §6 Implementation Phases를 Phase로, §3 FR을 Task로 매핑하고 의존성 순서대로 배치한다. 각 Task는 - [ ] 체크박스로 쓴다 — 이 파일이 /implement의 진행 원장(ledger)이다.

Step 6 — 검증 (Quality Gate)

prd-reviewer 에이전트를 실행한다. 판정은 findings 롤업이다:

결과	조건	다음
❌ BLOCKED	Critical ≥1	수정 후 재검증
✅ PASS	Critical 0	`/implement` 진행 가능

Critical은 위치 / 문제 / 영향 / 개선안 4줄로 제시한다. Major·Minor는 건수만 요약한다.

Step 7 — 다음 단계

§5.4 Pages에 Has FE Components: Yes 행이 1개 이상이면 /screen-spec {feature} 권장, 아니면 곧바로 /implement {feature}. PRD 경로·PLAN 경로·게이트 결과·감지된 FE 페이지 수를 함께 보고한다.

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.

2d ago First seen · 73 lines · 130 tokens per session scan A 0d786c8fb931

Subscribe to this mod's changes

prd is a command published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed 16d ago), licensed Apache-2.0. It adds 130 tokens to every session and 920 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.

Backend and APIs Code review Git and workflow agent-skills ai-native anthropic claude-code claude-code-plugin junior-developer

prd

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

PRD Generation

Step 1 — 계약을 먼저 읽는다 (건너뛰지 않는다)

Step 2 — 문서 유형과 규모

Step 3 — 프로젝트 컨텍스트

Step 4 — 작성

Step 5 — 저장

Step 6 — 검증 (Quality Gate)

Step 7 — 다음 단계

What this file has done since we first saw it

Other commands, from other repositories

operations-agent

inception-agent

fire

forge

spark

specsmd-flame