What is init-design-doc?

An interactive command that creates a design-doc.md file, a document describing a project's goals, inputs, users, and planned implementation.

Use /init-design-doc at the start of a project, optionally providing PDF or spreadsheet brief files for analysis.

It turns an initial project brief into an organised design document through a series of questions.

How pyramidheadshark/claude-scaffold configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pyramidheadshark/claude-scaffold/main/.claude/commands/init-design-doc.md

Clone the repo

git clone --depth 1 https://github.com/pyramidheadshark/claude-scaffold

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pyramidheadshark/claude-scaffold/init-design-doc.svg)](https://agentmods.dev/commands/pyramidheadshark/claude-scaffold/init-design-doc)

Your own site

<a href="https://agentmods.dev/commands/pyramidheadshark/claude-scaffold/init-design-doc"><img src="https://agentmods.dev/badge/commands/pyramidheadshark/claude-scaffold/init-design-doc.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 807 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00807
Opus 5	$0.00000	$0.00404
Sonnet 5	$0.00000	$0.00161
Haiku 4.5	$0.00000	$0.00081

Measured 8d ago against content hash bb1979604d79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

init-design-doc 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 8d 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.

.claude/commands/init-design-doc.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/init-design-doc

Интерактивный wizard для создания design-doc.md. Запускается в начале каждого нового проекта.

Usage

/init-design-doc
/init-design-doc --from-file client-brief.pdf
/init-design-doc --from-file brief.pdf --from-file data-sample.xlsx

What This Command Does

Ведёт разработчика через серию вопросов и создаёт полностью заполненный design-doc.md с заполненными секциями 0–5 и заготовками для секций 6–9.

Instructions for Claude Code

Step 1: Collect inputs

Если переданы файлы через --from-file:

Вызови multimodal-analyzer агент для каждого файла
Сформируй предварительный контекст перед вопросами

Step 2: Ask structured questions (one block at a time)

Задавай вопросы блоками — не все сразу. После каждого блока жди ответа.

Блок A — Суть проекта:

1. Что за продукт/сервис мы строим? (одно предложение)
2. Какую конкретную проблему он решает?
3. Кто заказчик / конечный пользователь?
4. Есть ли дедлайн или MVP-дата?

Блок B — Данные и входы:

5. С какими данными работает система? (тип, формат, объём)
6. Данные уже есть или будут предоставлены позже?
7. Есть ли чувствительные данные (ПД, медицина, финансы)?

Блок C — Функциональность:

8. Опиши 3–5 основных сценария использования (кто делает что и зачем)
9. Что система точно НЕ должна делать? (scope out)
10. Как выглядит успех? Как мы поймём что система работает хорошо?

Блок D — Технические ограничения:

11. Ожидаемая нагрузка (пользователей, запросов/сек)?
12. Требования к latency (допустимое время ответа)?
13. Нужен ли фронтенд или только API?
14. Деплой куда? (YC VM / K8s / локально)

Step 3: Fill the template

Возьми templates/design-doc.md и заполни его на основе ответов:

Секции 0–5: заполнить полностью из ответов
Секции 6–9: оставить как заготовки с [TBD] где нужна дополнительная проработка
Каждый TBD должен объяснять что нужно решить и почему это открытый вопрос

Step 4: Generate open questions

На основе пробелов в ответах сформируй секцию 9 (Open Technical Questions) и 1.5 (Open Business Questions).

Read the full file on GitHub · 90 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.

8d ago First seen · 90 lines · 0 tokens per session scan A bb1979604d79

Subscribe to this mod's changes

init-design-doc is a command published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 807 tokens. 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.

MLOps Planning Writing and docs ai ai-agents cicd hooks ml

sonarqube

Analyze SonarCloud quality issues for a specific PR.

FlorianBruniaux/claude-code-plugins · 14 tokens

plan-start

5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.

FlorianBruniaux/claude-code-plugins · 39 tokens

refactor

Analyze code for SOLID violations and suggest targeted improvements.

FlorianBruniaux/claude-code-plugins · 13 tokens

update

Use when: search results seem noisy or for periodic memory maintenance.

sdsrss/claude-mem-lite · 14 tokens

reconcile

Establish git ground truth (branch, status, stashes, worktrees, ahead/behind) before any mutation, halt on protected or destructive operations, then carry the known-good state through a single-concern commit, a push, an open PR, and — after the PR merges — a fast-forward of the default branch. Enforces Law 1 (Research…

naimkatiman/continuous-improvement · 80 tokens

content-start

Content production session start command. Gives the daily content session a structured start, shows pending work, and sets priorities.

fatihkan/badi · 0 tokens

claude-scaffold: Command for Claude Code