design-brief

design-brief is a command for Claude Code from dhslegen/digital-delivery-team. It costs 32 tokens per session (2,326 once invoked), scanned B, original, MIT.

A command that combines a product requirements document, an API contract, technology details, and user attachments into a single design brief. An API contract describes how software parts communicate.

In plain words
What is it for?
Use it to create docs/design-brief.md and related design records from the project’s requirements, API definition, technology stack, and attachments. It can also show a dry-run of the planned outputs.
Why use it?
It gathers design inputs into one agreed reference file instead of leaving them scattered across several documents. It also prepares material for later design execution through supported channels.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument.

Part of the digital-delivery-team plugin — 13 skills, 21 commands, 9 agents, 8 hooks shipped together

Good fit Use it to create docs/design-brief.md and related design records from the project’s requirements, API definition, technology stack, and attachments. It can also show a dry-run of the planned outputs.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dhslegen/digital-delivery-team/design-brief
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.

Clone the repo
git clone --depth 1 https://github.com/dhslegen/digital-delivery-team

Made for: Claude Code.

Or install digital-delivery-team, the plugin that ships this one along with the rest of its 13 skills, 21 commands, 9 agents, 8 hooks.

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 design-brief

README.md
[![agentmods](https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design-brief/github.svg)](https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-brief)
Your own site
<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-brief"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design-brief/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 design-brief

Your own site · 80×15
<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-brief"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00032 $0.02326
Opus 5 $0.00016 $0.01163
Sonnet 5 $0.00006 $0.00465
Haiku 4.5 $0.00003 $0.00233

Measured 9d ago against content hash d2a7a4db798d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

design-brief scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)
commands/design-brief.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-brief

输入:$ARGUMENTS

docs/prd.md + docs/api-contract.yaml + .ddt/tech-stack.json + 用户附件,编译为 docs/design-brief.md(10 字段 SSoT),并准备好供 /design-execute 派生 3 通道(claude-design / figma / v0)的输入材料。


Phase 1 — 前置校验

git rev-parse --is-inside-work-tree 2>/dev/null || { echo "❌ 非 git 仓库"; exit 1; }

[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT="${HOME}/.claude/plugins/marketplaces/digital-delivery-team"
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || { echo "❌ DDT plugin root 未解析。可能原因:(1) 插件未安装;(2) shell 中 DDT_PLUGIN_ROOT 指向无效路径,请 unset DDT_PLUGIN_ROOT 后重启会话;(3) 运行 /digital-delivery-team:doctor 自检"; exit 1; }
export DDT_PLUGIN_ROOT

if printf '%s' "$ARGUMENTS" | grep -q -- '--dry-run'; then
  node "$DDT_PLUGIN_ROOT/bin/print-dry-run.mjs" --phase design-brief --inputs "docs/prd.md,docs/api-contract.yaml,.ddt/tech-stack.json" --outputs "docs/design-brief.md,.ddt/design/tokens.json,.ddt/design/components-inventory.md" --next "/design-execute --channel claude-design"
  exit 0
fi
node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase design-brief --action start
"$DDT_PLUGIN_ROOT/bin/check-blockers.sh" || exit 2

# 必需输入校验
test -f docs/prd.md           || { echo "❌ 请先运行 /prd 生成 docs/prd.md"; exit 1; }
test -f docs/api-contract.yaml || { echo "❌ 请先运行 /design 生成 docs/api-contract.yaml"; exit 1; }
test -f .ddt/tech-stack.json   || { echo "❌ 请先运行 /design(会写入 .ddt/tech-stack.json)"; exit 1; }

# frontend.type 三态检查(PR-E):仅 spa 才需要 brief
FRONT_TYPE=$(node "$DDT_PLUGIN_ROOT/bin/get-frontend-type.mjs" 2>/dev/null)
if [ "$FRONT_TYPE" = "server-side" ] || [ "$FRONT_TYPE" = "none" ]; then
  echo "ℹ️  frontend.type=$FRONT_TYPE,/design-brief 跳过:服务端渲染由 /build-api 处理;纯 API/CLI 无前端工程。"
  node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase design-brief --action end
  exit 0
fi

Phase 2 — 编译 Brief

# 解析 --refresh 与 --visual-direction(透传给编译器)
COMPILE_ARGS=""
printf '%s' "$ARGUMENTS" | grep -q -- '--refresh' && COMPILE_ARGS="$COMPILE_ARGS --refresh"
VD=$(printf '%s' "$ARGUMENTS" | grep -oE -- '--visual-direction [a-z-]+' | awk '{print $2}')
if [ -n "$VD" ]; then COMPILE_ARGS="$COMPILE_ARGS --visual-direction $VD"; fi

node "$DDT_PLUGIN_ROOT/bin/compile-design-brief.mjs" $COMPILE_ARGS || exit 4

Read the full file on GitHub · 184 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.

  1. 9d ago First seen · 184 lines · 32 tokens per session scan B d2a7a4db798d

Subscribe to this mod's changes

design-brief is a command published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 2,326 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.