design-execute

design-execute is a command for coding agents from dhslegen/digital-delivery-team. It costs 36 tokens per session (3,367 once invoked), scanned B, original, MIT.

A command that turns a design brief into an attachment package and instructions for Claude Design, Figma, or v0, tools used to create interface designs. It then accepts the returned design source for use in a web project.

In plain words
What is it for?
Use it to prepare design-tool inputs, run a dry run of the handoff, or bring a returned design bundle or URL into the project's web folder.
Why use it?
It organizes the handoff between a written design brief and an external design tool, so the required files and prompts are prepared consistently. It also checks that the project and supporting setup are available.

Command

Part of the digital-delivery-team plugin — 13 skills, 21 commands, 9 agents, 8 hooks 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/dhslegen/digital-delivery-team/design-execute
Clone the repo
git clone --depth 1 https://github.com/dhslegen/digital-delivery-team

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-execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design-execute.svg)](https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-execute)
Your own site
<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-execute"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00036 $0.03367
Opus 5 $0.00018 $0.01684
Sonnet 5 $0.00007 $0.00673
Haiku 4.5 $0.00004 $0.00337

Measured 5d ago against content hash 0a21a167f05b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

design-execute 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 5d 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-execute.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-execute

输入:$ARGUMENTS

docs/design-brief.md(10 字段 SSoT)派生为目标通道的附件包 + 通道专属 prompt,引导用户投喂工具,等用户回贴设计源后摄取到 web/


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-execute --inputs "docs/design-brief.md,.ddt/tech-stack.json,.ddt/design/tokens.json" --outputs ".ddt/design/<channel>/upload-package,.ddt/design/<channel>/prompt.md (派发) | .ddt/design/<channel>/raw/ (摄取)" --next "(派发) 等用户回贴 → /design-execute --bundle <zip> | --url <url> ; (摄取后) /build-web"
  exit 0
fi
node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase design-execute --action start
"$DDT_PLUGIN_ROOT/bin/check-blockers.sh" || exit 2

# 必需输入校验
test -f docs/design-brief.md || { echo "❌ 请先运行 /design-brief 生成 brief"; exit 1; }

# frontend.type 三态检查(PR-E)
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=$FRONT_TYPE,/design-execute 跳过:服务端渲染由 /build-api 处理。"
  node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase design-execute --action end
  exit 0
fi

Phase 2 — 解析参数

# 通道:默认 claude-design(首选默认,零外部账号)
CHANNEL=$(printf '%s' "$ARGUMENTS" | grep -oE -- '--channel [a-z0-9-]+' | awk '{print $2}')
CHANNEL=${CHANNEL:-claude-design}

# 外部回贴源(可选,等用户在通道完成后再传)
# W7.5 R9:用 bin/parse-cli-flag.mjs 解析含空格路径 + 单/双引号(grep [^ ]+ 会截断)
BUNDLE_PATH=$(node "$DDT_PLUGIN_ROOT/bin/parse-cli-flag.mjs" --flag bundle -- "$ARGUMENTS")
URL=$(node "$DDT_PLUGIN_ROOT/bin/parse-cli-flag.mjs" --flag url -- "$ARGUMENTS")

# B4: URL 白名单校验(防 shell 注入;只允许 http/https + 标准 URL 字符)
if [ -n "$URL" ] && ! printf '%s' "$URL" | grep -qE '^https?://[A-Za-z0-9._~:/?#@!$&'\''()*+,;=%-]+$'; then
  echo "❌ --url 含非法字符或非 http(s) 协议,已拒绝(防 shell 注入)"; exit 1
fi

# 派生 / 摄取分支:
#   - 无 --bundle 与 --url:派生附件包 + 提示用户操作
#   - 有 --bundle <zip>:摄取 zip(仅 claude-design 通道支持)
#   - 有 --url:摄取 share URL(figma / v0 通道)
case "$CHANNEL" in
  claude-design|figma|v0) ;;
  all) [ -n "$BUNDLE_PATH" ] && { echo "❌ --channel all 不可与 --bundle 同时使用"; exit 1; }
       [ -n "$URL" ]         && { echo "❌ --channel all 不可与 --url 同时使用"; exit 1; } ;;
  *) echo "❌ --channel 必须是 claude-design / figma / v0 / all(实测:$CHANNEL)"; exit 1 ;;
esac

Read the full file on GitHub · 278 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. 5d ago First seen · 278 lines · 36 tokens per session scan B 0a21a167f05b

Subscribe to this mod's changes

design-execute is a command published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 3,367 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.