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.
npx agentmods add commands/dhslegen/digital-delivery-team/design-executegit clone --depth 1 https://github.com/dhslegen/digital-delivery-teamWrote 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.
[](https://agentmods.dev/commands/dhslegen/digital-delivery-team/design-execute)<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>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 | $0.00036 | $0.03367 |
| Opus 5 | $0.00018 | $0.01684 |
| Sonnet 5 | $0.00007 | $0.00673 |
| Haiku 4.5 | $0.00004 | $0.00337 |
Grade B, and why
design-execute scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null) 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:$ARGUMENTS
把 docs/design-brief.md(10 字段 SSoT)派生为目标通道的附件包 + 通道专属 prompt,引导用户投喂工具,等用户回贴设计源后摄取到 web/。
Phase 1 — 前置校验
git rev-parse --is-inside-work-tree 2>/dev/null || { echo "❌ 非 git 仓库"; exit 1; }
[ -f "$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
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.
- 5d ago First seen · 278 lines · 36 tokens per session scan B 0a21a167f05b
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.
Other commands, from other repositories
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
duck-off
Turn off Rubber Duck mode and answer normally.
create-topic
Research and generate a complete topic plan with keyword mapping, audience, angle, and competitive positioning.
extensions
Show what the connected context expects to reach, and whether this machine provides it.