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/designgit 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)<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/design"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/design.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 | $0.00022 | $0.02851 |
| Opus 5 | $0.00011 | $0.01425 |
| Sonnet 5 | $0.00004 | $0.00570 |
| Haiku 4.5 | $0.00002 | $0.00285 |
Grade B, and why
design scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design
输入:$ARGUMENTS
Phase 1 — 前置校验
test -f docs/prd.md || { echo "❌ docs/prd.md 不存在,请先运行 /prd"; exit 1; }
test -f docs/wbs.md || { echo "❌ docs/wbs.md 不存在,请先运行 /wbs"; exit 1; }
[ -f "$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 "$DDT_PLUGIN_ROOT/bin/print-dry-run.mjs" --phase design --inputs "docs/prd.md,docs/wbs.md,project-brief.md" --outputs "docs/arch.md,docs/api-contract.yaml,docs/data-model.md,.ddt/tech-stack.json" --next "/design-brief (spa) | /impl (server-side|none)"
exit 0
fi
node "$DDT_PLUGIN_ROOT/bin/emit-phase.mjs" --phase design --action start
"$DDT_PLUGIN_ROOT/bin/check-blockers.sh" || exit 2
若 docs/api-contract.yaml 已存在且未传 --refresh,进入增量修订模式。
Phase 2 — 解析技术栈(M3-3 优先级链 + M6.3 交互式问卷)
Step 2a:先尝试自动解析
# 提取参数中的 --preset 与 --ai-design(如果有)
PRESET_FLAG=$(printf '%s' "$ARGUMENTS" | grep -oE -- '--preset [a-zA-Z0-9_-]+' | head -1 | awk '{print $2}')
AIDESIGN_FLAG=$(printf '%s' "$ARGUMENTS" | grep -oE -- '--ai-design [a-zA-Z0-9_-]+' | head -1 | awk '{print $2}')
node "$DDT_PLUGIN_ROOT/bin/resolve-tech-stack.mjs" \
${PRESET_FLAG:+--preset "$PRESET_FLAG"} \
${AIDESIGN_FLAG:+--ai-design "$AIDESIGN_FLAG"} \
--write
Step 2b:M6.3 交互式问卷(关键)
LLM 必须执行:检查 project-brief.md 中的 "技术栈预设" 字段:
- 若值为
interactive或custom:必须用AskUserQuestion工具发起 Spring Initializr 等价 4 步问卷 - 若值为具体 preset(如
java-modern)但project-brief.md同时含 "后端框架"、"前端框架"等具体字段且与 preset 默认值冲突:用 AskUserQuestion 问 1 题确认偏好 - 若值为
none或interactive且 brief 无具体字段:强制走 4 步问卷,不允许 LLM 自行选栈
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 · 248 lines · 22 tokens per session scan B 8bd57c2925dd
design is a command published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 2,851 once invoked, about $0.0001 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
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.
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.
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.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
init-scaffolding
Bootstrap a new project with the scaffolding CLAUDE.md, settings.json, and .scaffolding/ directory structure.