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 skills add dhslegen/digital-delivery-team --skill ddt-brief-buildergit 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/skills/dhslegen/digital-delivery-team/ddt-brief-builder)<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/ddt-brief-builder"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/ddt-brief-builder/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.
<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/ddt-brief-builder"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/ddt-brief-builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00351 | $0.04820 |
| Opus 5 | $0.00176 | $0.02410 |
| Sonnet 5 | $0.00070 | $0.00964 |
| Haiku 4.5 | $0.00035 | $0.00482 |
Grade B, and why
ddt-brief-builder scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PR="${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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DDT Brief Builder · 工作流第零步
使命：把任意非结构化输入转成 DDT 标准
project-brief.md，让/prd一跑即过、不卡。 设计 KPI（v0.9.4 实战驱动）：从一句话 → 可启动 DDT 全流程 ≤ 90 秒、≤ 5 步互动。 范围：仅产出project-brief.md（可选附带项目目录脚手）。后续工作流由 DDT 各 phase 命令处理。
何时触发
| 用户场景 | 处理 |
|---|---|
| 显式要求："帮我写 brief" / "DDT 第零步" / "启动 alv-ops" | 主流程 |
| 粘贴非结构化需求 + 提到 DDT / 比赛 / 测试项目 | 主流程 |
| 给 URL / 文件 + 问"能用 DDT 开始吗" | 主流程 |
| 已有 PRD + "DDT 让我先填 brief" | 反向提炼模式 |
| 人员表 / 工时表 / 项目计划（独立给出，无 brief 上下文） | 改触发姊妹 skill ddt-baseline-sync |
不触发：
- 已有
project-brief.md且只想刷新 → 直接/prd --refresh - 提到
/design-brief→ 那是 v0.8 设计阶段，与本 skill 无关
输入识别（开场第一步）
| 类型 | 信号 | 处理 |
|---|---|---|
| A 自然语言描述 | 对话直接给文本（≥ 50 字） | 直接提取字段 |
| B 本地文件路径 | .md .pdf .docx .txt |
用 Read 读取 |
| C URL | http(s):// |
用 WebFetch 拉取 |
| D 已有 PRD | 提到 "PRD" / "需求文档" / 路径含 prd.md |
反向提炼：从详细 PRD 向上抽象 |
| E 比赛官网 / 题目 | 含"比赛" / "hackathon" / "评分标准" | 评分项作硬指标 + 历届作品作参考 |
| F 项目截图 / 草图 | 上传图片 | Read 看图后提 UI 线索作 §核心功能 |
| G 多源混合 | 同时多类 | 按 PRD/URL > 文件 > 文字优先级合并 |
| H 会议纪要 / 评审记录 | 含"会议" / "纪要" / "※" / "目标上线日" / "客户代表" | 客户驱动模式：会议确认范围作硬约束；§2 用户分甲方/乙方 |
| I xlsx / csv 功能清单 | 文件名含"功能清单" / "feature-list" / "需求" | 自动 dump：见下方 §"如何调脚本（绝对路径）"，跑 dump-xlsx.py |
| J 第三方 API 文档（v0.9.8 D25） | 目录名含 API / 开放平台 / SDK / OpenAPI / swagger / 集成规约 / 对接文档；或单 yaml/json 含 openapi: 顶层；或单 md 含 ## GET /xxx 章节 |
自动 dump 进 §11 集成依赖：跑 dump-api-docs.mjs，强制脱敏后注入 brief。详见 $DDT_PLUGIN_ROOT/skills/ddt-brief-builder/references/integration-detection.md |
识别后必须先告知用户："识别到 ⟨类型⟩，将走 ⟨路径⟩ 提取字段"——给用户机会纠正。
如何调用本 skill 的 scripts/（v0.9.5 D22）
LLM 跑 Bash 时 cwd 是用户项目根，不是 skill 根——必须用绝对路径调本 skill 的脚本：
# 推荐：先解析 plugin root（marker 文件 fallback chain）
PR="${DDT_PLUGIN_ROOT:-$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)}"
PR="${PR:-${HOME}/.claude/plugins/marketplaces/digital-delivery-team}"
# 然后调本 skill 的脚本（统一前缀 $PR/skills/ddt-brief-builder/scripts/）
python3 "$PR/skills/ddt-brief-builder/scripts/dump-xlsx.py" <path>
node "$PR/skills/ddt-brief-builder/scripts/dump-api-docs.mjs" <path> # v0.9.8 D25
node "$PR/skills/ddt-brief-builder/scripts/check-brief-quality.mjs" <brief-path>
node "$PR/skills/ddt-brief-builder/scripts/scaffold-brief.mjs" --target <dir> --brief <brief-path>
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/from-api-docs-folder.md 5.7 KB
- examples/from-competition-url.md 7.6 KB
- examples/from-existing-prd.md 3.4 KB
- examples/from-meeting-minutes.md 13 KB
- examples/from-paragraph.md 5.2 KB
- references/ai-design-quick-pick.md 4.7 KB
- references/decision-gates.md 4.8 KB
- references/field-rules.md 14 KB
- references/integration-detection.md 3.7 KB
- references/tech-stack-quick-pick.md 4.1 KB
- references/ui-library-by-scenario.md 4.3 KB
- scripts/check-brief-quality.mjs 11 KB runs code
- scripts/dump-api-docs.mjs 17 KB runs code
- scripts/dump-xlsx.py 4.1 KB runs code
- scripts/scaffold-brief.mjs 5.2 KB runs code
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.
- 10d ago First seen · 242 lines · 351 tokens per session scan B e3792445d488
ddt-brief-builder is a skill published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 351 tokens to every session and 4,820 once invoked, about $0.0018 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 skills, from other repositories
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
team-memory-protocol
A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.
handdrawn-diagram
Generate a hand-drawn (sketch-style) architecture or flow diagram as a committable image (SVG + PNG). Use when the user wants a sketch-aesthetic diagram for a README, docs, or hackathon/Devpost submission that still has correct, legible text and per-group color. Authors a Mermaid look:handDrawn source and renders it…
code-review-levels
Reference documents for deep code review (Level 3) and architecture review (Level 4). Used by code-reviewer agent for advanced review levels.
access
Manage who may drive telegram-topics sessions — view and edit the user allowlist. Use when the user asks to allow or remove a Telegram user, check who's allowed, or lock the channel down.