dev-design

dev-design is a skill for Claude Code, Codex from BlueprintOS/analysis-to-delivery. It costs 68 tokens per session (1,790 once invoked), scanned A, original, MIT.

A development-design workflow that turns an approved product requirements document into technical specifications, data models, implementation guidance, and design review documents.

In plain words
What is it for?
It is for designing modules, interfaces, state changes, database tables, migrations, layered architecture, and implementation tasks before quality review and development.
Why use it?
It connects product requirements to implementable technical details while checking fields, database syntax, architecture rules, and referenced project guidance.

Skill for Claude CodeCodex

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 skills/blueprintos/analysis-to-delivery/dev-design
Any agent
npx skills add BlueprintOS/analysis-to-delivery --skill dev-design
Clone the repo
git clone --depth 1 https://github.com/BlueprintOS/analysis-to-delivery

Made for: Claude Code, Codex.

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 dev-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/dev-design.svg)](https://agentmods.dev/skills/blueprintos/analysis-to-delivery/dev-design)
Your own site
<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/dev-design"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/dev-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,790 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00068 $0.01790
Opus 5 $0.00034 $0.00895
Sonnet 5 $0.00014 $0.00358
Haiku 4.5 $0.00007 $0.00179

Measured 5d ago against content hash 3a06b7374df6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dev-design scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/user-invoked/dev-design/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev-Design — 开发设计(7 件套)

Contract

  • 输入: 已签字的 05-产品需求文档 PRD.mdpaths/knowledge-path.mdpaths/tech-stack-path.mdpaths/doc-naming-path.md
  • 输出: AGENTS.md02-功能规格说明书 FSD.md03-数据模型设计.md06-开发设计说明书.md08-设计回测报告.md、可选 RETRO_任务复盘汇总.md
  • 门控: 字段对齐通过;SQL 方言检查通过;设计回测通过;用户签字
  • Required rules: stage-gate, no-field-guessing, no-self-invent, sql-dialect, doc-numbering, context-pointer, goal-boundary
  • Required paths: knowledge-path, tech-stack-path, doc-naming-path
  • 下一步: /qa-audit

适用场景

  • PRD 已签字
  • 需要把产品需求翻译成技术实现方案
  • 含数据模型、接口契约、前后端实现细节

流程步骤

§1. AGENTS.md(项目级 AI 助手配置)

  • 加载 templates/AGENTS.md
  • 在项目根生成,内容:
    • 项目约束
    • 文档索引
    • 分层架构规则
    • 关键纪律引用(no-field-guessing / stage-gate 等)
  • 渐进式披露:地图而非手册

§2. FSD(功能规格说明书)

加载 templates/FSD.md,生成 02-功能规格说明书 FSD.md:

  • 模块清单
  • 功能详述(输入/输出/业务规则/边界条件/异常路径)
  • 接口契约(REST/RPC/消息,含入参出参错误码)
  • 状态机(关键业务对象的状态流转)
  • 数据模型概览
  • 业务错误码字典

§3. 数据模型设计

加载 templates/数据模型设计.md,生成 03-数据模型设计.md:

  • 表清单(新增 / 扩展)
  • 表结构(字段、类型、可空、默认值、注释、索引)
  • 序列定义
  • 字段对齐验证(与知识库核对)
  • 初始化数据
  • 迁移脚本(如适用)

§4. 开发设计说明书(代码实现版)

加载 templates/开发设计说明书.md,生成 06-开发设计说明书.md:

  • 架构设计(分层、关键依赖)
  • 后端分层(Controller / Service / Repository / Entity / Mapper XML / DTO/VO)
  • 事务与异常处理
  • 前端组件(PC + APP,按需)
  • 联调说明(接口清单、步骤、Mock 数据)
  • 错误码映射
  • Checklist

关键纪律:

  • 严禁只写后端(必须含前端 + 联调 + Mock)
  • 严禁降级为伪代码 / TODO 列表
  • 字段名 / 表名 / 状态码必须与知识库一致

§5. 设计回测(HARD GATE)

触发条件(满足任一即必做):

  • 数据模型有新增/扩展表
  • 业务规则新增/修改
  • 状态机新增/修改
  • field-alignment-check.py 报错
  • 合规相关变更

4 大类回测(详见 rules/stage-gate.md):

  1. 数据模型回测 — 跑历史样本验证 DDL / 索引 / 查询
  2. 业务规则回测 — 关键场景样本手工重跑
  3. 状态机回测 — 历史单据状态变化回放
  4. 字段对齐回测 — 文档 vs 知识库 vs 生产库

输出:08-设计回测报告.md

HARD GATE:回测不通过(❌)禁止进入阶段 8。

§6. 子流程门控清单(可选实施扩展)

加载 templates/开发设计说明书.md §六,记录:

子流程 状态 签字 / 时间
brainstorming 设计稿
spec 自检
writing-plans 完成
TDD RED 测试
全部子任务 GREEN

仅在用户明确进入实施扩展模式(走 /using-superpowers 之后)才需要填。

§7. 任务复盘汇总

Read the full file on GitHub · 151 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 · 151 lines · 68 tokens per session scan A 3a06b7374df6

Subscribe to this mod's changes

dev-design is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,790 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

prd-taskmaster

Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…

anombyte93/prd-taskmaster · 80 tokens

execute-task

Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress ->…

anombyte93/prd-taskmaster · 98 tokens

handoff

Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…

anombyte93/prd-taskmaster · 158 tokens

generate

Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…

anombyte93/prd-taskmaster · 91 tokens

discover

Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…

anombyte93/prd-taskmaster · 92 tokens

execute-fleet

Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.

anombyte93/prd-taskmaster · 52 tokens