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 vien-meng/vien-skills --skill generic-dev-sopgit clone --depth 1 https://github.com/vien-meng/vien-skillsWrote 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/vien-meng/vien-skills/generic-dev-sop)<a href="https://agentmods.dev/skills/vien-meng/vien-skills/generic-dev-sop"><img src="https://agentmods.dev/badge/skills/vien-meng/vien-skills/generic-dev-sop/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/vien-meng/vien-skills/generic-dev-sop"><img src="https://agentmods.dev/badge/skills/vien-meng/vien-skills/generic-dev-sop.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 | $0.00117 | $0.04102 |
| Opus 5 | $0.00059 | $0.02051 |
| Sonnet 5 | $0.00023 | $0.00820 |
| Haiku 4.5 | $0.00012 | $0.00410 |
Grade A, and why
generic-dev-sop 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
通用项目开发 SOP
把每项功能作为「计划、契约、UI、实现、测试、证据」同步交付的可追踪闭环;把整个项目作为「底座 → 纵向切片 → 阶段门禁」的迭代推进。除纯文案、无行为变化的单行修改外,不得跳过步骤;没有 UI 的后端/基础设施功能可跳过视觉设计稿,但必须在开发记录中说明原因。
适用场景与边界
该用:从零搭建并完整交付的新项目(前端 / 后端 / 跨端客户端 / 服务端);需要规范化流程、多角色协作与质量门禁的中大型项目;希望每个功能「计划 → 实现 → 测试 → 证据」可追溯的团队。
已有项目迭代:不重新搭建,复用现有架构决策与质量底座;每个新需求仍按「分析需求 → 补充 UI 设计稿 → 划入任务计划(功能矩阵定 P0/P1/P2)→ 开发 → 审查验收」的第三部分闭环推进。计划缺失时先补最小计划(见第三部分第 1 步)。
不该用:纯文案或无行为变化的单行修改;已有仓库的快速小改动;一次性脚本、Demo、原型验证。这些场景直接改代码即可,不必走完整 SOP。
轻量用法:小型项目可只走「项目搭建 + 任务计划 + 单功能闭环」,跳过「完整交付」中的灰度、合规、回滚演练等门禁,并在 README 记录跳过原因。
快速上手
- 说「用这个 SOP 从零搭一个 XX 项目」,并指定技术栈(或回车采用
default-stack.md默认组合)。 - 按
architecture-template.md产出架构决策,按task-plan-template.md产出任务计划。 - 每个功能按「第三部分」闭环交付,记录写入
references/features/<功能短名>.md。 - P0 全绿后走「第四部分」发布候选、灰度回滚与交付检查。
状态仅使用:未开始、分析中、设计确认、开发中、审查测试中、已完成、阻塞。
生命周期总览
新项目按四步推进,功能闭环可循环执行,直到 P0 全部完成再进入交付:
一、项目搭建(架构决策 + 质量底座 + 记录机制)
→ 二、详细任务计划(阶段 / 任务 / 验收 / 门禁)
→ 三、单功能开发闭环 × N(确认计划→需求→方案→记录→设计稿→数据→开发→审查→回写)
→ 四、完整交付(发布候选 → 灰度回滚 → 文档同步 → 项目交付检查)
第一部分:项目搭建
新项目先搭底座,不直接堆业务页面。
1. 确认工程边界
- 新工程放独立目录、独立 package 边界;旧仓库只读,只作为功能与行为基线,禁止复制、import 或 workspace-link 旧实现。
- 固定包管理器与锁文件,全仓统一;开发与 CI 使用同一安装命令。
- 先确认新工程根目录,不要在旧仓库内覆盖创建。
2. 确认技术栈
启动开发前先与用户确认技术栈,避免中途返工:
- 按项目形态展示
references/default-stack.md的默认组合作为推荐(Web/桌面、跨端移动、服务端各一套)。 - 用户指定技术栈(如「用 Vue」「用 Go」)→ 记录并以用户为准,写进
references/architecture.md的「固定技术栈」节。 - 用户未指定或直接回车跳过 → 视为同意使用默认,采用
references/default-stack.md的组合,并在架构决策中注明「默认技术栈,用户已确认跳过选型」。 - 确认结果与理由写入架构决策;后续所有实现按该栈执行,不重复争论选型。
3. 输出架构决策(按 references/architecture-template.md 创建 references/architecture.md)
- 产品边界:P0/P1/P2 与「明确不做」清单,冻结首版范围。
- 固定技术栈与理由;优先复用团队已验证的框架、分层与平台桥接模式,不重复发明。
- 技术栈选型:用户指定则以用户为准;未指定时默认采用
references/default-stack.md的已验证组合,不重复争论选型。 - 目录结构与职责边界:技术职责先分层,业务再按模块归档;写入「允许/禁止」对照。
- 数据模型:主库选择、核心表/模型、稳定 ID 与时间约定、迁移与兼容策略。
- 接口契约:API 前缀、统一错误码格式、鉴权/RBAC、实时事件边界。
- 安全与隐私底线:密钥只存环境变量、日志脱敏、最小权限、审计留痕。
- 可行性风险与决策门:每项高风险能力列出 J0 必须验证的门槛。
- 决策结果写入
references/architecture.md,作为后续所有实现的依据;有改动同步更新。
What ships with it
6 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.
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 · 245 lines · 117 tokens per session scan A ea5cec493f7d
generic-dev-sop is a skill published in the GitHub repository vien-meng/vien-skills (10 stars, last pushed 27d ago), licensed Apache-2.0. It adds 117 tokens to every session and 4,102 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…