What is standard-team?

A Chinese-language playbook for coordinating a full software project through 11 phases, from requirements and architecture to implementation, testing, and release.

It helps coordinate product planning, system design, database work, backend and frontend development, deployment, and evidence-based quality checks.

It gives a development team a shared sequence, defined responsibilities, interface agreements, and checks after each task.

standard-team — Skill for Claude Code and Codex by xuanbingbingo

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.

Any agent

npx skills add xuanbingbingo/claude-standard-dev-team --skill standard-team

Clone the repo

git clone --depth 1 https://github.com/xuanbingbingo/claude-standard-dev-team

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xuanbingbingo/claude-standard-dev-team/standard-team/github.svg)](https://agentmods.dev/skills/xuanbingbingo/claude-standard-dev-team/standard-team)

Your own site

<a href="https://agentmods.dev/skills/xuanbingbingo/claude-standard-dev-team/standard-team"><img src="https://agentmods.dev/badge/skills/xuanbingbingo/claude-standard-dev-team/standard-team/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xuanbingbingo/claude-standard-dev-team/standard-team"><img src="https://agentmods.dev/badge/skills/xuanbingbingo/claude-standard-dev-team/standard-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,111 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00172	$0.10111
Opus 5.5	$0.00069	$0.04044
Sonnet 5.5	$0.00034	$0.02022
Haiku 4.5	$0.00017	$0.01011

Measured 7d ago against content hash 922a146409a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

standard-team scanned grade B with 2 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 7d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- ❌ `rm -rf` 残留目录从零开始 → 浪费已完成的工作

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- grep：fetch('/api、axios.get('/api、axios.post('/api 等

skills/standard-team/SKILL.md · 822 lines

How it starts

The opening of the file, as written. The whole thing — 822 lines — stays where its author put it; the contents beside it link to each section on GitHub.

标准开发团队总指挥剧本

执行模型：本 skill 是主会话执行的剧本，不是一个独立运行的 agent。主会话读完本剧本后，用 Task 工具直接派遣 12 个成员 agent（按下方 Phase 0-11 顺序），可并行的并行。

为什么是 skill 不是 agent：Claude Code 平台限制 —— subagent 不能 spawn 其他 subagent，Task 工具会被运行时强制剥离。所以"总指挥"必须由主会话亲自担任，剧本以 skill 形式装载。详见 reference_subagent_nesting_proof.md（5-8 沙箱实测铁证）。

角色定义

你（主会话）是总指挥，整合两种质量保障机制：

契约层（事前）：强迫所有 agent 在动手前对齐接口和数据结构
Dev-QA Loop（事中）：每个任务实现后立即由 EvidenceCollector 验证

你不写任何业务代码。你的职责是调度、传递契约、决策打回。所有过程产出的 md 文件,都使用中文来描述

团队成员（全部来自标准团队 agents/）

规划层

Agent	来源文件	职责
`product-manager`	product-manager.md	PRD、用户故事、MVP范围
`software-architect`	software-architect.md	技术选型、系统设计、契约生成

实现层

Agent	来源文件	职责
`database-optimizer`	database-optimizer.md	Schema、migrations、索引
`backend-architect`	backend-architect.md	API实现、业务逻辑
`ui-designer`	ui-designer.md	设计规范、颜色/字体/间距体系、组件视觉规范
`frontend-developer`	frontend-developer.md	UI、组件、接口调用
`devops-automator`	devops-automator.md	Docker、CI/CD、部署配置

质量层

Agent	来源文件	职责
`testing-evidence-collector`	testing-evidence-collector.md	任务级静态核查QA（typecheck/grep/单测，无浏览器/截图），PASS/FAIL决策
`security-engineer`	security-engineer.md	安全扫描
`code-reviewer`	code-reviewer.md	代码规范review
`reality-checker`	reality-checker.md	最终上线前整体验收

文档层

Agent	来源文件	职责
`technical-writer`	technical-writer.md	README、API文档

完整执行流程

► Audit 模式（已有代码审查）

触发方式：用户说"审查 xxx 项目"、"audit xxx"、"检查现有代码"时进入此模式，不走 Phase 0–11。

Audit-1：代码审查

调用 code-reviewer

输入：项目源码目录（用户指定，或默认当前工作目录）
重点检查（除常规项外，必须额外扫描）：

  Step 0 - 先侦察项目的部署方式：
    - 是否配置了子路径部署？（next.config basePath / vite.config base / nginx location 前缀）
    - 前端框架是什么？（Next.js / Vue / React / 其他）
    - 是否有服务端跳转逻辑？（middleware / proxy / 路由守卫 / 后端 redirect）
    → 根据侦察结果决定检查哪些文件和模式，不要假设文件名

  Step 1 - 若有子路径部署，检查所有跳转 / 重定向：
    - grep 关键词：redirect、router.push、router.replace、navigate、
      location.href、window.location、Response.redirect、NextResponse.redirect
    - 对每一处：目标路径是否正确携带了部署前缀？
      （框架路由方法通常自动补前缀；直接构造 URL 字符串时最容易丢失）

  Step 2 - 检查 API 请求路径是否硬编码：
    - grep：fetch('/api、axios.get('/api、axios.post('/api 等
    - 应使用环境变量前缀（VITE_API_BASE / NEXT_PUBLIC_BASE_PATH / 项目自定义变量）

  Step 3 - 常规 Blocker 项（安全、契约、错误处理等）

产出：docs/REVIEW_REPORT.md

Read the full file on GitHub · 822 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.

7d ago Changed · +222 lines · +71 tokens per session scan C → B 922a146409a6
2mo ago First seen · 600 lines · 101 tokens per session scan C 02d2bdb58740

Subscribe to this mod's changes

standard-team is a skill published in the GitHub repository xuanbingbingo/claude-standard-dev-team (106 stars, last pushed 7d ago), licensed MIT. It adds 172 tokens to every session and 10,111 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Planning

standard-team next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
standard-teamxuanbingbingo/claude-standard-dev-team	Skill	106	7d ago	MIT	B	172	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code

standard-team