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 xuanbingbingo/claude-standard-dev-team --skill standard-teamgit clone --depth 1 https://github.com/xuanbingbingo/claude-standard-dev-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/xuanbingbingo/claude-standard-dev-team/standard-team)<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.
<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>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 | $0.00101 | $0.06045 |
| Opus 5 | $0.00051 | $0.03023 |
| Sonnet 5 | $0.00020 | $0.01209 |
| Haiku 4.5 | $0.00010 | $0.00605 |
Grade C, and why
standard-team scanned grade C 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 11d 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 deletehighDestructive 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 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 How it starts
The opening of the file, as written. The whole thing — 600 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
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.
- 11d ago First seen · 600 lines · 101 tokens per session scan C 02d2bdb58740
standard-team is a skill published in the GitHub repository xuanbingbingo/claude-standard-dev-team (101 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 6,045 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C 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.
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…