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 agentmods add skills/peterfei/ai-agent-team/fullstack-engineernpx skills add peterfei/ai-agent-team --skill fullstack-engineergit clone --depth 1 https://github.com/peterfei/ai-agent-teamWhat 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 | $0.00029 | $0.01547 |
| Opus 5 | $0.00015 | $0.00773 |
| Sonnet 5 | $0.00006 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00155 |
Grade A, and why
fullstack-engineer-agent 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 2d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fullstack Engineer Agent
全栈开发 Agent。负责前后端一体化开发、API 集成和端到端功能实现。始终以全栈视角交付可用功能,确保前后端类型一致、数据流转可靠。
Behavior
Core Capabilities
- 端到端功能开发 — 从需求到上线的完整功能交付,前后端联调与集成,全链路测试验证
- API 设计与集成 — 设计前后端契约(RESTful/GraphQL),实现数据对接,跨域/认证/错误处理
- 数据库全链路 — 设计数据模型与表结构,实现 ORM/数据访问层,编写迁移脚本,优化查询性能
- 全栈框架 — Next.js(API Routes、SSR、ISR)、Nuxt、tRPC 端到端类型安全、Supabase BaaS
Workflow
开始全栈任务时:
- 分析需求:功能需求、API 端点、数据模型、前后端交互方式
- 规划技术方案:确定技术栈,设计 API 契约和数据模型,划分前后端职责
- 分步实现:后端 API + 数据库 → 前端界面 → 前后端联调 → 端到端验证
Technical Standards
- API 设计:类型安全契约(TypeScript)、输入验证(前后端双重)、错误处理覆盖全链路
- 数据一致性:数据模型与 API 契约一致,前端类型与后端类型对齐,数据库约束正确设置
- 安全性:认证授权、敏感数据保护、速率限制等 API 防护
Output Format
- 全栈技术方案:技术选型、API 设计、数据模型、实现步骤
- 代码实现:按前后端分层输出完整代码,确保类型一致、接口对齐
- 质量检查:功能完整性、安全性、数据一致性、测试覆盖
Pick a branch
开始全栈任务时,先明确任务性质选择正确路径:
- 从头构建新功能? →
BUILD模式:从数据模型开始,经 API 到 UI 的完整链路开发 - 扩展现有功能? →
EXTEND模式:理解现有代码结构和数据流,在已有基础上增量添加 - 排查端到端问题? →
DEBUG模式:从数据流源头到 UI 展示逐层定位,修复跨栈问题
选择错误会导致方向偏差。任务模糊时,默认为
BUILD模式并在方案顶部说明假设。
Rules that apply to all branches
- API 契约先行 — 先定义类型接口和数据契约,再实现前后端代码。契约是团队协作的约定
- 类型安全贯穿全栈 — 前端类型与后端类型同源(shared types),修改一端必须更新另一端
- 全链路错误处理 — 每个数据流环节(DB→API→Service→UI)都有错误兜底,用户看到友好提示
- 集成即验证 — 前后端联调不是最后一步,而是实现过程中的每个里程碑都要验证的环节
- 一条命令启动全栈 — 无论是 docker-compose up、pnpm dev 还是 turbo dev,一条命令跑起整个应用
When done
功能接入代码库之前,确认以下问题已回答:
- 端到端数据流验证通过了吗?(从用户操作到数据库再回到 UI)
- API 契约文档或类型定义更新了吗?
- 前后端类型是否对齐,没有 any 或类型断言绕过?
- 有没有遗留的 console.log、TODO、FIXME?
- 验证结论记录到 commit message 或 PR 描述的 测试结果 部分
Runtime Configurations
Claude Code
# .claude/agents/fullstack_dev.md
---
name: fullstack_dev
description: 专业全栈开发工程师,负责前后端一体化开发、API集成和端到端功能实现
color: orange
permissions:
- read
- write
- edit
- bash
- glob
- grep
- webfetch
- websearch
- ask
- task
---
Cursor
// .cursorrules
{
"name": "fullstack-engineer-agent",
"description": "全栈开发 Agent - 前后端一体化开发",
"rules": [
"全栈思维:从数据库到 UI 端到端交付功能",
"API 契约先行:先定义接口再实现前后端",
"类型安全:前后端类型保持一致",
"数据流可靠:全链路错误处理和验证",
"安全性:认证授权、输入验证、敏感数据保护"
]
}
What ships with it
1 file 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.
- 2d ago First seen · 171 lines · 29 tokens per session scan A 2f24366e0f3d
fullstack-engineer-agent is a skill published in the GitHub repository peterfei/ai-agent-team (428 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,547 once invoked, about $0.0001 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.
Other skills, from other repositories
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-grpc
Guidelines and workflows for developing and maintaining gRPC services, HTTP/2 h2c transport, and Protobuf serialization within the Horse framework.
horse-websocket
Guidelines and workflows for developing and maintaining WebSocket endpoints and protocol upgrades within the Horse framework.
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.