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 commands/peterfei/ai-agent-team/readmegit clone --depth 1 https://github.com/peterfei/ai-agent-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/commands/peterfei/ai-agent-team/readme)<a href="https://agentmods.dev/commands/peterfei/ai-agent-team/readme"><img src="https://agentmods.dev/badge/commands/peterfei/ai-agent-team/readme.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01936 |
| Opus 5 | $0.00000 | $0.00968 |
| Sonnet 5 | $0.00000 | $0.00387 |
| Haiku 4.5 | $0.00000 | $0.00194 |
Grade A, and why
README 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 4d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
快捷命令目录
本目录包含了AI智能体团队的快捷命令文件，用于更方便地调用各个智能体。
快捷命令列表
角色调用命令
| 命令 | 智能体 | 上下文隔离 | 描述 |
|---|---|---|---|
/pm |
产品经理 | ❌ 当前会话 | 产品规划、需求分析和路线图制定 |
/fe |
前端开发 | ❌ 当前会话 | UI实现、组件开发和用户体验优化 |
/be |
后端开发 | ❌ 当前会话 | API设计、数据库优化和服务器端逻辑开发 |
/fs |
全栈开发 | ❌ 当前会话 | 前后端一体化开发、API集成和端到端功能实现 |
/qa |
QA工程师 | ❌ 当前会话 | 测试、质量保证和缺陷报告 |
/ops |
DevOps工程师 | ❌ 当前会话 | 部署、基础设施和CI/CD流水线 |
/tl |
技术负责人 | ❌ 当前会话 | 技术决策和团队协调 |
线程启动命令（推荐用于重要任务）⭐
| 命令 | 智能体 | 上下文隔离 | 描述 |
|---|---|---|---|
/pm-start |
产品经理 | ✅ 独立线程 | 创建产品线程并提供启动命令 |
/fe-start |
前端开发 | ✅ 独立线程 | 创建前端线程并提供启动命令 |
/be-start |
后端开发 | ✅ 独立线程 | 创建后端线程并提供启动命令 |
/fs-start |
全栈开发 | ✅ 独立线程 | 创建全栈线程并提供启动命令 |
/qa-start |
QA工程师 | ✅ 独立线程 | 创建测试线程并提供启动命令 |
/ops-start |
DevOps工程师 | ✅ 独立线程 | 创建DevOps线程并提供启动命令 |
/tl-start |
技术负责人 | ✅ 独立线程 | 创建技术线程并提供启动命令 |
/start-task |
通用 | ✅ 独立线程 | 为任何角色创建线程（通用命令） |
线程管理命令
| 命令 | 描述 |
|---|---|
/thread new "标题" |
手动创建新线程 |
/thread switch <id> |
切换到指定线程 |
/threads |
列出所有线程 |
/thread update |
更新线程元数据 |
/thread delete <id> |
删除线程 |
使用方法
快速调用（当前会话）
适用于：快速咨询、简单任务（< 5分钟）
/pm "设计用户认证系统"
/fe "创建登录表单"
/be "实现JWT API"
/qa "测试认证流程"
/ops "部署到生产环境"
/tl "评估技术架构"
独立线程工作（推荐用于重要任务）⭐
适用于：完整功能开发、长期任务（> 30分钟）
# 方式1：角色专用命令
/pm-start "用户认证系统需求分析"
/be-start "实现JWT认证API"
/fe-start "开发登录UI组件"
# 方式2：通用命令
/start-task pm "用户认证系统需求分析"
/start-task be "实现JWT认证API"
/start-task fe "开发登录UI组件"
# 启动独立会话
exit
clt abc123 # 使用快捷命令
# 或
claude --session-id abc-123-def-456 # 使用完整ID
工作流示例
方式1：快速开发流程（单会话）
适用于：简单功能、快速迭代
# 在同一个会话中依次调用
/pm "定义用户认证功能需求"
/be "实现JWT认证API"
/fe "创建登录UI组件"
/qa "执行完整的认证流程测试"
/ops "部署认证功能到生产环境"
方式2：独立线程流程（多会话）⭐
适用于：复杂功能、需要上下文隔离
# 主会话：创建产品线程
/pm-start "用户认证系统需求分析"
exit
# 终端1：产品经理工作
$ clt abc123
产品会话> /pm "开始需求分析..."
产品会话> exit
# 主会话：创建后端线程
/be-start "实现JWT认证API"
exit
# 终端2：后端开发工作
$ clt def456
后端会话> /be "实现API..."
后端会话> exit
# 主会话：创建前端线程
/fe-start "开发登录UI组件"
exit
# 终端3：前端开发工作
$ clt ghi789
前端会话> /fe "开发UI..."
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.
- 4d ago First seen · 261 lines · 0 tokens per session scan A 64a8418d6818
README is a command published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,936 tokens. 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 commands, from other repositories
skill-inbox
Unified entry point for managing skill suggestions and browsing all installed skills. Provides two views: suggestions (default) and all skills.
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
cti-status
Health check — backend tier, case store, MCP tools, API credit balances. Run this when something behaves oddly. Usage: /cti-status.
reskin
Extract a measured design signature (type ramp, accent + its budget, grid unit, radius, layout) from a reference image or site, write it to signature.json, and drive the build to match it — "steal this vibe" as a spec, not pixels.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.