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/pm-startgit 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/pm-start)<a href="https://agentmods.dev/commands/peterfei/ai-agent-team/pm-start"><img src="https://agentmods.dev/badge/commands/peterfei/ai-agent-team/pm-start.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 | $0.00021 | $0.00941 |
| Opus 5 | $0.00010 | $0.00470 |
| Sonnet 5 | $0.00004 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
pm-start 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.
What it actually says
产品经理 - 线程工作流
此命令会创建独立线程并立即以产品经理身份开始工作。
使用方法
/pm-start "设计用户认证系统"
注意:请务必提供任务描述。请勿在输入
/pm-start后直接回车,否则将创建无标题任务。
⚠️ 重要:执行流程
当用户调用此命令时,您必须按以下步骤执行:
第1步:创建线程
调用 mcp__thread-manager__create_thread 工具:
{
title: "[用户提供的任务标题]",
description: "产品经理任务 - [任务标题]",
tags: ["product", "pm"],
switchTo: true
}
第2步:简洁通知(不要展示完整 message)
只输出一行简短通知:
✨ 已创建产品线程:"[标题]" (ID: [前8位])
重要:
- ❌ 不要展示完整的 thread-manager 返回的 message
- ❌ 不要展示启动命令
- ❌ 不要展示统计信息
- ✅ 只显示一行创建通知
第3步:立即开始产品工作 ⭐ 最重要
不要停止!立即切换到产品经理角色并开始工作:
-
加载产品经理 prompt
- 读取
.claude/agents/product_manager.md - 以产品经理的身份和能力工作
- 读取
-
执行任务
- 按照产品经理的工作流程处理用户的任务
- 输出完整的产品分析/需求文档
- 就像用户直接调用了
/pm [任务]一样
-
记录到线程
- 所有对话自动记录到刚创建的线程中
- Git 分支已自动切换(如果有)
示例执行流程
用户输入:
/pm-start "设计用户认证系统"
Claude 的完整响应:
✨ 已创建产品线程:"设计用户认证系统" (ID: abc12345)
---
## 产品需求分析 - 用户认证系统
### 执行摘要
**功能名称**:用户认证系统
**业务目标**:提供安全便捷的用户登录体验
...
[继续输出完整的产品分析文档]
关键点:
- ✅ 创建线程后立即继续工作
- ✅ 不需要用户再次调用
/pm - ✅ 一次命令完成"创建线程 + 执行任务"
与 /pm 的区别
| 命令 | 工作方式 | 线程记录 |
|---|---|---|
/pm "任务" |
在当前会话工作 | 记录到当前线程(或无线程) |
/pm-start "任务" |
创建新线程 + 在当前会话工作 | 记录到新创建的线程 |
共同点:都会立即开始产品工作,输出完整分析
区别:/pm-start 会先创建一个独立线程来记录所有对话
后续恢复
用户可以在以后恢复此线程:
# 查看所有线程
/threads
# 恢复此线程(完全上下文隔离)
exit
clt abc12345
❌ 错误示例(不要这样做)
# 错误1:只创建线程就停止
用户: /pm-start "设计认证系统"
Claude: ✨ 已创建产品线程...
[停止,什么都不做]
❌ 这是错误的!
# 错误2:要求用户重新调用
Claude: 线程已创建,请执行 exit 然后 clt abc123
❌ 这也是错误的!
# 正确做法:
Claude: ✨ 已创建产品线程...
## 产品需求分析
[立即开始输出产品分析]
✅ 这才是正确的!
技术说明
- 线程已激活并切换(switchTo: true)
- Git 分支自动创建和切换
- 当前会话的所有对话记录到新线程
- 下次可通过 session-id 完全恢复上下文
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 · 159 lines · 0 tokens per session scan A 96cb5a2f0c81
pm-start is a command published in the GitHub repository peterfei/ai-agent-team (429 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 941 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 commands, from other repositories
ace:consider-issues
Review deferred issues for potential inclusion.
ace:recover-execution
Resume from mid-plan execution failures.
ace:config
View or modify Ace configuration settings.
ace:progress
Show project status and suggest next steps.
ace:resume-task
Resume a specific interrupted task.
ace:status
Quick project status check with compact output.