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/threadsgit 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 | $0.00006 | $0.00670 |
| Opus 5 | $0.00003 | $0.00335 |
| Sonnet 5 | $0.00001 | $0.00134 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
threads 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.
What it actually says
List Threads Command
List all available conversation threads with their status and statistics.
Usage
/threads [options]
Options
--sort [field]: Sort byupdatedAt,createdAt, ormessageCount(default:updatedAt)--order [asc|desc]: Sort order (default:desc)--tags [tag1,tag2]: Filter by tags--limit [number]: Limit the number of results (default: 50)
Implementation Details for Claude
⚠️ 前置检查(最高优先级)
在执行任何操作之前,必须先检查 thread-manager MCP 服务器是否可用。
判断方法:检查当前可用的工具列表中是否包含 mcp__thread-manager__list_threads 工具。
如果 MCP 工具不可用,必须立即输出以下错误信息并停止,不要尝试调用任何工具:
❌ thread-manager MCP 服务器未配置
当前项目未配置 thread-manager MCP 服务器,无法使用线程管理功能。
🔧 解决方案:
方案 1:全局安装(推荐,一次配置全局可用)
claude mcp add thread-manager -s user -- node <path-to-thread-manager>/dist/index.js
方案 2:项目级安装
claude mcp add thread-manager -s project -- node <path-to-thread-manager>/dist/index.js
方案 3:切换到已配置该服务的项目目录
添加后需要重启 Claude Code 会话才能生效。
🔴 重要:绝对不要在 MCP 不可用时尝试调用工具,这会导致命令卡住无响应!
正常流程
When the user invokes /threads, call the thread-manager.list_threads tool.
Example:
If user types: /threads --sort messageCount
You call:
use_mcp_tool({
server_name: "thread-manager",
tool_name: "list_threads",
arguments: {
sortBy: "messageCount"
}
});
Output Format: Please format the output as a compact table with the following structure:
状态 标题 ID 消息 文件 更新时间
────────────────────────────────────────────────────────────────────────
✅ [当前线程标题] [short-id] [n] [n] [时间]
[其他线程标题] [short-id] [n] [n] [时间]
[描述] (如果有)
...
────────────────────────────────────────────────────────────────────────
总计: [n] 个线程
格式要求:
- 当前活跃线程用 ✅ 标记
- ID 显示前 8 位短 ID
- 如果线程有描述,在标题下方缩进显示
- 消息列显示消息数量
- 文件列显示文件变更数量
- 更新时间使用相对时间(如:刚刚、3分钟前、1小时前)
- 表格使用 ASCII 字符分隔线
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 · 94 lines · 6 tokens per session scan A b7ec8f4c32b9
threads is a command published in the GitHub repository peterfei/ai-agent-team (428 stars, last pushed 2mo ago), licensed MIT. It adds 6 tokens to every session and 670 once invoked, about $0.0000 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
providers
Display Better Auth available authentication providers and their configuration.
verify
Verify any change surface against approved acceptance criteria and preserve evidence.
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].
setup
Prepare the current project for UIForge — ensure shadcn init, the component registries (shadcn + @motion-primitives), and the motion/lucide-react/cn prerequisites.