AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Build Managed Agents

skill-yijiaduan-build-managed-agents-build-managed-agents · by YijiaDuan

教 Claude Code / OpenClaw 等 coding agent 使用 Anthropic Claude Managed Agents(云端托管代理服务)API —— create/run/audit 全流程。当用户(或上游 coding agent)需要创建托管 agent、跑 session、流式处理事件、审计用量或调用 /v1/agents、/v1/environments、/v1/sessions 等 API 时使用。触发词:managed agents、托管代理、build a managed agent、agent_toolset_20260401、client.beta.agents、client.beta.sessions。

No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-yijiaduan-build-managed-agents-build-managed-agents

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yijiaduan-build-managed-agents-build-managed-agents)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Build Managed Agents? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

build-managed-agents

这是一个给 coding agent(Claude Code / OpenClaw / Cursor agent 等)用的 skill —— 当 coding agent 需要帮用户构建基于 Claude Managed Agents 的应用时,照着本 skill 的 recipe 执行。

Anthropic 托管的 agent 运行时:云容器 + 内置工具 + 事件流。你不用自己搭 agent loop、工具执行、沙箱。

本 skill 覆盖三个阶段:Create(定义 agent/环境/session)→ Run(发消息、流式接收、处理工具确认)→ Audit(查状态、事件流、token 用量、成本)。

何时使用

  • 用户要"创建一个 managed agent" / "托管 agent" / "跑一个 session"
  • 代码里出现 client.beta.agentsclient.beta.environmentsclient.beta.sessions
  • 用户询问 /v1/agents/v1/environments/v1/sessions 等端点
  • 用户要审计/调试 session(看事件流、token 消耗、错误重试)

前置条件

pip install anthropic  # Python
# 或 npm install @anthropic-ai/sdk  # TypeScript

export ANTHROPIC_API_KEY="sk-ant-..."

所有 API 需要 beta header:anthropic-beta: managed-agents-2026-04-01(SDK 自动加)。

Research preview 功能(outcomes / 多 agent / memory stores)需额外:managed-agents-2026-04-01-research-preview

核心概念速查

| 概念 | 说明 | 生命周期 | |------|------|---------| | Agent | 模型 + system prompt + 工具 + MCP + skills | 复用,有版本号 | | Environment | 云容器模板(预装包、网络规则) | 复用 | | Session | 一次运行实例(Agent × Environment) | 一次性,有完整事件流 | | Event | 会话中每条消息/工具调用/状态变更 | 永久存储,可审计 |

标准工作流

1. Create 阶段(一次性)

from anthropic import Anthropic
client = Anthropic()

agent = client.beta.agents.create(
    name="My Agent",
    model="claude-sonnet-4-6",
    system="你的 system prompt",
    tools=[{"type": "agent_toolset_20260401"}],  # bash/read/write/edit/glob/grep/web_fetch/web_search
)

env = client.beta.environments.create(
    name="my-env",
    config={"type": "cloud", "networking": {"type": "unrestricted"}},
)

详细参数、MCP、skills、自定义工具、权限策略 → 见 reference/create.md

2. Run 阶段(每个任务一次)

session = client.beta.sessions.create(agent=agent.id, environment_id=env.id)

with client.beta.sessions.events.stream(session.id) as stream:
    client.beta.sessions.events.send(
        session.id,
        events=[{"type": "user.message", "content": [{"type": "text", "text": "..."}]}],
    )
    for event in stream:
        match event.type:
            case "agent.message":
                for block in event.content:
                    print(block.text, end="")
            case "agent.tool_use":
                pass  # 内置工具,系统自动执行
            case "agent.custom_tool_use":
                # 自定义工具 — 你必须发 user.custom_tool_result 回去
                ...
            case "session.status_idle":
                break

关键细节:

  • 必须先开 stream 再 send(不然前几个事件丢失)
  • 遇到 always_ask 权限的工具,agent 会停下等 user.tool_confirmation
  • 遇到 agent.custom_tool_use,你必须回 user.custom_tool_result,否则 session 卡死
  • 要中断 agent 用 user.interrupt

完整事件类型表、图片/文档输入、多 agent、outcomes、memory stores → 见 reference/run.mdreference/events.md

3. Audit 阶段(任何时候)

# 列出所有 session 状态
for s in client.beta.sessions.list(limit=50):
    print(s.id, s.status, s.usage.input_tokens + s.usage.output_tokens)

# 拉某个 session 的完整事件流(审计链)
for evt in client.beta.sessions.events.list(session_id):
    print(evt.type, evt.processed_at)

# 看 token 用量 + 时长
s = client.beta.sessions.retrieve(session_id)
print(s.usage, s.stats)

成本估算、按时间段过滤、错误分类统计 → 见 reference/audit.md

可用脚本

  • scripts/quickstart.py — 一键跑通 create→run→audit 的最小模板
  • scripts/admin.py — 管理工具(list-sessions / show / stats / cleanup)

直接 copy 到项目里改 system prompt 即可。

常见陷阱

  1. Agent 版本漂移:生产环境要 pin 版本 agent={"type": "agent", "id": "...", "version": N},否则 update 后静默升级
  2. Stream 顺序:先 .stream() 打开通道,再 .send() 发消息,顺序反了会丢事件
  3. Custom tool 悬挂:收到 agent.custom_tool_use 必须回 user.custom_tool_resultis_error=True 也行),否则 session 永远 idle
  4. Tool confirmationalways_ask 权限下 agent 会停在 session.status_idlestop_reason.type="requires_action",需要 user.tool_confirmation 放行
  5. Rate limits:Create 类 60/min,Read 类 600/min。列表操作尽量用 limit + pagination
  6. Archive vs Delete:优先 archive(保留审计),delete 是永久的
  7. Running session 不能 delete:先发 user.interrupt 让它 idle

参考文件索引

  • reference/create.md — Agent/Environment/Session 完整创建参数
  • reference/run.md — 事件收发、流式、多 agent、memory stores、outcomes
  • reference/events.md — 所有事件类型 schema(agent. / user. / session. / span.
  • reference/audit.md — 列表查询、用量统计、成本估算、合规审计
  • reference/errors.md — 错误类型、重试策略、状态机
  • scripts/quickstart.py — 可运行模板
  • scripts/admin.py — CLI 管理工具

官方文档

  • https://platform.claude.com/docs/en/managed-agents/overview
  • https://platform.claude.com/docs/en/managed-agents/quickstart
  • https://platform.claude.com/docs/en/api/agents

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.