Not in the top 1,000 by GitHub stars
YijiaDuan/build-managed-agents
Claude Code skill for Anthropic Managed Agents — create / run / audit the cloud-hosted agent API end-to-end. 教 Claude 用 Anthropic 托管代理 API 的 skill,覆盖创建/运行/审计全流程。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → f43ec00d15c0
No earlier version was observed for comparison.
10GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
build-managed-agents
When your agent uses it
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。
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
1,683 tokensWhen the skill is activated
Reference documents
9,853 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 何时使用
- 前置条件
- 核心概念速查
- 标准工作流
- 可用脚本
- 常见陷阱
- 参考文件索引
- 官方文档
Scripts executed separately
scripts/admin.pyscripts/quickstart.py
Files
.gitignoreasset246 bytesLICENSEasset1,067 bytesREADME.mddoc4,458 bytesSKILL.mdcore6,433 bytesSKILL.mdcore6,433 bytesSKILL.mdcore6,433 bytesSKILL.mdcore6,433 bytesSKILL.mdcore6,433 bytesreference/audit.mddoc6,202 bytesreference/create.mddoc7,917 bytesreference/errors.mddoc5,657 bytesreference/events.mddoc4,615 bytesreference/run.mddoc8,465 bytesscripts/admin.pyruns6,401 bytesscripts/quickstart.pyruns3,408 bytes
Read SKILL.md
# 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.agents`、`client.beta.environments`、`client.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）Skills included
- build-managed-agents
Repository facts
- License
- MIT
- Created
- Apr 15, 2026
- Last pushed
- Apr 15, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 23 network referencesin 6 files: README.md:10 reference/create.md:84 reference/run.md:40 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: scripts/admin.py:1 scripts/quickstart.py:1
- 6 references to secretsin 5 files: reference/run.md:259 .gitignore:18 README.md:24 and 2 more
- No requests to vote in Hot
Show all 31 signals by file
.gitignore
- Access to secretsline 18
[Credential-related source omitted]
README.md
- Network accessline 10
# 全局（推荐，所有项目可用） git clone https://github.com/YijiaDuan/build-managed-agents \ - Network accessline 11
git clone https://github.com/YijiaDuan/build-managed-agents \ - Network accessline 14
# 或只装到当前项目 mkdir -p .claude/skills git clone https://github.com/YijiaDuan/build-managed-agents \ - Network accessline 15
mkdir -p .claude/skills git clone https://github.com/YijiaDuan/build-managed-agents \ .claude/skills/build-managed-agents - Network accessline 16
git clone https://github.com/YijiaDuan/build-managed-agents \ - Access to secretsline 24
[Credential-related source omitted]
SKILL.md
reference/audit.md
- Network accessline 182
https://console.anthropic.com → Agents / Sessions 标签页，GUI 展示：
reference/create.md
- Network accessline 84
mcp_servers=[ {"name": "my_server", "type": "url", "url": "https://example.com/mcp"}, - Network accessline 85
{"name": "my_server", "type": "url", "url": "https://example.com/mcp"}, - Network accessline 203
{ "type": "github_repository", "url": "https://github.com/org/repo", - Network accessline 204
[Credential-related source omitted] - Network accessline 205
"url": "https://github.com/org/repo",
reference/errors.md
- Network accessline 121
4. **Agent 版本** — 是不是 update 了但 session pin 了旧版本 5. **Environment 可达性** — networking limited 但工具要访问外网 6. **MCP server** — 单独 curl 测 MCP URL 是否可达 - Network accessline 122
[Credential-related source omitted] - Network accessline 123
6. **MCP server** — 单独 curl 测 MCP URL 是否可达 - Network accessline 124
[Credential-related source omitted]
reference/run.md
- Network accessline 40
{"type": "text", "text": "Hello"}, {"type": "image", "source": {"type": "base64", "data": "...", "media_type": "image/png"}}, {"type": "image", "source": {"type": "url", "url": "https://..."}}, - Network accessline 41
{"type": "image", "source": {"type": "base64", "data": "...", "media_type": "image/png"}}, {"type": "image", "source": {"type": "url", "url": "https://..."}}, {"type": "image", "source": {"type": "file", "file_id": "file_... - Network accessline 42
{"type": "image", "source": {"type": "url", "url": "https://..."}}, - Network accessline 258
# 流式接收（SSE） curl -sS -N "https://api.anthropic.com/v1/sessions/$S/events/stream" \ - Network accessline 259
[Credential-related source omitted] - Access to secretsline 259
[Credential-related source omitted] - Access to secretsline 262
[Credential-related source omitted]
scripts/admin.py
- Executable scriptline 1
Executable file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 30 facts
- Network access in code of documentationREADME.md:10Low confidence
- Network access in code of documentationREADME.md:11Low confidence
- Network access in code of documentationREADME.md:14Low confidence
- Network access in code of documentationREADME.md:15Low confidence
- Network access in code of documentationREADME.md:16Low confidence
- Access to secrets in code of documentationREADME.md:24Low confidence
- Access to secrets in code of the SKILL.mdSKILL.md:27High confidence
- Network access in prose of the SKILL.mdSKILL.md:145Low confidence
- Network access in prose of the SKILL.mdSKILL.md:146Low confidence
- Network access in prose of the SKILL.mdSKILL.md:147Low confidence
- Network access in prose of documentationreference/audit.md:182Low confidence
- Network access in code of documentationreference/create.md:84Low confidence
- Network access in code of documentationreference/create.md:85Low confidence
- Network access in code of documentationreference/create.md:203Low confidence
- Network access in code of documentationreference/create.md:204Low confidence
- Network access in code of documentationreference/create.md:205Low confidence
- Network access in prose of documentationreference/errors.md:121Low confidence
- Network access in prose of documentationreference/errors.md:122Low confidence
- Network access in prose of documentationreference/errors.md:123Low confidence
- Network access in prose of documentationreference/errors.md:124Low confidence
- Network access in code of documentationreference/run.md:40Low confidence
- Network access in code of documentationreference/run.md:41Low confidence
- Network access in code of documentationreference/run.md:42Low confidence
- Network access in code of documentationreference/run.md:258Low confidence
- Network access in code of documentationreference/run.md:259Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuereference/run.md:259Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuereference/run.md:262Low confidence
- Executable script in prose of a file that runsscripts/admin.py:1Low confidence
- Executable script in prose of a file that runsscripts/quickstart.py:1Low confidence
- Access to secrets in prose of a file that runsscripts/quickstart.py:6Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
