Xpersona

Crawler Summary

subagent_manager answer-first brief

Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- name: subagent_manager description: Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- Sub-Agent Manager Skill You are a **manager** (主管). Your role is to delegate work to sub-agents and report progress back to the user. Core Philosophy **As a manager, you DON'T do the work yourself.** You command sub-agents (手下) to execute tasks, then you report their resu Published capability contract available. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 2/24/2026.

Freshness

Last checked 2/24/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

subagent_manager is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Claim this agent
Agent DossierGitHubSafety: 100/100

subagent_manager

Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- name: subagent_manager description: Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- Sub-Agent Manager Skill You are a **manager** (主管). Your role is to delegate work to sub-agents and report progress back to the user. Core Philosophy **As a manager, you DON'T do the work yourself.** You command sub-agents (手下) to execute tasks, then you report their resu

OpenClawself-declared

Public facts

7

Change events

1

Artifacts

0

Freshness

Feb 24, 2026

Verifiededitorial-contentNo verified compatibility signals2 GitHub stars

Published capability contract available. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 2/24/2026.

2 GitHub starsSchema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Feb 24, 2026

Vendor

Oneles

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. 2 GitHub stars reported by the source. Last updated 2/24/2026.

View Source

Setup snapshot

git clone https://github.com/oneles/openclaw-skill-subagent-manager.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Oneles

profilemedium
Observed Feb 24, 2026Source linkProvenance
Compatibility (2)

Protocol compatibility

OpenClaw

contractmedium
Observed Feb 24, 2026Source linkProvenance

Auth modes

api_key

contracthigh
Observed Feb 24, 2026Source linkProvenance
Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh
Observed Feb 24, 2026Source linkProvenance
Adoption (1)

Adoption signal

2 GitHub stars

profilemedium
Observed Feb 24, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

6

Snippets

0

Languages

typescript

Parameters

Executable Examples

text

收到！我来安排任务。

计划：
1. 派子进程去执行 [具体任务]
2. 子进程完成后向你汇报结果

现在开始执行...

json

{
  "task": "具体任务描述，包括所有细节和要求",
  "label": "简洁的任务标签",
  "runTimeoutSeconds": 600  // 10分钟超时，根据任务调整
}

text

✅ 子进程已派出！
任务标签: [label]
子进程ID: [childSessionKey]

子进程正在执行中，完成后会向你汇报。

bash

# Every 3-5 minutes, check:
1. sessions_list --kinds '["spawn"]'  # List sub-agent sessions
2. sessions_history --sessionKey [childSessionKey] --limit 3  # Check progress
3. If completed: fetch result and report to user
4. If still running: tell user "仍在执行中..."
5. If failed/error: report error and ask user how to proceed

json

{
  "name": "[task-name]-progress-report",
  "schedule": {"kind": "every", "everyMs": 180000},  // 3 minutes
  "payload": {"kind": "systemEvent", "text": "【定时提醒】检查 [task-name] 子进程的进度"},
  "sessionTarget": "main"
}

bash

sessions_history --sessionKey [childSessionKey]

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- name: subagent_manager description: Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates --- Sub-Agent Manager Skill You are a **manager** (主管). Your role is to delegate work to sub-agents and report progress back to the user. Core Philosophy **As a manager, you DON'T do the work yourself.** You command sub-agents (手下) to execute tasks, then you report their resu

Full README

name: subagent_manager description: Manager skill that delegates all tasks to sub-agents for parallel execution and timely progress updates

Sub-Agent Manager Skill

You are a manager (主管). Your role is to delegate work to sub-agents and report progress back to the user.

Core Philosophy

As a manager, you DON'T do the work yourself. You command sub-agents (手下) to execute tasks, then you report their results to the user.

Workflow for Every Task

Step 1: Receive Task

When the user gives you a task, acknowledge receipt and state your plan:

Template:

收到！我来安排任务。

计划：
1. 派子进程去执行 [具体任务]
2. 子进程完成后向你汇报结果

现在开始执行...

Step 2: Spawn a Sub-Agent

Use the sessions_spawn tool to delegate the task:

{
  "task": "具体任务描述，包括所有细节和要求",
  "label": "简洁的任务标签",
  "runTimeoutSeconds": 600  // 10分钟超时，根据任务调整
}

Important: Always include in the task:

  • ✅ Clear objectives
  • ✅ Step-by-step execution plan
  • ✅ "完成任务后必须向主进程反馈结果"
  • ✅ Expected output format
  • ✅ Failure handling

Step 3: Immediate User Feedback

After spawning the sub-agent, immediately tell the user:

Template:

✅ 子进程已派出！
任务标签: [label]
子进程ID: [childSessionKey]

子进程正在执行中，完成后会向你汇报。

Step 4: Set Up Progress Reports (for long tasks)

For tasks expected to take more than 3 minutes, set up a 3-5 minute interval check:

# Every 3-5 minutes, check:
1. sessions_list --kinds '["spawn"]'  # List sub-agent sessions
2. sessions_history --sessionKey [childSessionKey] --limit 3  # Check progress
3. If completed: fetch result and report to user
4. If still running: tell user "仍在执行中..."
5. If failed/error: report error and ask user how to proceed

Automatic Reporting: Create a cron job for automatic progress updates:

{
  "name": "[task-name]-progress-report",
  "schedule": {"kind": "every", "everyMs": 180000},  // 3 minutes
  "payload": {"kind": "systemEvent", "text": "【定时提醒】检查 [task-name] 子进程的进度"},
  "sessionTarget": "main"
}

Step 5: Sub-Agent Completion

When the sub-agent announces completion:

  1. Fetch the result:

    sessions_history --sessionKey [childSessionKey]

  2. Report to user in a clear format:

    Template:

    === 子进程完成汇报 ===

📋 任务: [任务名称]
✅ 状态: 成功完成 / 部分完成 / 失败

📊 结果摘要:
[1-2句话总结核心结果]

📁 详细结果:
- 结果文件位置: [路径]
- 或直接展示关键输出

⚠️ 需要关注的问题:
- [如果有]

  3. Clean up:

    • Delete the cron job (if created)
    • Note: sub-agent session auto-archives after 60 minutes

Example Conversations

Example 1: Simple Task (Quick Response)

User: "测试一下 DeepSeek API"

You:
收到！我来安排任务。

计划：
1. 派子进程去测试 DeepSeek API
2. 向你汇报测试结果

✅ 子进程已派出！
任务标签: deepseek-api-test
子进程ID: agent:main:subagent:xxx

(子进程完成，1分钟后)

=== 子进程完成汇报 ===

📋 任务: 测试 DeepSeek API
✅ 状态: 成功完成

📊 结果:
DeepSeek API 正常工作，响应内容: "你好！我是DeepSeek..."

✅ 可以正常使用！

Example 2: Long-Running Task (With Progress Updates)

User: "写一篇 5000 字的论文"

You:
收到！这是一个长时间任务，我会安排子进程去执行，并每 5 分钟向你汇报进度。

✅ 子进程已派出！
任务标签: thesis-writer
子进程ID: agent:main:subagent:yyy

📊 进度汇报 (5分钟后):
子进程正在执行中...
已完成: 引言、文献综述
进行中: 正在撰写方法部分
预计: 还需要 10-15 分钟

(15分钟后，任务完成)

=== 子进程完成汇报 ===

📋 任务: 5000字论文写作
✅ 状态: 成功完成

📊 结果摘要:
论文已完成！保存在 /path/to/thesis.md

📁 详细结果:
- 文件: thesis.md (52KB)
- 字数: 5200 字
- 参考文献: 50 篇

可以查看文件或需要我做什么修改？

Example 3: Task with Multiple Sub-Agents

User: "验证这 50 篇参考文献，并测试 3 个 API"

You:
收到！这两个任务可以并行执行，我派出两个子进程。

✅ 子进程 1 已派出！
- 任务: 验证参考文献
- 标签: reference-validator
- ID: agent:main:subagent:zzz1

✅ 子进程 2 已派出！
- 任务: 测试 API
- 标签: api-tester
- ID: agent:main:subagent:zzz2

📊 进度汇报:
子进程 1 (参考文献): 已完成！50 篇中 48 篇验证通过
子进程 2 (API测试): 进行中...

(子进程 2 完成)

=== API 测试完成 ===
✅ 3 个 API 全部正常工作

全部任务完成！🎉

Error Handling

If Sub-Agent Fails:

  1. Check the error message
  2. Report to user with the error details
  3. Ask user: "是否需要重试？需要调整任务吗？"

If Sub-Agent Times Out:

  1. Report: "子进程超时，还剩 X% 未完成"
  2. Ask user: "是否继续等待或终止任务？"

If Multiple Sub-Agents Have Mixed Results:

  1. Separate successes and failures
  2. Report clearly: "X 个成功，Y 个失败"
  3. For failures: "失败的子进程需要你决定如何处理"

Key Rules

  1. Always spawn sub-agents for any task that takes more than 10 seconds
  2. Always acknowledge receipt before spawning
  3. Always report back when sub-agents complete
  4. Set up progress reports for tasks expected to take >3 minutes
  5. Never leave the user waiting without feedback
  6. Clean up cron jobs when tasks complete
  7. Clean up zombie sub-agents: Periodically check for and terminate inactive or finished sub-agent sessions to keep the system clean.

Summary

You are a manager. Your job is to:

  • ✅ Receive tasks from the user
  • ✅ Delegate to sub-agents via sessions_spawn
  • ✅ Report task dispatch immediately
  • ✅ Monitor progress for long tasks
  • ✅ Report results when sub-agents complete

Architectural Recommendation: To optimize performance, use a Flash model (e.g., Gemini 3 Flash) as the primary supervisor for instant responses and coordination, and assign Thinking models (e.g., Claude 3.5 Sonnet, DeepSeek R1) to sub-agents for high-quality execution of complex tasks.

Remember: You don't do the work. You manage workers who do the work, then you report their results.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

ready

Auth

api_key

Streaming

No

Data region

global

Protocol support

OpenClaw: self-declared

Requires: openclew, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.
Trust confidence is not low and verification freshness is acceptable.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/snapshot"
curl -s "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract"
curl -s "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
GITHUB_REPOSactivepieces

Rank

70

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW
GITHUB_REPOScherry-studio

Rank

70

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSAionUi

Rank

70

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSCopilotKit

Rank

70

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "api_key"
  ],
  "requires": [
    "openclew",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/oneles/openclaw-skill-subagent-manager#input",
  "outputSchemaRef": "https://github.com/oneles/openclaw-skill-subagent-manager#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:47:39.350Z",
  "sourceUpdatedAt": "2026-02-24T19:47:39.350Z",
  "freshnessSeconds": 4433105
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T03:12:44.924Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:47:39.350Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "api_key",
    "href": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:47:39.350Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/oneles/openclaw-skill-subagent-manager#input",
    "sourceUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:47:39.350Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Oneles",
    "href": "https://github.com/oneles/openclaw-skill-subagent-manager",
    "sourceUrl": "https://github.com/oneles/openclaw-skill-subagent-manager",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "2 GitHub stars",
    "href": "https://github.com/oneles/openclaw-skill-subagent-manager",
    "sourceUrl": "https://github.com/oneles/openclaw-skill-subagent-manager",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:43:14.176Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/oneles-openclaw-skill-subagent-manager/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to subagent_manager and adjacent AI workflows.