Xpersona

Crawler Summary

foreman answer-first brief

This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. --- name: foreman description: >- This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. version: 0.1.1 tools: Read, Glob, Grep, Bash Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Freshness

Last checked 4/15/2026

Best For

foreman is best for be, delegate workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Claim this agent
Agent DossierGitHubSafety: 94/100

foreman

This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. --- name: foreman description: >- This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. version: 0.1.1 tools: Read, Glob, Grep, Bash

OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Apr 15, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Apr 15, 2026

Vendor

Joneshong Skills

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

Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

View Source

Setup snapshot

git clone https://github.com/joneshong-skills/foreman.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

Joneshong Skills

profilemedium
Observed Apr 15, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Apr 15, 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

maestro (cross-CLI, heavy) ←→ foreman (within-session, light)

bash

FOREMAN="python3 ~/.claude/skills/foreman/scripts/foreman.py"

# List available agents
$FOREMAN list

# Find best agent for a task
$FOREMAN match "review this code for security issues"

# Show agent details
$FOREMAN inspect code-reviewer

# Show capability matrix
$FOREMAN capabilities

bash

$FOREMAN list

bash

$FOREMAN match "description of the task" --json

text

"use the {agent-name} agent to {task description}"

text

Sequential: "First use code-reviewer to review, then use security-scanner to audit"
Parallel: Launch multiple Task tool calls simultaneously
Pipeline: Chain results — agent A's output becomes agent B's input

Docs & README

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

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. --- name: foreman description: >- This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. version: 0.1.1 tools: Read, Glob, Grep, Bash

Full README

name: foreman description: >- This skill should be used when the user asks to "dispatch to agents", "assign work to agents", "which agent should handle this", "list my agents", "agent capabilities", "派任務給 agent", "哪個 agent 適合", "agent 清單", "工頭模式", mentions sub-agent dispatch, agent workforce management, task-to-agent matching, or agent orchestration within Claude Code. version: 0.1.1 tools: Read, Glob, Grep, Bash argument-hint: "<task description> or list/capabilities"

Foreman — Sub-Agent Workforce Manager

The foreman knows your agent workforce. It scans available sub-agents, matches tasks to the right agent, and orchestrates dispatch within Claude Code.

Foreman ≠ Maestro: Maestro dispatches across CLIs (claude/codex/gemini). Foreman dispatches within Claude Code to sub-agents. They're complementary layers.

maestro (cross-CLI, heavy) ←→ foreman (within-session, light)

Core Principle: Task Decomposition is an Art

拆解是門藝術 — 不是越細越好，也不是越粗越好。 大膽假設，小心求證。

  • Tasks can be split into many small steps for incremental verification
  • But splitting too much wastes effort and loses coherence
  • Tasks too large lead to getting lost
  • Find the sweet spot: each task should be independently completable and verifiable

Quick Start

FOREMAN="python3 ~/.claude/skills/foreman/scripts/foreman.py"

# List available agents
$FOREMAN list

# Find best agent for a task
$FOREMAN match "review this code for security issues"

# Show agent details
$FOREMAN inspect code-reviewer

# Show capability matrix
$FOREMAN capabilities

Workflow

Step 1: Discover Available Agents

$FOREMAN list

Shows all agents from ~/.claude/agents/ (user) and .claude/agents/ (project).

Step 2: Match Task to Agent

$FOREMAN match "description of the task" --json

Returns ranked matches with scores. The matching considers keyword overlap between the task description and each agent's description field.

Note: The matcher does not filter stopwords (e.g., "for", "and", "the"). When scores are close or the workforce has 5+ agents, inspect the top candidates manually.

Step 3: Dispatch

After finding the best agent, dispatch using Claude Code's native Task tool:

"use the {agent-name} agent to {task description}"

Claude Code will:

  1. Load the agent's Markdown file
  2. Apply model, tool, and permission constraints
  3. Run the agent in an isolated context window
  4. Return results to the main conversation

Step 4: Review Results

The agent's output appears in the conversation. Verify:

  • Output quality meets expectations
  • Agent stayed within its constraints (read-only, tool access)
  • Results are actionable

Multi-Agent Dispatch

For tasks needing multiple agents, dispatch sequentially or describe the workflow:

Sequential: "First use code-reviewer to review, then use security-scanner to audit"
Parallel: Launch multiple Task tool calls simultaneously
Pipeline: Chain results — agent A's output becomes agent B's input

Decision: Agent vs CLI

When to use foreman (sub-agent) vs maestro (CLI):

| Signal | Use Foreman (Agent) | Use Maestro (CLI) | |--------|--------------------|--------------------| | Read-only analysis | Yes (fast, cheap) | Overkill | | Needs Codex sandbox | No | Yes | | Needs Gemini 1M context | No | Yes | | Quick specialist task | Yes | Overkill | | Multi-phase with different CLIs | No | Yes | | Budget-sensitive, agent exists | Yes (no CLI startup cost) | No |

Rule of thumb: If a matching agent exists and the task doesn't need cross-CLI capabilities, use the agent. It's faster and cheaper.

Creating New Agents

When no existing agent matches a task, create one:

/create-sub-agent <name>

Or suggest to the user that a new specialized agent would help for recurring tasks.

Integration with Maestro

Maestro can delegate to foreman for lightweight steps in a pipeline:

Pipeline: Build feature
  Phase 1: Claude -p (plan)          → cli_dispatch (needs full reasoning)
  Phase 2: Codex -p (implement)      → cli_dispatch (needs sandbox)
  Phase 3: code-reviewer agent       → agent_dispatch via foreman (read-only, fast)

This hybrid approach uses heavy CLI dispatch for heavy work and lightweight agent dispatch for specialist tasks.

Important Notes

  • Foreman ONLY manages agents within Claude Code. It cannot dispatch to Codex or Gemini.
  • Agent matching is heuristic-based (keyword overlap). For ambiguous matches, inspect the top candidates and choose manually.
  • Sub-agents run in isolated context windows — they cannot see the main conversation. Pass all needed context in the task description.
  • Sub-agents cannot nest (no agent calling another agent). If you need multi-layer orchestration, use maestro + foreman together.

Continuous Improvement

After every invocation:

  1. Reflect — Did the right agent get matched? Was the dispatch effective?
  2. Record — Append lessons to lessons.md
  3. Refine — Update SKILL.md when patterns recur (2+ times)

Contract & API

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

MissingGITHUB OPENCLEW

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/snapshot"
curl -s "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/contract"
curl -s "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/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

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
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 5d 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": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/joneshong-skills-foreman/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/joneshong-skills-foreman/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/joneshong-skills-foreman/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T01:29:19.164Z"
    }
  },
  "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"
    },
    {
      "key": "be",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "delegate",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:be|supported|profile capability:delegate|supported|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": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Joneshong Skills",
    "href": "https://github.com/joneshong-skills/foreman",
    "sourceUrl": "https://github.com/joneshong-skills/foreman",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T01:15:03.026Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T01:15:03.026Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/joneshong-skills-foreman/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 foreman and adjacent AI workflows.