New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Orchestration Skill

by OpenLoaf in OpenLoaf/OpenLoaf

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

AGPL-3.0Auto-check passedAgent Workflows

Install Agent Orchestration Skill

skills CLI
$ npx skills add OpenLoaf/OpenLoaf --skill agent-orchestration-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OpenLoaf/OpenLoaf agent-orchestration-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/agent-orchestration/en .claude/skills/agent-orchestration-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-orchestration-skill
GitHub stars
108
Token cost
~1.9k tokens
SKILL.md length
717 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

  • Tasks that involve Subagents
  • SKILL.md covers Tool Inventory, Delegation Decision, Six Built-in Subagents and Agent Tool Invocation, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Multi-agent orchestration

What it does

Agent Orchestration Skill is an agent skill from OpenLoaf/OpenLoaf. Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor / canvas-designer / coder, etc.). Not for: single-step Q&A / reads / simple side effects (master Agent handles directly), or scenarios where Agent is already confirmed and subagenttype is known.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents, Multi-agent orchestration and Data analysis. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve Multi-agent orchestration
  • Tasks that involve Data analysis

Example prompts

  • “Use the agent-orchestration-skill skill to trigger when the master Agent faces a multi-step complex task and is deciding whether / how to outsource…”
  • “/agent-orchestration-skill”

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Orchestration Skill loads about 1.9k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 717 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 717 words, ~1,863 tokens.

Download SKILL.mdSave it as .claude/skills/agent-orchestration-skill/SKILL.md (or your agent's skills folder).
name
agent-orchestration-skill
description
Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor / canvas-designer / coder, etc.). **Not for**: single-step Q&A / reads / simple side effects (master Agent handles directly), or scenarios where `Agent` is already confirmed and `subagent_type` is known.
version
5.0.0

Subagent Delegation & the Agent Tool

The master Agent can dispatch built-in or custom subagents on demand via the Agent tool, outsourcing specialized sub-tasks. This skill answers four questions: when to delegate, to whom, how to invoke, and what the system constraints are.

Tool Inventory

ToolResponsibilityRead-only
AgentLaunches a built-in or custom subagent by subagent_type to handle a multi-step complex taskNo

Loading: Agent is a core tool — always available, no ToolSearch activation required.

Delegation Decision

User message →
  ├─ Simple Q&A / chat / read / query / single-step side effect (create event, send email, create project) → master Agent handles directly
  └─ Multi-step complex task →
      ├─ Web interaction (click/fill form/login/screenshot/paginated scraping) → browser
      ├─ Rich text / long document editing (Markdown, DOCX, PDF) → doc-editor
      ├─ Spreadsheet data analysis / chart generation → data-analyst
      ├─ Structured extraction from PDF / images / web pages → extractor
      ├─ Canvas node operations / layout → canvas-designer
      ├─ Code writing / debugging (global mode only; in project mode the PM does it themselves) → coder
      └─ Mixed task → master Agent decomposes, then delegates to multiple subagents sequentially or in parallel

Don't "delegate everything": simple Q&A, single-step operations, and pure reads should be handled directly by the master Agent. Delegation itself introduces context-passing overhead and extra steps — for small tasks the cost outweighs the benefit.

Six Built-in Subagents

Each subagent has its own system prompt and tool set, with step counts tuned to the task profile.

SubagentWhen to triggerTool setSteps
📝 doc-editorRich text / Markdown / Word / PDF editing, long-document rewritingWrite, Read, Glob15
🌐 browserPage navigation, DOM interaction, form filling, screenshots, paginated scrapingbrowser-*, WebSearch20
📊 data-analystCSV/Excel cleaning, statistical computation, ECharts/Mermaid chartsRead, Write, Bash15
🔍 extractorPDF/image OCR, table extraction, multi-document comparison extractionRead, office-read, WebFetch10
🎨 canvas-designerNode add/remove/update, auto layout, text-to-canvas conversioncanvas-*, canvas-read15
💻 coderMulti-language code writing / review / debuggingWrite, Read, Grep, Glob, Bash20

Agent Tool Invocation

Agent { description: "Scrape product table from site A", prompt: "...", subagent_type: "browser" }
ParameterPurpose
descriptionShort title, shown to the user as progress
promptThe full instruction handed to the subagent
subagent_typeSubagent type
subagent_typeScenarioCapabilities
general-purposeGeneral tasks (default)Full tool set
exploreCodebase/doc exploration, read-only analysisRead-only tools
planSolution design, produce an implementation planRead-only tools
Any of the 6 built-in subagent names aboveSpecialized tasksTool set defined per subagent
Custom Agent nameA registered specialized AgentTool set defined by that Agent

The Agent tool waits synchronously by default for the subagent to complete and return — after calling, you immediately get the output and proceed to the next step; no extra wait tool needed.

SendMessage: Follow-up Instructions

When a subagent is already running but needs additional instructions or a course correction:

SendMessage { toolCallId: "agent-xxx", message: "Additional requirement: output results in JSON format" }

SendMessage auto-resumes a stopped agent — no need to recreate via Agent, avoiding the cost of re-passing the full context.

Parallel Fan-out & Aggregation

When sub-tasks are independent of each other, issue multiple Agent calls in the same turn; each returns synchronously, and the master Agent aggregates:

Master Agent decomposes task → issues in parallel:
  Agent { description: "Scrape site A", subagent_type: "browser", prompt: "..." }
  Agent { description: "Scrape site B", subagent_type: "browser", prompt: "..." }
  Agent { description: "Scrape site C", subagent_type: "browser", prompt: "..." }
  ↓ Each returns synchronously: A / B / C
Master Agent aggregates → final response

Good for parallel: sub-tasks are independent and parallelism meaningfully shortens total runtime. Not for parallel: later tasks depend on earlier tasks' output (serial dependency); total count exceeds the concurrency limit of 4 and needs batching.

Show full SKILL.md (299 more words)Show less

Context Inheritance

Subagents automatically inherit from the master Agent:

  • projectId — same project sandbox; path permissions and file access stay consistent
  • Skills tied to pageContext — the subagent sees the same capability awareness (if the master Agent creates an extractor on the email page, the extractor also sees email-ops)
  • Temporary project path — if the master Agent has created a temp project, subagents share that directory

This means you don't need to repeat environment information in the prompt — the subagent can derive it from inherited context.

System Hard Limits

LimitValueRationale
Max delegation depth2 (master → sub; sub cannot spawn further)Each level copies context — deeper nesting grows token consumption exponentially; also avoids cascading failures that are hard to diagnose
Max concurrency4 subagentsBalance point between response speed and system resources (memory, API connections)
Auto cleanup5 minutesCompleted Agents are auto-removed from memory to prevent accumulation leaks
Hard step limitMaster 200 / Sub 10-20Sub values as listed above; Master has a larger budget for coordination work

Subagent streaming output is pushed to the frontend via data-sub-agent-start / delta / chunk / end events. Each toolCallId corresponds to one independent stream, supporting multiple concurrent subagents streaming simultaneously. State transitions: output-streaming → output-available | output-error.

Common Misjudgments

  • Don't nest hierarchically: subagents cannot spawn further subagents. When deeper nesting seems needed, re-decompose so the master Agent invokes multiple subagents in sequence.
  • Don't pick the wrong type: for page interaction choose browser; to merely read a static page use WebFetch (the master Agent can call it directly); for OCR choose extractor; for precise DOM manipulation choose browser.
  • Don't re-Agent when one already exists: use SendMessage to append instructions and reuse the existing context.
  • Don't delegate simple tasks: a single read, a single query, a single create — the master Agent doing it itself is far faster than delegating.

© OpenLoaf, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in apps/server/src/ai/builtin-skills/agent-orchestration/en of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6

Compare with similar skills

Agent Orchestration Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Orchestration Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Orchestration Skill this skillOpenLoaf/OpenLoaf108—~1.9kAutomated safety check: PassAGPL-3.0
WavesRayFernando1337/rayfernando-skills130—~9.7kAutomated safety check: PassApache-2.0
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Kimi Code DelegationCherryHQ/cherry-studio52k1 repos~504Automated safety check: PassAGPL-3.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0

Similar skills

  • Waves

    RayFernando1337/rayfernando-skills

    WAVES — Workers · Aggregate · Verify · Extend — wave-based orchestration for Cursor.

    130 GitHub stars~9.7k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Kimi Code Delegation

    CherryHQ/cherry-studio

    Delegates one bounded repository task to Kimi Code in non-interactive prompt mode and reads back the final result from its JSON event stream.

    52k GitHub starsUsed in 1 repo~504 tokens
    Agent WorkflowsAuto-check passed

  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

More from OpenLoaf/OpenLoaf

All 33 skills in this repo

  • Browser Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…

    108 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

  • Canvas Ops Skill

    OpenLoaf/OpenLoaf

    Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.

    108 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed

  • Word Document Read, Write and Convert

    OpenLoaf/OpenLoaf

    Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.

    108 GitHub stars~1.9k tokensUpdated 4 mo ago
    Auto-check passed

  • Email Operations

    OpenLoaf/OpenLoaf

    Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.

    108 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check passed

  • macOS Desktop Control

    OpenLoaf/OpenLoaf

    Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.

    108 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed

  • PDF Skill

    OpenLoaf/OpenLoaf

    All-in-one PDF read / write / convert / OCR. An agent skill from OpenLoaf/OpenLoaf.

    108 GitHub stars~2k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Agent Orchestration Skill

What does Agent Orchestration Skill do?

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…. Agent Orchestration Skill is an agent skill from OpenLoaf/OpenLoaf.).

When should I use Agent Orchestration Skill?

Agent Orchestration Skill fits situations like: tasks that involve Subagents; tasks that involve Multi-agent orchestration; tasks that involve Data analysis.

How do I install Agent Orchestration Skill in Claude Code?

Run `npx skills add OpenLoaf/OpenLoaf --skill agent-orchestration-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/agent-orchestration/en in OpenLoaf/OpenLoaf) into .claude/skills/agent-orchestration-skill in your project. Claude Code loads it when a task matches its description.

How do I install Agent Orchestration Skill in Codex?

Run `npx skills add OpenLoaf/OpenLoaf --skill agent-orchestration-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/agent-orchestration/en in OpenLoaf/OpenLoaf) into .agents/skills/agent-orchestration-skill in your project. Codex loads it when a task matches its description.

Can I use Agent Orchestration Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLoaf/OpenLoaf --skill agent-orchestration-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-orchestration-skill, .gemini/skills/agent-orchestration-skill, .github/skills/agent-orchestration-skill and .opencode/skills/agent-orchestration-skill in your project.

What does Agent Orchestration Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Orchestration Skill is instructions for the agent only.

Does Agent Orchestration Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Orchestration Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Orchestration Skill use?

Agent Orchestration Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Orchestration Skill use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Orchestration Skill?

Skills that share tags, products or a category with Agent Orchestration Skill: Waves (RayFernando1337/rayfernando-skills, 130 stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars) and Kimi Code Delegation (CherryHQ/cherry-studio, 52k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Orchestration Skill?

OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.

Source: OpenLoaf/OpenLoaf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.