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

Multi Agent Orchestration

by seb1n in seb1n/awesome-ai-agent-skills

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis.

MITAuto-check passedAgent Workflows

Install Multi Agent Orchestration

skills CLI
$ npx skills add seb1n/awesome-ai-agent-skills --skill multi-agent-orchestration -a claude-code

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

GitHub CLI
$ gh skill install seb1n/awesome-ai-agent-skills multi-agent-orchestration --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/seb1n/awesome-ai-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-engineering/multi-agent-orchestration .claude/skills/multi-agent-orchestration && 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
multi-agent-orchestration
GitHub stars
206
Token cost
~1.5k tokens
SKILL.md length
714 words
Files
4 (incl. scripts, references)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis.

  • Works in 6 steps: A decomposition rationale and explicit… → A directed acyclic task graph with… → A handoff protocol and shared-state… → …
  • A task contains genuinely independent workstreams
  • SKILL.md covers Use when, Inputs, Output contract and Workflow, plus 4 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Multi Agent Orchestration is an agent skill from seb1n/awesome-ai-agent-skills. Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/orchestration-patterns.md` and `scripts/validate_plan.py`).

It sits in Agent Workflows, covering Multi-agent orchestration and Task breakdown. The repository describes itself as: 103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other Agent Skills-compatible tools. Complete SKILL.md… The licence is MIT.

When your agent uses it

  • A task contains genuinely independent workstreams
  • Specialized roles
  • Parallel research
  • Reviewer-worker loops

Example prompts

  • “/multi-agent-orchestration”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. A decomposition rationale and explicit non-goals.
  2. A directed acyclic task graph with owner, dependencies, inputs, output contract, write scope, and verification for every task.
  3. A handoff protocol and shared-state policy.
  4. Approval points, timeout and retry limits, escalation routes, and stop conditions.
  5. A synthesis plan that resolves disagreements and verifies the integrated result.
  6. A completion report with evidence, remaining uncertainty, and unused or failed branches.

What it can do on your machine

Read from SKILL.md and the folder at commit 75865a5. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Multi Agent Orchestration loads about 1.5k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 714 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from seb1n/awesome-ai-agent-skills at commit 75865a5, republished under its MIT licence (© seb1n). 714 words, ~1,478 tokens.

Download SKILL.mdSave it as .claude/skills/multi-agent-orchestration/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
multi-agent-orchestration
description
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

Multi-Agent Orchestration

Use multiple agents only when specialization or safe parallelism outweighs coordination cost.

Use when

  • Split a large objective into independent, verifiable workstreams.
  • Coordinate specialists that need distinct tools, permissions, or context.
  • Run worker-reviewer, planner-executor, map-reduce, or bounded debate patterns.
  • Diagnose duplicate work, conflicting edits, weak handoffs, or stalled dependencies.

Do not delegate a tightly coupled, small, or inherently sequential task merely to increase agent count.

Inputs

Collect the objective, completion criteria, task graph, available agents and tools, concurrency limits, shared files or systems, authority boundaries, deadlines, budget, and final decision owner. State assumptions and unresolved dependencies.

Output contract

Produce:

  1. A decomposition rationale and explicit non-goals.
  2. A directed acyclic task graph with owner, dependencies, inputs, output contract, write scope, and verification for every task.
  3. A handoff protocol and shared-state policy.
  4. Approval points, timeout and retry limits, escalation routes, and stop conditions.
  5. A synthesis plan that resolves disagreements and verifies the integrated result.
  6. A completion report with evidence, remaining uncertainty, and unused or failed branches.

Workflow

  1. Define one measurable objective and the authority boundary before assigning work.
  2. Decompose by separable outputs, not vague roles. Keep shared mutable state to a minimum and retain tightly coupled steps under one owner.
  3. Draw dependencies and identify the critical path. Parallelize only tasks with independent inputs and non-overlapping side effects. Read orchestration-patterns.md when choosing a topology.
  4. Assign one accountable owner per task. Specify inputs, deliverable format, write scope, validation, deadline or timeout, and what warrants escalation.
  5. Give each agent the minimum context and permissions needed. Include source artifacts, not hidden conclusions, when independent judgment matters.
  6. Require structured handoffs: status, result, evidence, changed state, assumptions, risks, and next dependency. Acknowledge receipt before downstream mutation.
  7. Monitor dependency state and useful progress. Bound retries and debates; do not recursively delegate without a clear capacity and ownership model.
  8. Synthesize centrally or through a named integrator. Resolve conflicting claims from primary evidence, run integration checks, and confirm the original completion criteria.
  9. Close or cancel unused work, record unresolved risks, and return control to the final decision owner.

Use python3 scripts/validate_plan.py plan.json --strict before execution. The command structurally checks dependencies, cycles, ownership, approval references, and numeric execution bounds. Strict mode also fails on warnings, including exact parallel write conflicts, missing timeout/retry bounds, and incomplete retry contracts. It validates declarations only; it cannot verify runtime isolation, authorization, approval authenticity, or actual task behavior.

Show full SKILL.md (307 more words)Show less

Safety and permissions

  • Delegation never expands authority. Do not let a child agent perform an action the requester did not authorize.
  • Reserve external messages, purchases, deployments, destructive actions, credential access, and production changes for explicit approval points.
  • Isolate credentials and sensitive context by role; do not broadcast secrets through shared state or handoffs.
  • Use single-writer ownership, branches, transactions, or locks for mutable resources.
  • Preserve user-owned changes and make cancellation recoverable.

Verification

  • Validate the plan is acyclic and every dependency and approval reference resolves. Tag consequential work with consequential, deploy, or external-mutation and require its task-local approval_ref to name an approval point for that task.
  • Confirm concurrently runnable tasks do not write the same file, record, branch, or environment.
  • Check every handoff against its output contract before unblocking dependents.
  • Re-run end-to-end tests or evidence checks after synthesis; individual task success is insufficient.
  • Confirm the final report accounts for all tasks as completed, failed, canceled, or superseded.

Failure handling

  • If an agent stalls, inspect its last evidence, retry once only when the failure is transient, then reassign or collapse the task.
  • If agents disagree, ask each for source-backed claims and let the named integrator adjudicate; do not average incompatible answers.
  • If shared state conflicts, pause writers, preserve both versions, and reconcile through the single owner.
  • If a dependency fails, block or redesign downstream work instead of silently fabricating its input.
  • If coordination overhead exceeds remaining work, stop delegation and complete the critical path under one owner.

Example

For “prepare and implement a cross-platform authentication change,” keep architecture and integration under one owner, delegate independent threat modeling and test-fixture design, assign non-overlapping implementation files only after the interface is frozen, require each handoff to include changed paths and test evidence, gate production configuration behind approval, and have the integrator run the complete suite and reconcile security findings before declaring completion.

© seb1n, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in agent-engineering/multi-agent-orchestration of seb1n/awesome-ai-agent-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/orchestration-patterns.md
  • scripts/validate_plan.py

Open the folder on GitHubat commit 75865a5

Compare with similar skills

Multi Agent Orchestration 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.

Multi Agent Orchestration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Multi Agent Orchestration this skillseb1n/awesome-ai-agent-skills206—~1.5kAutomated safety check: PassMIT
MemPalace Task HandoffMemPalace/mempalace59k—~1.9kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
Agtx Task Sweepfynnfluegge/agtx1.7k—~1.7kAutomated safety check: PassApache-2.0
Cookrjcorwin/cook371—~1.5kAutomated safety check: PassNone
OMA Multi-Agent Orchestratorfirst-fluke/oh-my-agent1.3k—~3.1kAutomated safety check: PassMIT

Similar skills

  • MemPalace Task Handoff

    MemPalace/mempalace

    Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.

    59k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • agtx One-Shot Project Runner

    fynnfluegge/agtx

    Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • Agtx Task Sweep

    fynnfluegge/agtx

    Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

    1.7k GitHub stars~1.7k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • Cook

    rjcorwin/cook

    Agent orchestration primitives — review loops, repeat passes, parallel races, and task-list progression.

    371 GitHub stars~1.5k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • OMA Multi-Agent Orchestrator

    first-fluke/oh-my-agent

    Splits a complex feature into prioritized tasks, spawns specialist CLI subagents in parallel, tracks them through shared memory and verifies each result.

    1.3k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Swarm Parallel Dispatch

    langchain-ai/langchain-skills

    Official

    Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.

    1.3k GitHub stars~3k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from seb1n/awesome-ai-agent-skills

All 91 skills in this repo

  • Agent Red Teaming

    seb1n/awesome-ai-agent-skills

    Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.

    206 GitHub stars~2.8k tokensUpdated 2 mo ago
    Auto-check passed

  • Eu AI Act Readiness

    seb1n/awesome-ai-agent-skills

    Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…

    206 GitHub stars~3.3k tokensUpdated 2 mo ago
    Auto-check passed

  • Human In The Loop

    seb1n/awesome-ai-agent-skills

    Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

  • MCP Server Building

    seb1n/awesome-ai-agent-skills

    Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

  • Skill Supply Chain Audit

    seb1n/awesome-ai-agent-skills

    Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk.

    206 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Spreadsheet Analysis

    seb1n/awesome-ai-agent-skills

    Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files.

    206 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Multi Agent Orchestration

What does Multi Agent Orchestration do?

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Multi Agent Orchestration is an agent skill from seb1n/awesome-ai-agent-skills. Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis.

When should I use Multi Agent Orchestration?

Multi Agent Orchestration fits situations like: A task contains genuinely independent workstreams; specialized roles; parallel research; reviewer-worker loops.

How do I install Multi Agent Orchestration in Claude Code?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill multi-agent-orchestration -a claude-code`. Or copy the skill folder (agent-engineering/multi-agent-orchestration in seb1n/awesome-ai-agent-skills) into .claude/skills/multi-agent-orchestration in your project. Claude Code loads it when a task matches its description.

How do I install Multi Agent Orchestration in Codex?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill multi-agent-orchestration -a codex`. Or copy the skill folder (agent-engineering/multi-agent-orchestration in seb1n/awesome-ai-agent-skills) into .agents/skills/multi-agent-orchestration in your project. Codex loads it when a task matches its description.

Can I use Multi Agent Orchestration 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 seb1n/awesome-ai-agent-skills --skill multi-agent-orchestration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multi-agent-orchestration, .gemini/skills/multi-agent-orchestration, .github/skills/multi-agent-orchestration and .opencode/skills/multi-agent-orchestration in your project.

What does Multi Agent Orchestration need to run?

Going by SKILL.md and its folder, Multi Agent Orchestration needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Multi Agent Orchestration 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 Multi Agent Orchestration 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Multi Agent Orchestration use?

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

How many tokens does Multi Agent Orchestration use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Multi Agent Orchestration?

Skills that share tags, products or a category with Multi Agent Orchestration: MemPalace Task Handoff (MemPalace/mempalace, 59k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars) and Cook (rjcorwin/cook, 371 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Multi Agent Orchestration?

seb1n (a GitHub user) maintains it in seb1n/awesome-ai-agent-skills, which has 206 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on August 9, 2026.

Source: seb1n/awesome-ai-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.