What is claude-orchestration?

A plugin for coordinating multiple coding agents on one complex feature. It delegates work, tracks tasks, and uses separate Git worktrees so agents can implement changes independently.

Use it to plan parallel agent tasks, coordinate their progress, and combine their implementations through a shared workflow.

It helps split large work into parallel pieces while keeping each agent's files and branch isolated.

claude-orchestration — Plugin for Claude Code by bengous: A plugin for coordinating multiple coding agents on one…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add bengous/claude-code-plugins

agentmods

npx agentmods add plugins/bengous/claude-code-plugins/orchestration

Clone the repo

git clone --depth 1 https://github.com/bengous/claude-code-plugins

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/orchestration.svg)](https://agentmods.dev/plugins/bengous/claude-code-plugins/orchestration)

Your own site

<a href="https://agentmods.dev/plugins/bengous/claude-code-plugins/orchestration"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/orchestration.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 6 commands, 3 agents cost 174 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-orchestration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

orchestration/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "claude-orchestration",
  "version": "2.8.0",
  "description": "Parallel multi-agent orchestration for complex features with Task-based coordination and git-wt --stack worktree isolation",
  "author": {
    "name": "Augustin BENGOLEA",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/bengous/claude-code-plugins",
  "repository": "https://github.com/bengous/claude-code-plugins",
  "license": "MIT",
  "keywords": [
    "orchestration",
    "workflow",
    "automation",
    "multi-agent",
    "delegation",
    "git-worktree",
    "stack"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 6 commands, 3 agents travel with it, and installing the plugin installs all of them — 174 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 22 lines scan A ff4251c74f78

Subscribe to this mod's changes

claude-orchestration is a plugin published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Project management automation claude-code developer-tools workflow

taskwarrior

Token-dense recipes for taskwarrior CLI: dense listings, single-field lookups, batched exports, full-text search.

technicalpickles/pickled-claude-plugins · not measured

weft

Deterministic workflow tracking with event-sourced logs for Claude Code.

dioptx/weft · not measured

cc-code

极简开发工作流系统。角色串行(PM→Architect→Dev→QA) + L0L4 文件分层的状态机循环。/cc-code:init 三轨初始化（新建/已最新/旧版升级迁移，全程零删除），13 skill + 3 配套 agent，含 /cc-code:plan-prd-feature 增量迭代规划、/cc-code:whole-qa 全量验收修复闭环与 /cc-code:experience-summary 项目级经验沉淀（references 按需读取）。⭐0.10.0 codegraph 全静默深度集成（15/15 能力：静默建索引 + affected 精准回归 + impact 真爆炸半径 + 角色权限矩阵，人零心智负.

weiyi88/cc-code · not measured

ticket-flow

Beads-backed ticket workflow for Claude Code: spec → pickup → implement → finish behind verdict and merge gates, orchestrated by /flow (--local with resume, --parallel, --serial/--loop unattended queue runner), each ticket in its own git worktree. Five visible commands; the phase skills are model-invoked.

keefar/ticket-flow · not measured

aiwork

.aiwork/ folder protocol for AI work artifacts, plus skills for the full loop: triage → spec → tickets → implement → review.

lttr/claude-marketplace · not measured

csw

Ship a tracker ticket: dispatch it into a worktree, drive it to a pull request, merge it after review, and clean up after itself.

mikestankavich/claude-ship-workflow · not measured