orchestrate

orchestrate is a skill for Claude Code, Codex from Kasempiternal/Claude-Agent-System. It costs 79 tokens per session (2,270 once invoked), scanned A, original, MIT.

An orchestrator mode for Claude Agent System that assigns work to teams while the main agent acts as the coordinator. It is beta, and its full end-to-end behavior is untested.

In plain words
What is it for?
Use it when you want a central coordinator to direct multiple teams or agents. Its documentation also describes setup and troubleshooting for the Orchestrator output style.
Why use it?
Large tasks can be difficult to coordinate when all work is handled in one place. This provides a role and workflow for delegating work and combining the results.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cas plugin — 19 skills, 7 agents, 3 hooks, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/kasempiternal/claude-agent-system/orchestrate
Any agent
npx skills add Kasempiternal/Claude-Agent-System --skill orchestrate
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code, Codex.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 7 agents, 3 hooks, 2 MCP servers.

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.

agentmods badge for orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/orchestrate.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/orchestrate)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/orchestrate"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,270 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.02270
Opus 5 $0.00039 $0.01135
Sonnet 5 $0.00016 $0.00454
Haiku 4.5 $0.00008 $0.00227

Measured 5d ago against content hash f91851b1c7af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

orchestrate 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/orchestrate-state.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

claude-agent-system-plugin/skills/orchestrate/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

 ██████╗ ██████╗  ██████╗██╗  ██╗███████╗███████╗████████╗██████╗  █████╗ ████████╗███████╗
██╔═══██╗██╔══██╗██╔════╝██║  ██║██╔════╝██╔════╝╚══██╔══╝██╔══██╗██╔══██╗╚══██╔══╝██╔════╝
██║   ██║██████╔╝██║     ███████║█████╗  ███████╗   ██║   ██████╔╝███████║   ██║   █████╗
██║   ██║██╔══██╗██║     ██╔══██║██╔══╝  ╚════██║   ██║   ██╔══██╗██╔══██║   ██║   ██╔══╝
╚██████╔╝██║  ██║╚██████╗██║  ██║███████╗███████║   ██║   ██║  ██║██║  ██║   ██║   ███████╗
 ╚═════╝ ╚═╝  ╚═╝ ╚═════╝╚═╝  ╚═╝╚══════╝╚══════╝   ╚═╝   ╚═╝  ╚═╝╚═╝  ╚═╝   ╚═╝   ╚══════╝

        ◎ Orchestrator Mode — you are the CEO, your teams do the work ◎
                          CLAUDE AGENT SYSTEM
                     ⚠ BETA — UNTESTED END-TO-END ⚠

MANDATORY: Output the banner above verbatim as your very first message, before any tool calls.

⚠ BETA — UNTESTED END-TO-END

This skill and its Orchestrator output style have passed script-level smoke tests but have not been run end-to-end in a real Claude Code session. Expect rough edges:

  • The exact outputStyle value for a plugin-shipped style is undocumented — "Orchestrator" is an inference. If the persona doesn't engage after /clear, set it via /config → Output style → Orchestrator.
  • Output styles take effect only on a fresh session (/clear or restart) — /orchestrate on cannot flip it mid-session.
  • Keep-alive agent lifecycle, handoff archiving, and the SessionStart resume hook are unverified under live conditions.

Before relying on it: try it in a throwaway project. To disarm, run /orchestrate off (+ /clear) or switch the output style back via /config. Feedback: https://github.com/Kasempiternal/Claude-Agent-System/issues

You are entering / managing Orchestrator Mode. The persistent CEO behavior lives in the Orchestrator output style; this skill activates that mode, seeds an objective workspace, and runs the CEO loop.

How the two pieces fit

  • The Orchestrator output style (output-styles/orchestrator.md) is the persona — it makes the whole session delegate-first. Selected once via /config, it persists across every session until you switch away. This is why you don't re-invoke a skill each time.
  • This /orchestrate skill is the control surface — it flips the setting on/off, seeds the per-objective workspace, and kicks off a CEO loop on a specific goal.

Platform reality (be honest with the user): output styles are read once at session start. /orchestrate on writes the setting but it only takes effect after /clear or a new session — the skill cannot flip the persona mid-session. The exact setting value for a plugin-shipped style is undocumented; the script writes the grounded inference ("Orchestrator") and tells the user the authoritative /config path as a fallback.

Read the full file on GitHub · 110 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 5d ago First seen · 110 lines · 79 tokens per session scan A f91851b1c7af

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 2,270 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

ops-pocket

OPS on-demand: This skill should be used when the user asks to "pocket memos", "voice memo pipeline"…

Lifecycle-Innovations-Limited/claude-ops · 29 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

extract-resume

Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.

suxrobGM/jobpilot · 32 tokens