Claude Code mod
orchestrator
Turns a session into an orchestrator that delegates work to haiku and sonnet subagents, keeps its own context small, sizes each task to about 150K tokens of subagent context, and lists the running and past agents in an expandable band (/orchestrator on|off|status)
Install
/plugin marketplace add rotembm12/claude-mods
/plugin install orchestrator@rotem-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads mod state, persists state, draws
- Sees
- every prompt, Agent calls, subagent spawns, every tool call
- Draws in
AbovePrompt- Hooks
session.startcommand.runui.renderprompt.submitprompt.composeagent.offertool.callagent.spawnturn.complete
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- rotembm12/claude-mods
- Folder
orchestrator- Marketplace
rotem-mods- Author
- Rotem
- Last updated
- 8 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is orchestrator?
Turns a session into an orchestrator that delegates work to haiku and sonnet subagents, keeps its own context small, sizes each task to about 150K tokens of subagent context, and lists the running and past agents in an expandable band (/orchestrator on|off|status) It is a mod for Claude Code, from rotembm12/claude-mods on GitHub.
What can the orchestrator mod access?
Its widest reach is "writes or runs" (drives Claude, reads mod state, persists state, draws). It sees every prompt, Agent calls, subagent spawns, every tool call. It draws in AbovePrompt. Like any mod, it runs with your permissions.
How do I install orchestrator?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add rotembm12/claude-mods and then /plugin install orchestrator@rotem-mods.
More context & usage mods
orchestrator
katipally/modz
Pick orchestrator settings once; the main agent delegates all reads and writes, and subagent limits (models, how many run at once, context per subagent) are enforced
origami
dullfig/origami
Variable-resolution context: folds bulky stale tool output to disk behind always-visible stubs; hydrate() recovers detail on demand.
openspec-status
pierreboissinot/openspec-status
Shows the OpenSpec changes of the open project under the prompt, for local roots and stores, and warns in any project when the context fills up.
paceline
rogadev/paceline-mod
Paces your Claude usage limits: today's budget, session and week limits, and where each session stands, in a line above the prompt
oneliner
deadraw/OneLiner
A calm instrument strip for Claude Code: 5-hour limit with forecast, prompt-cache countdown, context fill, git changes and ship, helper agents, prompt upgrade, a work report, and next-step ideas, in one line above your prompt.
painel-lateral
fabioivandro04-lgtm/painel-lateral
Painel lateral com abas: tarefas, tokens e custo, log de ferramentas, arquivos alterados e notas.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.