orchestrator

A coordination skill that turns the current coding-agent conversation into a chief-of-staff thread for routing branch-specific implementation work to reusable child threads.

In plain words
What is it for?
Use it to coordinate tickets, issue work, API migrations, and pull-request feedback across multiple implementation threads.
Why use it?
It keeps intake, routing, status, and context in one place while separate threads handle work tied to individual branches or pull requests.

Skill for Claude CodeCodex

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/udecode/plate-template/orchestrator
Any agent
npx skills add udecode/plate-template --skill orchestrator
Clone the repo
git clone --depth 1 https://github.com/udecode/plate-template

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,191 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00030 $0.01191
Opus 5 $0.00015 $0.00596
Sonnet 5 $0.00006 $0.00238
Haiku 4.5 $0.00003 $0.00119

Measured 3d ago against content hash 868da8f887c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator 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 3d ago.

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.

Origin

This is a copy

100% identical to orchestrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/orchestrator/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator

Use this skill when the user wants the current thread to act as a chief-of-staff thread: route work, keep context, check child threads, and avoid doing implementation locally.

Commands

  • $orchestrator on: activate orchestration-only mode for this thread.
  • $orchestrator off: return this thread to normal local execution.
  • $orchestrator status: report mode, active child threads, known branch keys, and blockers.

Do not add a manual routing command. In orchestrator mode, routing is automatic.

Core Contract

When orchestrator mode is on:

  • Do not implement product code in this thread.
  • Do not create or suggest worktrees.
  • Automatically route any per-branch task to a child thread.
  • Reuse the same child thread for future work on the same branch.
  • Keep this thread for intake, triage, routing, status, summaries, and context forwarding.
  • If mode state is unclear, ask once before executing locally.

Per-Branch Task

A per-branch task is any work that is expected to create, modify, review, or continue a code branch, PR, or branch-scoped implementation plan.

Examples:

  • Ticket execution.
  • Issue execution.
  • API migration work.
  • PR feedback resolution.
  • Code-changing bug, feature, refactor, or migration.
  • Goal-backed implementation that would touch files or branch state.
  • Follow-up phrased as "continue", "fix CI", "push", "commit", or "that branch" when it refers to an existing branch.

Not per-branch by default:

  • One-off answers.
  • Read-only status summaries.
  • Cross-thread triage.
  • External context intake.
  • Asking which child thread owns a branch when the mapping is missing.

Routing Rules

  1. Classify the request.
  2. If it is not per-branch, handle it in the orchestrator thread.
  3. If it is per-branch, find the branch key:
    • explicit branch name
    • PR branch
    • tracker issue branch already recorded
    • child thread title or prior status mentioning the branch
    • if no branch exists yet, use the tracker/workstream key until the child creates and reports the branch
  4. Find an existing child thread for that branch key.
  5. If found, send the new instruction to that child thread.
  6. If not found, create a new child thread with a title like:

Read the full file on GitHub · 154 lines

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. 3d ago First seen · 154 lines · 30 tokens per session scan A 868da8f887c7

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository udecode/plate-template (59 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,191 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to orchestrator, differing in 0 lines, and is treated as a copy.