Agent skill

Orchestrator

by udecode in udecode/plate

Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

Custom licenceAuto-check passedDevelopment

Install Orchestrator

skills CLI
$ npx skills add udecode/plate --skill orchestrator -a claude-code

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

GitHub CLI
$ gh skill install udecode/plate orchestrator --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/udecode/plate.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/orchestrator .claude/skills/orchestrator && 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
orchestrator
GitHub stars
17k
Token cost
~1.3k tokens
SKILL.md length
644 words
Files
1
Skills in repo
78
Repo updated
First seen
Licence
Custom licence

At a glance

Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

  • Works in 9 steps: Classify the request. → If it is not per-branch, handle it in… → If it is per-branch, find the branch key → …
  • Tasks that involve Git worktrees
  • SKILL.md covers Commands, Core Contract, Per-Branch Task and Routing Rules, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Orchestrator is an agent skill from udecode/plate. Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Git worktrees. The repository describes itself as: Rich-text editor with AI and shadcn/ui.

When your agent uses it

  • Tasks that involve Git worktrees

Example prompts

  • “/orchestrator”

Workflow steps

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

  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
  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
  7. Tell the child thread exactly what skill/request to run and include the
  8. Ask the child thread to report its branch key, PR URL, blockers, and next
  9. Record the mapping in the orchestrator status

What it can do on your machine

Read from SKILL.md and the folder at commit 6f3815d. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Orchestrator loads about 1.3k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 644 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 644 words (~1,310 tokens).

“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.”

— opening of SKILL.md by udecode, Custom licence
name
orchestrator

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/orchestrator of udecode/plate.

Open the folder on GitHubat commit 6f3815d

Compare with similar skills

Orchestrator 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.

Orchestrator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Orchestrator this skilludecode/plate17k—~1.3kAutomated safety check: PassCustom licence
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Build Px4 macOSPX4/PX4-Autopilot13k—~1.1kAutomated safety check: PassBSD-3-Clause
WorktreeAgentsMesh/AgentsMesh2.4k—~553Automated safety check: NotesCustom licence
Git Worktree IsolationjnMetaCode/superpowers-zh8.3k1 repos~982Automated safety check: PassMIT
Cursor Composer Task DelegateChachamaru127/claude-code-harness3.2k—~4.4kAutomated safety check: NotesMIT

Similar skills

  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Build Px4 macOS

    PX4/PX4-Autopilot

    Build PX4 board firmware on macOS in the px4-dev Docker container, including git worktrees, and stage commit-labeled artifacts without flashing hardware.

    13k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Worktree

    AgentsMesh/AgentsMesh

    Creates or reuses an isolated AgentsMesh Git worktree from a verified base branch, preserves existing changes, and optionally starts the worktree-scoped development environment.

    2.4k GitHub stars~553 tokensUpdated 15 days ago
    DevelopmentAuto-check: notes
  • Git Worktree Isolation

    jnMetaCode/superpowers-zh

    Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.

    8.3k GitHub starsUsed in 1 repo~982 tokens
    DevelopmentAuto-check passed
  • Cursor Composer Task Delegate

    Chachamaru127/claude-code-harness

    Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

    3.2k GitHub stars~4.4k tokensUpdated 3 days ago
    DevelopmentAuto-check: notes
  • Automate git worktree creation and copy private files (not tracked in git) to new workdirs.

    155 GitHub stars~930 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

More from udecode/plate

All 78 skills in this repo
  • React Useeffect

    udecode/plate

    React useEffect best practices from official docs. An agent skill from udecode/plate.

    17k GitHub starsUsed in 6 repos~573 tokens
    Auto-check passed
  • Video Transcripts

    udecode/plate

    Generate structured video transcripts from local files or video URLs using Gemini Files API.

    17k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Build new Plate plugins with Slate-first architecture, sane typing, and explicit React/Plate wrapper boundaries.

    17k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Plate UI

    udecode/plate

    Build new shadcn-style components for Plate's registry and editor surfaces.

    17k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Researches and synthesizes external best practices, documentation, and examples for any technology or framework.

    17k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Frontend Design

    udecode/plate

    Build web interfaces with genuine design quality, not AI slop.

    17k GitHub stars~3.6k tokensUpdated today
    Auto-check passed

Questions about Orchestrator

What does Orchestrator do?

Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees. Orchestrator is an agent skill from udecode/plate. Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

When should I use Orchestrator?

Orchestrator fits situations like: tasks that involve Git worktrees.

How do I install Orchestrator in Claude Code?

Run `npx skills add udecode/plate --skill orchestrator -a claude-code`. Or copy the skill folder (.agents/skills/orchestrator in udecode/plate) into .claude/skills/orchestrator in your project. Claude Code loads it when a task matches its description.

How do I install Orchestrator in Codex?

Run `npx skills add udecode/plate --skill orchestrator -a codex`. Or copy the skill folder (.agents/skills/orchestrator in udecode/plate) into .agents/skills/orchestrator in your project. Codex loads it when a task matches its description.

Can I use Orchestrator 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 udecode/plate --skill orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/orchestrator, .gemini/skills/orchestrator, .github/skills/orchestrator and .opencode/skills/orchestrator in your project.

What does Orchestrator need to run?

SKILL.md names no scripts, command-line tools or credentials: Orchestrator is instructions for the agent only.

Does Orchestrator 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 Orchestrator 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. Review the folder before installing.

What licence does Orchestrator use?

Orchestrator has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Orchestrator use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Orchestrator?

Skills that share tags, products or a category with Orchestrator: Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Build Px4 macOS (PX4/PX4-Autopilot, 13k stars), Worktree (AgentsMesh/AgentsMesh, 2.4k stars) and Git Worktree Isolation (jnMetaCode/superpowers-zh, 8.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orchestrator?

udecode (a GitHub organization) maintains it in udecode/plate, which has 16,642 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 8, 2026.

Source: udecode/plate on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.