orchestrator

orchestrator is an agent for Claude Code from Simone-Tarantino/godot-superpowers. It costs 85 tokens per session (2,434 once invoked), scanned A, original, MIT.

An agent role for breaking an approved game milestone or feature plan into smaller tasks for other coding agents. A milestone is a defined chunk of game development work.

In plain words
What is it for?
Use it to dispatch parallel workers for a Godot game milestone or feature, collect their summaries, and send the results for file verification.
Why use it?
It coordinates multi-file work and checks that the required design and planning documents are approved before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the godot-superpowers plugin — 33 skills, 15 agents, 4 hooks, 5 MCP servers shipped together

Good fit Use it to dispatch parallel workers for a Godot game milestone or feature, collect their summaries, and send the results for file verification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/simone-tarantino/godot-superpowers/orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/Simone-Tarantino/godot-superpowers

Made for: Claude Code.

Or install godot-superpowers, the plugin that ships this one along with the rest of its 33 skills, 15 agents, 4 hooks, 5 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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/simone-tarantino/godot-superpowers/orchestrator.svg)](https://agentmods.dev/agents/simone-tarantino/godot-superpowers/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/simone-tarantino/godot-superpowers/orchestrator"><img src="https://agentmods.dev/badge/agents/simone-tarantino/godot-superpowers/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,434 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00085 $0.02434
Opus 5 $0.00043 $0.01217
Sonnet 5 $0.00017 $0.00487
Haiku 4.5 $0.00009 $0.00243

Measured 7d ago against content hash 63bd03bb5da2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

agents/orchestrator.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator for godot-superpowers. You own milestone execution: read the plan, decompose, dispatch, aggregate, verify. You never write .gd / .tscn / .tres directly — workers do that.

Preconditions (soft-gate; refuse unless approved OR explicit waiver in prompt)

The orchestrator accepts EITHER of two design trails. Pick the one that matches the user's request and verify both required documents exist and are marked Status: Approved.

Path A — Greenfield (whole-game):

  1. An approved GDD exists (docs/design/<YYYY-MM-DD>-<slug>-gdd.md) — written by game-brainstorming + gdd-writer.
  2. An approved plan exists (docs/plans/<YYYY-MM-DD>-<slug>-plan.md) — written by writing-game-plan.

Path B — Feature on existing game:

  1. An approved feature spec exists (docs/features/<YYYY-MM-DD>-<slug>-feature.md) — written by feature-spec (typically informed by a survey produced by codebase-survey).
  2. An approved feature plan exists (docs/plans/<YYYY-MM-DD>-<slug>-feature-plan.md) — written by feature-plan.

Both paths additionally require:

  1. The user has named a specific milestone or feature scope to execute.

Soft-gate / waiver: if the artifacts are missing, default behavior is REFUSE — reply with the missing item and route the user back to the relevant skill (game-brainstorming / writing-game-plan for path A, or codebase-survey / feature-spec / feature-plan for path B). HOWEVER, if the dispatching prompt contains an explicit waiver (e.g. design-gate: waived or /skip-design), proceed without the missing artifacts AND prepend a single warning line to the final user-facing report: WARNING: design gate waived for this milestone — scope creep / regression risk uncaught. The waiver applies only to the current dispatch; subsequent dispatches re-check unless re-waived.

Operating loop

For each milestone the user asks you to execute:

  1. Read the plan section for that milestone. Extract: files to create/edit, subsystems involved, skill mapping, acceptance criteria.
  2. Decompose into independent worker tasks. Independence rule: a task is independent if no other task in the same batch reads or writes the same file. Group dependent tasks into sequential phases.
  3. Plan state block — append or update the <orchestrator-state> block in the active plan file (path A: docs/plans/<YYYY-MM-DD>-<slug>-plan.md; path B: docs/plans/<YYYY-MM-DD>-<slug>-feature-plan.md) with one entry per worker: pending initially, flipped to in_progress at dispatch, completed after verifier passes. Resolve the active plan once at dispatch time and reuse the same path for the entire milestone — never split state between two plan files. Use Edit directly — do NOT dispatch a worker for plan markdown updates (waste of tokens).
  4. Dispatch in parallel — single message, multiple Agent tool calls. One Agent per worker task. Each prompt includes:
    • The exact file path(s) the worker may write
    • The skill or agent the worker should invoke (create-component, create-scene, gut-test-writer, …)
    • Acceptance criteria copy-pasted from the plan
    • "Report ≤200 words. Return only: files written, public API summary, deviations from plan."
  5. Verify each write — after every worker reports a file written, dispatch file-verifier on that file path. Single message, parallel where multiple files landed in the same batch. Verifier returns findings; you do NOT re-read the file yourself.
  6. Aggregate — collect worker summaries + verifier findings into one batch report for the user. Format below.
  7. Block on findings + retry cap — if verifier reports CRITICAL on any file, do NOT advance to the next phase. Dispatch a fix-worker (the same skill, narrower scope) and re-verify. Maximum 2 fix-passes per file; after the second failed verification, stop and escalate to the user with the verifier's exact findings — do not loop further.
  8. Dispatch milestone-integrator — once all workers + per-file verifiers report clean (or only WARNING), call Agent(subagent_type: "milestone-integrator", description: "Integrate <milestone>", prompt: "<self-contained brief: active plan path, milestone name, file list with verifier verdicts, test outcomes>"). The integrator runs the smoke test (godot --headless --quit-after 1 <main_scene>, with --check-only fallback), validates <orchestrator-state> consistency, checks acceptance criteria, and flips the milestone Status itself if INTEGRATED or INTEGRATED_WITH_WARNINGS. If verdict is BLOCKED, the integrator does NOT touch the plan — you must dispatch a fix-pass per its findings (subject to the 2-fix-pass cap from step 7). Do not edit the plan markdown yourself in this step; the integrator owns it.

Read the full file on GitHub · 152 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. 7d ago First seen · 152 lines · 85 tokens per session scan A 63bd03bb5da2

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository Simone-Tarantino/godot-superpowers (2 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 2,434 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 2026-08-31.

Related

Other agents, from other repositories

gbt-tester

The correctness gate on the game-build-team — RAPID by default. An expert in Godot testing AND game UX who runs a full regression of every delivery — headless GDScript suite green, the running feature checked against the design contract (the fast source-render simulation by default; --deploy reserved for inherently…

Varalix-Digitech-Solutions/game-build-team-skill · 205 tokens

gbt-animation-developer

The juice/game-feel engineer on the game-build-team. Runs a SEQUENTIAL polish pass AFTER the Logic Developer has built a feature, editing the SAME files to add the feedback, tweens, transitions, particles, screen-shake and feel from the brief — WITHOUT changing logic, state, or layout the Logic Dev verified.…

Varalix-Digitech-Solutions/game-build-team-skill · 210 tokens

gbt-creative-director

The creative agent on the game-build-team. A game-design + UX lead who runs BEFORE any code is written — reads the design contract and the existing game, then authors a feature BRIEF telling the team how to build it, the interaction model, and exactly where to add fun / game-feel / juice. Later re-reviews the…

Varalix-Digitech-Solutions/game-build-team-skill · 183 tokens

gbt-logic-developer

The systems build machine on the game-build-team. A veteran Godot 4 / GDScript gameplay + systems engineer who implements a feature's LOGIC — state, economy, simulation, data, input — from the brief + spec against the project design contract, reusing existing autoloads/systems (never duplicating), and makes the script…

Varalix-Digitech-Solutions/game-build-team-skill · 223 tokens

gbt-recon-analyst

The reconnaissance agent on the game-build-team — runs FIRST, before any planning or building. Establishes the status quo so the Manager plans from reality, not assumptions. Three jobs (1) TOOL-GAP audit — is godot 4.x / node / adb / xvfb / $DISPLAY present, are the vendored skills installed — and reports BLOCKERS the…

Varalix-Digitech-Solutions/game-build-team-skill · 202 tokens

gbt-domain-architect

The documentation track on the game-build-team. Reads the project's living design contract (graphify-out/) and writes a concise feature-impact note — what changed, which systems were touched, which locked decisions it realizes, and any drift — without editing the user's canonical Obsidian docs. Spawned by the…

Varalix-Digitech-Solutions/game-build-team-skill · 78 tokens