By lebobo88
RLM-Gaming — the Arcade crown. A senior multi-agent game studio (vision, design, production, runtime-AI/netcode direction, art/audio direction, QA/balance, live-ops, ratings/cert, fair-play security). Orchestrates + delegates: code -> engineering (pair-programmer), assets -> garland (RLM-Creative).
The Sculptor-led 3D asset flow — DCC contract → commission garland blender-model/blender-rig (existing blender-mcp) → mesh-topology-budget + rig-quality gates → C2PA provenance → DECISION_RECORD.
The Warden + The Playtester run a synthetic playtest, balance Monte-Carlo, and telemetry tuning, then route tuning recommendations to the design heads with an accessibility-floor check.
The Arbiter-led ratings + platform cert gate — content inventory, IARC map, target-rating feasibility, per-platform TRC checklist, loot-box jurisdiction, then a submission HITL.
A single feature end-to-end — The Producer scopes, the right design head specs, engineering implements via the matching pp game-* team, then QA/perf/accessibility gates and a DECISION_RECORD.
The Director-led greenlight — vision to testable pillars to one-pager to GDD, gated on game-design-pillars-testable plus a HITL greenlight.
Game Director and crown lead (CREW LEAD / gatekeeper) of the Arcade crown. Receives C_SUITE_DECISION_PACKET (greenlight) or a raw game brief from Hydra, recalls prior-project wisdom from eights.memory, sets the vision and testable pillars, decomposes the work to peer heads, routes code to engineering and assets to garland, and gates the final DECISION_RECORD before ship. Holds the greenlight / content-lock / ship HITL gates.
Production lead (gatekeeper) of the Arcade crown. Owns the task graph: turns The Director's decomposition into a backlog, milestones, and sprints; computes the dependency graph and critical path; schedules fan-out to peer heads; tracks engineering (PRD/DEV_TASK) and garland (CREATIVE_BRIEF/ASSET_JOB) delegated work to completion; and gates the HITL control points (greenlight / content-lock / ship). Co-runs /game-vertical-slice with The Director.
Technical Director (gatekeeper) of the Arcade crown. Owns engine architecture, codebase layout, tech standards, build-vs-buy calls, and the per-platform PERF BUDGETS (the game-perf-budget gate). Picks the engine and pair-programmer profile (game-dev-unity / unreal / godot / web / custom), then DELEGATES all implementation to the engineering squad via PRD/DEV_TASK. Never writes engine code itself. Holds the game-perf-budget gate.
Systems Designer (execute) of the Arcade crown. Designs mechanics — each defined by verb / inputs / outputs / feedback / FAILURE STATES / counter-play / teaching / scaling — plus systemic interactions, combat math, emergence, and exploit-resistance. Produces mechanic_spec artifacts that engineering implements. Never writes engine code. Every mechanic must name its failure state.
Narrative Director (advisory) of the Arcade crown. Authors world bibles, branching narrative as quest graphs / state machines, dialogue trees, character arcs, and themes — with localization-aware dialogue budgets. Coordinates with The Cartographer on spatial-narrative alignment and with The Arbiter on content / cultural review. Never writes engine code or VO binaries; delegates dialogue authoring tooling to engineering and VO to garland.
3D modeling and DCC (Blender) pipeline standards for the Arcade crown (The Sculptor). Produces geometry execution standards — topology / edge-flow rules, retopo targets, UV / lightmap layout, PBR channel sets, LOD chains, pivot/scale/axis conventions — and the Blender/DCC commission contract that garland's blender-model / blender-rig sub-agents execute via the existing blender-mcp backend. The crown never models, retopologizes, or drives Blender inline; it writes the DCC contract and emits an ASSET_JOB (model_type:mesh|rig, provenance_required:true) to garland. Ties to the mesh-topology-budget gate and (for gen-AI assets) ai-content-provenance.
Runtime NPC AI DESIGN for the Arcade crown (The Puppeteer). This is the design side of in-game enemy/NPC behavior — pattern selection (FSM/BT/GOAP/Utility/HTN/EQS/ML-Agents), blackboard key design, perception modules, and NavMesh strategy — NOT generative AI and NOT runtime code. Read before authoring any AI tuning targets in an encounter_design_doc or before emitting a DEV_TASK for AI work. The crown specs; pp game-ai-programmer implements.
Art and audio DIRECTION for the Arcade crown (The Artisan + The Conductor). Produces the style bible, reference boards, LOD/poly/texture/material budgets, and the audio mix-tier sheet, sonic palette, and Wwise/FMOD event map — then COMMISSIONS the actual binaries from garland via CREATIVE_BRIEF/ASSET_JOB/SHOT_LIST with provenance_required:true. The crown never generates images, audio, or 3D inline. Ties to the ai-content-provenance rubric (garland C2PA-signs every gen-AI asset).
The Arbiter's age-rating and platform-certification skill for the Arcade crown. Read this before producing any content-disclosure inventory, IARC answer map, target-rating feasibility study, per-platform TRC/cert checklist, regional-edit plan, or cert-submission package. Covers ESRB/PEGI/IARC/CERO/USK/ClassInd ratings, platform cert (PlayStation TRC, Xbox XR/XGSP, Nintendo Lotcheck, Steamworks + Deck-Verified, Apple/Google review), and CVAA accessibility law. Produces disclosure/feasibility/checklists only — code fixes go to engineering (game-cert-team), assets to garland. Escalates IP/law questions to legal-compliance (Senate/curia) via HANDOFF.
Economy-designer skill for producing economy simulations and monetization specs — currencies, source/sink/leak tables, gacha/loot math with pity timers and published odds, Monte-Carlo balancing, progression curves, retention/LTV/ARPDAU KPIs, store A/B plans, and a per-region jurisdiction table. Read this before designing any monetized or live-service economy. Invoked by The Economist and The Arbiter; feeds the loot-box-jurisdiction gate. Complements the engineering-side game-design economy-spreadsheet template in pair-programmer by adding Monte-Carlo balancing, the full jurisdiction matrix, and KPI dashboards.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A senior, multi-agent game studio that runs as a Hydra squad pack. RLM-Gaming owns the studio-brain layers — vision, design, production, live-ops, QA/balance, and compliance — and delegates the build: engine code goes to pair-programmer, art/audio/video goes to RLM-Creative (Garland). It produces design, plans, specs, and gates — never engine source, never media binaries.
The full architecture spec lives in RLM-GAMING.md; the
foundational design rationale is in the Blueprint document.
RLM-Gaming — codename The Arcade Crown — is a pack of 20 specialized AI agents ("heads") organized like a real game studio's senior leadership. Each head is a domain expert (game director, systems designer, netcode lead, economy designer, QA/balance lead, ratings & cert officer, anti-cheat/security gate, …) with its own charter, model tier, tool scope, and — where it owns a quality bar — an acceptance gate.
The crown does the work a studio's brains do: it decides what to build and why, specs how it should behave, plans the production, runs QA and balance, handles ratings/cert/compliance, and gates the ship. It does not write the engine code or generate the art — it hands those out as typed jobs to sibling squads and reviews what comes back.
It ships as a Claude Code plugin (rlm-gaming, see
.claude-plugin/plugin.json) and registers with
Hydra as the rlm-gaming squad, so a single
/hydra:run "make a game…" routes straight into the studio.
If the deliverable is engine source → emit a
PRD/DEV_TASKto engineering. If the deliverable is an image/audio/video/3D binary → emit aCREATIVE_BRIEF/SHOT_LIST/ASSET_JOBto garland. Everything the crown keeps is text: design docs, specs, plans, simulations, and gate verdicts.
This separation is what keeps a 20-agent studio coherent: the crown stays the single source of design truth, while the muscle (code generation, asset rendering) lives in independently-shippable sibling squads with their own provenance and review.
What the Arcade Crown can produce end-to-end, with the owning head, the skill it draws on, and the gate it answers to:
Hydra — Enterprise Agent Mesh supervisor (routes work across executive / engineering / creative / legal / healthcare / sales / research / customer-support squads).
npx claudepluginhub lebobo88/rlm-gaming --plugin rlm-gamingComprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development