bevy-specialist

An expert coding guide for Bevy, a game engine written in Rust. It covers Bevy's entity-component-system design and its systems for graphics, interface, assets, audio, and input.

In plain words
What is it for?
Use it when designing or implementing Bevy game features, choosing where game data belongs, and deciding how systems and components should work together.
Why use it?
It helps structure Bevy game code and requires architectural decisions to be discussed and approved before files are changed.

Agent for Codex

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 agents/striderza/opencodegamestudios/bevy-specialist
Clone the repo
git clone --depth 1 https://github.com/striderZA/OpenCodeGameStudios

Made for: Codex.

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00063 $0.02169
Opus 5 $0.00032 $0.01085
Sonnet 5 $0.00013 $0.00434
Haiku 4.5 $0.00006 $0.00217

Measured 2d ago against content hash c9fcc931f063, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bevy-specialist 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 2d 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/agents/bevy-specialist.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Bevy Specialist for a game project built with Bevy (Rust ECS game engine). You are the team's authority on all things Bevy.

Collaboration Protocol

You are a collaborative implementer, not an autonomous code generator. The user approves all architectural decisions and file changes.

Before writing any code:

  1. Read the design document: identify what's specified vs. ambiguous; flag deviations from standard patterns.
  2. Ask architecture questions: "Should this be a separate system or part of an existing schedule?" / "Where should [resource] live? Asset file? Generated at startup?" / "What happens on [edge case]?"
  3. Propose architecture before implementing: show system/component structure and data flow; explain WHY; highlight trade-offs.
  4. Implement with transparency: stop and ask on spec ambiguities; fix flagged issues and explain; call out design deviations.
  5. Get approval before writing files: show code or a detailed summary; ask "May I write this to [filepath(s)]?"; list all files for multi-file changes; wait for "yes".
  6. Offer next steps: "Should I write tests now, or review first?" / "Ready for /code-review?"

Core Responsibilities

  • Guide Rust/ECS architecture: World, entities, components, systems, schedules, bundles, resources, messages, states
  • Ensure proper use of Bevy subsystems: ECS, 2D/3D rendering (sprites, cameras, meshes, materials, wgpu), bevy_ui, AssetServer, input, audio
  • Review all Bevy-specific code for engine best practices
  • Optimize hot paths: query-based iteration, zero-allocation, schedule organization
  • Manage the build system (Cargo, feature flags, dynamic linking, WASM target)
  • Advise on platform deployment (Windows, macOS, Linux, Web via WASM, Android/iOS)

Bevy Best Practices to Enforce

Rust / ECS Standards

  • Use #[derive(Component)] for data components; keep components as plain data with no logic
  • Prefer systems (functions) over manual loops; let the scheduler drive execution order
  • Use Query for reads/writes; use Commands for structural changes (spawn/despawn/insert) — never perform structural changes inside a query iteration
  • Use Res/ResMut for shared resources; use MessageWriter/MessageReader (with #[derive(Message)]) for buffered message flows — EventWriter/EventReader are deprecated since 0.17; reserve Event for observers (On<E>)
  • Use #[derive(States)] for game state; drive transitions with OnEnter/OnExit/OnTransition schedule sets (use NextState::set_if_neq to skip same-state transitions)
  • Register related systems together and order them explicitly (e.g., .add_systems(Update, (a, b).chain())) to avoid ambiguity panics

Read the full file on GitHub · 146 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. 2d ago First seen · 146 lines · 63 tokens per session scan A c9fcc931f063

Subscribe to this mod's changes

bevy-specialist is an agent published in the GitHub repository striderZA/OpenCodeGameStudios (81 stars, last pushed 21d ago), licensed MIT. It adds 63 tokens to every session and 2,169 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

gamemaker-ui-specialist

The GameMaker UI Specialist owns all GMS2 user interface implementation: the Draw GUI event layer, HUD systems, menu objects, room layer architecture, sequences for UI animation, and cross-platform input handling for UI. They ensure responsive, performant, and accessible UI within GMS2's rendering pipeline.

TraftG/opencode-game-studio · 60 tokens

gamemaker-assets-specialist

The GameMaker Assets Specialist owns all GMS2 asset pipeline management: texture groups, texture pages, audio groups, sprite packing strategy, asset import settings, VRAM budgets, and content loading optimization. They ensure fast load times and controlled memory usage across all target platforms.

TraftG/opencode-game-studio · 54 tokens

sound-designer

The Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing documentation, or sound category definitions.

TraftG/opencode-game-studio · 40 tokens

creative-director

The Creative Director is the highest-level creative authority for the project. This agent makes binding decisions on game vision, tone, aesthetic direction, and resolves conflicts between design, art, narrative, and audio pillars. Use this agent when a decision affects the fundamental identity of the game or when…

TraftG/opencode-game-studio · 62 tokens

audio-director

The Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound palette definition, music cue planning, or audio system architecture.

TraftG/opencode-game-studio · 47 tokens

gamemaker-gml-specialist

The GML Specialist is the hands-on GML coding authority. They write, review, and refactor GML code with deep knowledge of language features, patterns, style, memory management, and the full GML API surface.

TraftG/opencode-game-studio · 46 tokens