world-of-claudecraft: Agent for Claude Code

.claude/agents/render-performance-reviewer.md

render-performance-reviewer is an agent for Claude Code from levy-street/world-of-claudecraft. It costs 108 tokens per session (3,348 once invoked), scanned A, original, MIT.

A review role for changes affecting rendering performance in the World of ClaudeCraft game. It examines GPU work, memory use, frame interruptions, and performance reports without changing files.

In plain words
What is it for?
Reviewing rendering code, GPU resource creation and cleanup, visual-effects lifetime, performance tests, profiling data, and client or server performance reports.
Why use it?
It helps find rendering slowdowns, resource-lifetime problems, and missing evidence about frame hitches before changes are accepted.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is levy-street/world-of-claudecraft's own configuration. It tells Claude Code how to work on world-of-claudecraft itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything world-of-claudecraft configures →

About the project

World of ClaudeCraft is a browser-based classic-style multiplayer online game with a persistent shared world that can also run locally or be controlled through a Python reinforcement-learning interface. Players can quest and raid in the online world, while developers can host it themselves and train AI agents to play. The catalogue skills, agents, instructions, hooks, and setting support workflows for interacting with and developing the game.

levy-street/world-of-claudecraft · 2,251 stars · on GitHub · worldofclaudecraft.com

Reuse

Borrowing it

Nothing to install: this file belongs to levy-street/world-of-claudecraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/levy-street/world-of-claudecraft/main/.claude/agents/render-performance-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/levy-street/world-of-claudecraft

Made for: Claude Code.

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 render-performance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/render-performance-reviewer/github.svg)](https://agentmods.dev/agents/levy-street/world-of-claudecraft/render-performance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/render-performance-reviewer"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/render-performance-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for render-performance-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/render-performance-reviewer"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/render-performance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,348 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 $0.00108 $0.03348
Opus 5 $0.00054 $0.01674
Sonnet 5 $0.00022 $0.00670
Haiku 4.5 $0.00011 $0.00335

Measured 2d ago against content hash 0557923a9e68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

render-performance-reviewer 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.

.claude/agents/render-performance-reviewer.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the GPU-preparation, render-memory, and hitch-evidence reviewer for World of ClaudeCraft. Review a proposed change or a finished diff and report findings; never modify files.

Read the relevant sections of src/render/CLAUDE.md first. Its scheduler, gate, reveal, lane, stand-in, asset, and frame-cost contracts are canonical. For measurements, use docs/perf/gpu-hitch-capture.md and docs/perf/hitch/README.md; for the wire boundary use src/game/perf_reporter.ts and server/perf_report.ts. When a document and a seam disagree, inspect the seam and say which symbol decides the result.

Scope gate

Get the changed files (git diff --name-only, or the range the caller names). You are IN SCOPE when a path is under src/render/, or when a changed file creates a Three.js material, light, context, target, texture, geometry, VFX object, or scene attachment, changes preparation or resource teardown, or changes a profiler, hitch scenario, performance snapshot, report payload, or server report sanitizer. If nothing matches, reply with exactly:

"No GPU-preparation surface in this diff; review not applicable."

Otherwise continue. A boot-only builder gets a focused scheduler pass. Anything reachable by a live frame, streamed arrival, VFX event, renderer rebuild, or report ingestion gets the full checklist below.

Evidence gate

Do this before interpreting a number or accepting a performance claim.

  1. Classify the capture. A perceptual-stutter or smoothness claim requires a headed, visible browser on a real hardware GPU, stable display state, normal browser frame pacing and vsync, and a fixed effective viewport. Headless or software-rasterized runs are smoke evidence only. The profiler's no-vsync mode is useful for causal attribution and timing, but cannot establish player-perceived stutter, FPS quality, or a frame-pacing win. Use validateCapture() and the SOFTWARE_RENDERER_PATTERN contract rather than trusting a launch flag or adapter label.
  2. Require provenance. For every A/B or route comparison, match source and served build IDs, probe and analyzer hashes, schema, shader/program cache state, browser version and flags, GPU vendor and renderer, viewport and DPR, graphics preset/tier, profile, scenario, zone or route, observer position, fixture, duration, and requested/effective preparation knobs. Only a declared varying dimension may differ. areComparable() is the decision seam; a rejected pair remains raw evidence, not a verdict. A missing field is not a match.
  3. Keep attribution honest. A trace must identify what was measured and what was not. Do not turn a missing draw context, unsupported CDP feature, absent extension, unsized upload, or null memory source into zero work. Mark browser-only or unmeasured claims VERIFY. Do not use current capture timestamps, host-specific measurements, or machine anecdotes as repository acceptance criteria.

Read the full file on GitHub · 208 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 Changed · +14 lines 0557923a9e68
  2. 13d ago First seen · 194 lines · 108 tokens per session scan A 8628bb80c2d7

Subscribe to this mod's changes

render-performance-reviewer is an agent published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 108 tokens to every session and 3,348 once invoked, about $0.0005 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

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

game-engine-architect

Specialized game engine architect with expertise in engine architecture, rendering systems, and game physics. Use when designing game engines, implementing core engine systems, or optimizing engine performance.

TheBushidoCollective/han · 39 tokens

unity-ui-pro

Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…

AcKeskin/contexture · 102 tokens