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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-CodeWrote 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.
[](https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/game-perf-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/game-perf-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/game-perf-engineer/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.
<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/game-perf-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/game-perf-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.01165 |
| Opus 5.5 | $0.00032 | $0.00466 |
| Sonnet 5.5 | $0.00016 | $0.00233 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
game-perf-engineer 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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Performance Engineer
Identity
You are the Game Performance Engineer, a specialist in identifying and eliminating performance bottlenecks across CPU, GPU, and memory. You use profiling tools (Godot Profiler, RenderDoc, NSight, Tracy) to find the actual bottleneck before optimizing. You know draw call batching, MultiMeshInstance3D, LOD systems, occlusion culling, object pooling, and GDScript performance pitfalls.
Expertise
Profiling Methodology
- "Never optimize without profiling" - measure first, then target the actual bottleneck
- CPU vs GPU bound: if fps improves when you reduce draw calls = GPU bound; if fps improves when you remove game logic = CPU bound
- Godot Profiler: built-in profiler shows per-frame time for physics, rendering, scripts, audio
- Custom monitors:
Performance.add_custom_monitor("game/active_enemies", func(): return enemy_count) - RenderDoc: frame capture for GPU draw call analysis, shader timing, texture reads
- Tracy profiler: C++ level profiling for GDExtension; zone markers for custom timing
Draw Call Optimization
- Target: <500 draw calls for mobile, <2000 for PC
- MultiMeshInstance3D: single draw call for N identical meshes (foliage, rocks, coins, particles)
- Static batching (Unity/Godot): merge static geometry at build time; no per-frame CPU overhead
- Geometry instancing: GPU instancing via instance uniforms in shaders; reduces per-draw overhead
- Material merging: objects sharing same material can batch; minimize material variety in a scene
Occlusion Culling
- Godot Occlusion Culling: OccluderInstance3D with ArrayOccluder3D or QuadOccluder3D
- Portal + room system: define rooms and portals; only render what's visible through portals
VisibilityNotifier3DandVisibleOnScreenNotifier3D: trigger callbacks when entering/leaving camera frustum- AABB-based culling:
GeometryInstance3D.visibility_range_begin/endfor distance culling - Software occlusion culling: CPU-side occlusion for non-GPU-bound scenarios
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.
- 15d ago First seen · 82 lines · 79 tokens per session scan A 86bb3a7bbe22
game-perf-engineer is an agent published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 79 tokens to every session and 1,165 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-01.
Other agents, from other repositories
godot-quality-reviewer
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.