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/commands/hermeticormus/libregamedev-claude-code/game-perf)<a href="https://agentmods.dev/commands/hermeticormus/libregamedev-claude-code/game-perf"><img src="https://agentmods.dev/badge/commands/hermeticormus/libregamedev-claude-code/game-perf/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/commands/hermeticormus/libregamedev-claude-code/game-perf"><img src="https://agentmods.dev/badge/commands/hermeticormus/libregamedev-claude-code/game-perf.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 | $0.00017 | $0.00786 |
| Opus 5.5 | $0.00007 | $0.00314 |
| Sonnet 5.5 | $0.00003 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
game-perf 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/game-perf
Game performance profiling, batching, LOD configuration, and object pooling.
Trigger
/game-perf [action] [target]
Actions
profile
Identify performance bottleneck from symptom description.
/game-perf profile "game drops to 45fps with 50 enemies on screen"
/game-perf profile "30fps on mobile with 1000 foliage instances"
/game-perf profile "frame spike every 2 seconds"
Output: Diagnosis checklist (CPU vs GPU bound, draw calls, physics contacts), profiler setup guide, custom monitor code.
batch
Implement draw call reduction strategies.
/game-perf batch "1000 foliage meshes causing 1000 draw calls"
/game-perf batch "200 coins scattered in level all individual"
/game-perf batch "particle effects creating hundreds of draw calls"
Output: MultiMeshInstance3D implementation, instancing shader, or static batching setup.
lod
Configure LOD transitions for 3D objects.
/game-perf lod "character models need LOD at 10, 30, 80 meters"
/game-perf lod "vegetation disappears abruptly instead of fading"
/game-perf lod "impostor LOD for distant buildings"
Output: LOD node configuration, visibility range values, fade mode setup.
pool
Implement object pool for frequently spawned objects.
/game-perf pool "bullet projectiles, 200 active max"
/game-perf pool "enemy spawner, 50 concurrent enemies"
/game-perf pool "audio player pool for SFX"
Output: GenericPool GDScript, acquire/release usage, pool size calculation.
Examples
Diagnosing 45fps with 50 enemies:
/game-perf profile "game runs at 45fps. 50 enemies active. physics on."
Diagnostic steps:
- Open Godot Profiler; check physics % of frame time
- If physics > 50%: reduce physics body count, use Area3D for detection instead of RigidBody
- If render > 50%: check draw calls; enable Profiler > GPU
- If script > 50%: check enemy AI tick rate; reduce to 10Hz for distant enemies
1000 foliage draw calls:
/game-perf batch "1000 grass meshes using 1000 draw calls, 30fps on target GPU"
Produces: FoliageRenderer using MultiMeshInstance3D, terrain-aligned random placement, optional wind shader via instance uniforms.
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 · 93 lines · 17 tokens per session scan A d3d57b4bb581
game-perf is a command published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 17 tokens to every session and 786 once invoked, about $0.0001 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 commands, from other repositories
build-and-compilation
These commands drive the build/compile/test dev loop, plus build configuration: triggering Player builds and reading the resulting BuildReport, switching the active build target, enumerating targets, reading/writing EditorUserBuildSettings, and listing Build Profiles. Several commands are asynchronous: trigger the…
animation
Author animation assets: AnimationClips (and their float curves), AnimatorControllers (parameters, layers, states, transitions), and Timeline assets. Create commands write under the authoring root and follow the shared confirm/dryrun convention.
assets-and-files
Commands for creating, importing, moving, copying, renaming, deleting and finding project assets, plus folder and text-file operations. Every agent-supplied path is funnelled through the authoring-root sandbox (it rejects ../ and out-of-project writes); destructive or overwriting operations require confirm=true and…
gameobjects-and-components
Commands for creating GameObjects, querying the scene hierarchy, mutating the core GameObject/Transform surface, and adding/removing components and editing their serialized properties. Scene mutations are wrapped in Unity's Undo system (so a multi-step action reverts as one collapsible step) and are blocked during…
project-settings
Read and change a representative slice of Unity's project-wide settings (Audio, Graphics, Input, Physics, Player, Quality, Tags & Layers, Time). get commands read a group's current values into a ProjectSettingsResponse; set commands mutate them through the shared confirm/dryrun convention, so confirm=true is required…
baking
Bake and clear precomputed scene data: lightmaps, NavMesh, and occlusion culling. Each bake runs asynchronously (returns immediately) — poll the matching bakestatus until completed. The clear commands are destructive and require confirm=true. The getsettings / setsettings pairs read and tune the bake parameters.