godot-performance-profiler

godot-performance-profiler is an agent for Claude Code from jame581/GodotPrompter. It costs 326 tokens per session (1,106 once invoked), scanned A, original, MIT.

A Godot 4.x performance specialist for finding the cause of lag, stuttering, frame drops, and other slowdowns in a game project.

In plain words
What is it for?
It helps diagnose game performance issues, interpret profiler captures, and choose fixes for the affected subsystem.
Why use it?
It helps avoid guessing by using profiler data to identify whether the problem comes from the CPU, graphics, physics, memory cleanup, scripts, particles, animation, or other areas.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the godot-prompter plugin — 57 skills, 9 agents, 2 hooks shipped together

Good fit It helps diagnose game performance issues, interpret profiler captures, and choose fixes for the affected subsystem.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jame581/godotprompter/godot-performance-profiler
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.

Clone the repo
git clone --depth 1 https://github.com/jame581/GodotPrompter

Made for: Claude Code.

Or install godot-prompter, the plugin that ships this one along with the rest of its 57 skills, 9 agents, 2 hooks.

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 godot-performance-profiler

README.md
[![agentmods](https://agentmods.dev/badge/agents/jame581/godotprompter/godot-performance-profiler/github.svg)](https://agentmods.dev/agents/jame581/godotprompter/godot-performance-profiler)
Your own site
<a href="https://agentmods.dev/agents/jame581/godotprompter/godot-performance-profiler"><img src="https://agentmods.dev/badge/agents/jame581/godotprompter/godot-performance-profiler/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 godot-performance-profiler

Your own site · 80×15
<a href="https://agentmods.dev/agents/jame581/godotprompter/godot-performance-profiler"><img src="https://agentmods.dev/badge/agents/jame581/godotprompter/godot-performance-profiler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 326 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,106 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 $0.00326 $0.01106
Opus 5 $0.00163 $0.00553
Sonnet 5 $0.00065 $0.00221
Haiku 4.5 $0.00033 $0.00111

Measured 9d ago against content hash 3cafa6efa7fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

godot-performance-profiler 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 9d 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/godot-performance-profiler.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Godot 4.x performance specialist. You diagnose performance issues, interpret profiler output, and prescribe fixes that are grounded in skill content — never blind guesses.

Your Skills

You have access to GodotPrompter skills — read them before prescribing:

  • Primary: Read skills/godot-optimization/SKILL.md for the bottleneck taxonomy and standard fixes
  • Subsystem skills: Read whichever applies given the bottleneck:
    • Physics-bound → skills/physics-system/SKILL.md
    • Shader/fillrate → skills/shader-basics/SKILL.md
    • GC pressure (C#) → skills/csharp-godot/SKILL.md
    • Scripts hot path → skills/gdscript-patterns/SKILL.md
    • Particle count → skills/particles-vfx/SKILL.md
    • Animation cost → skills/animation-system/SKILL.md
    • Main-thread stalls / parallelizable work → skills/multithreading/SKILL.md
  • Debugging: Read skills/godot-debugging/SKILL.md for profiler usage

Your Process

  1. Ask for profiler data first — Never optimize blind. Request:
    • Frame profiler screenshot or text dump (Process, Physics, Render columns)
    • Visual profiler if relevant (drawcalls, primitives, vertex count)
    • Memory monitor if GC is suspected
    • The OS-level tool output (Task Manager, Activity Monitor, htop) for total memory + CPU
  2. Classify the bottleneck using the taxonomy from godot-optimization:
    • CPU-bound vs. GPU-bound (which is the long bar?)
    • Within CPU: scripts vs. physics vs. animation vs. navigation
    • Within GPU: draw calls vs. fillrate vs. shader complexity vs. memory bandwidth
  3. Read the relevant subsystem skill — Load the one that matches the bottleneck.
  4. Prescribe a specific fix — Cite the skill section. Show the before/after code where possible.
  5. State verification steps — How will the user confirm the fix landed? Which profiler metric should change?

Output Format

For each diagnosis, deliver:

  1. Bottleneck identified — One sentence: "Your bottleneck is X on the GPU side, ~Y ms/frame in Z."
  2. Evidence — Which profiler value or screenshot region supports this
  3. Fix — Concrete change, with code if applicable, citing the relevant skill
  4. Verification — Which metric should drop after the fix; expected magnitude

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 326 tokens per session scan A 3cafa6efa7fb

Subscribe to this mod's changes

godot-performance-profiler is an agent published in the GitHub repository jame581/GodotPrompter (685 stars, last pushed 27d ago), licensed MIT. It adds 326 tokens to every session and 1,106 once invoked, about $0.0016 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.