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.
npx skills add HermeticOrmus/claude-code-game-development --skill godot-developmentgit clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-developmentWrote 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/skills/hermeticormus/claude-code-game-development/godot-development)<a href="https://agentmods.dev/skills/hermeticormus/claude-code-game-development/godot-development"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/godot-development/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/skills/hermeticormus/claude-code-game-development/godot-development"><img src="https://agentmods.dev/badge/skills/hermeticormus/claude-code-game-development/godot-development.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 | $0.00077 | $0.03612 |
| Opus 5.5 | $0.00031 | $0.01445 |
| Sonnet 5.5 | $0.00015 | $0.00722 |
| Haiku 4.5 | $0.00008 | $0.00361 |
Grade A, and why
godot-development 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- godot-development — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Godot development pattern library
Reference patterns for Godot 4 development. Use as lookup when designing or reviewing Godot code.
Signal vs. direct call decision
| Case | Choose |
|---|---|
| Emitter doesn't know listeners (achievement system, sound manager) | Signal |
| Emitter knows exactly one listener and the relationship is tight | Direct call |
| Multiple listeners with shared interest | Signal |
| Receiver needs to return a value to caller | Direct call |
| Order of execution matters | Direct call (signals are deferred by default) |
| Crossing scene boundaries | Signal (or autoload) |
Convention: signal names are past-tense verbs (died, damaged, level_completed).
Resource sharing
The trap: @export var config: ConfigResource gives every instance the SAME resource. Modifying it affects all instances.
Safe patterns:
# Pattern A: Always duplicate
@onready var my_config: ConfigResource = config.duplicate()
# Pattern B: Make Unique in Inspector
# Right-click resource → Make Unique. Per-scene instance.
# Pattern C: Treat as immutable
# Document + discipline. Never write to config from runtime code.
Input handling matrix
| Source | Use for |
|---|---|
Input.is_action_pressed("name") in _process |
Continuous input (movement) — but adds 1 frame latency |
Input.is_action_just_pressed("name") in _process |
One-shot input — same latency caveat |
_unhandled_input(event) with event.is_action_pressed("name") |
One-shot input with no latency |
_input(event) with event.is_action_pressed("name") |
Input that should ignore GUI focus |
_gui_input(event) |
UI input only (on Control nodes) |
Physics body decision
| Body | Use when |
|---|---|
CharacterBody2D / CharacterBody3D |
Player or NPC under direct control |
RigidBody2D / RigidBody3D |
Object responds to physics forces |
RigidBody* with freeze_mode = KINEMATIC |
Want physics events but control velocity directly |
StaticBody* |
Immovable collider (wall, floor) |
AnimatableBody* |
Moving platform — animates but pushes RigidBody correctly |
Area2D / Area3D |
Trigger volume, no collision response |
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 · 409 lines · 77 tokens per session scan A abebbe75ec3b
godot-development is a skill published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 77 tokens to every session and 3,612 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 skills, from other repositories
cgs-bug-report
Use for bug report tasks that capture a reproducible bug with environment, steps, expected/actual behavior, severity, evidence, and owner; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-bug-triage
Use for bug triage tasks that classify bugs by severity, priority, reproduction confidence, owner role, risk, and release impact; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-bugfix
Use for bugfix tasks that fix a bounded bug with reproduction evidence, minimal change, regression coverage, and handoff notes; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-dev-story
Use for dev story tasks that turn a design or bug into an implementation-ready story with owner, files, acceptance tests, and dependencies; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-playtest-report
Use for playtest report tasks that capture player observations, comprehension, friction, loop completion, bugs, quotes, and design implications; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-regression-suite
Use for regression suite tasks that define or run regression coverage for changed systems, prior bugs, critical paths, and release blockers; produce verification evidence, changed or proposed files, and handoff boundaries.