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 agentmods add skills/m1em1e/vibecoding-tools-4codex-cn/godot-code-generatenpx skills add m1em1e/vibecoding-tools-4codex-cn --skill godot-code-generategit clone --depth 1 https://github.com/m1em1e/vibecoding-tools-4codex-cnWrote 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/m1em1e/vibecoding-tools-4codex-cn/godot-code-generate)<a href="https://agentmods.dev/skills/m1em1e/vibecoding-tools-4codex-cn/godot-code-generate"><img src="https://agentmods.dev/badge/skills/m1em1e/vibecoding-tools-4codex-cn/godot-code-generate.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.03087 |
| Opus 5 | $0.00031 | $0.01543 |
| Sonnet 5 | $0.00012 | $0.00617 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
gdscript-codegen 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 4d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GDScript 代码生成 Skill
用途:AI 生成高质量 GDScript 代码的规范和模板
版本:v1.0 · 2026-04-22
适用引擎:Godot 4.5/4.6
一、GDScript 4.x 核心规范
1.1 类型系统
Godot 4.x 使用强类型 GDScript,AI 生成代码时必须遵循:
# ✅ 推荐:显式类型标注
var health: int = 100
var speed: float = 10.0
var player_name: String = "Player"
var position: Vector3 = Vector3.ZERO
var enemies: Array[Node3D] = []
var weapon_data: Dictionary = {}
# ✅ 推荐:函数参数和返回值标注
func take_damage(amount: int) -> void:
health -= amount
func get_health_ratio() -> float:
return float(health) / float(max_health)
# ❌ 避免:无类型标注(编译器警告)
var health = 100 # 类型推断,但不推荐
1.2 类型推断陷阱
# ❌ 错误:for 循环迭代变量无法推断
for x in [-1.0, 1.0]:
var pos := center + Vector2(x, 0) * radius # 报错!
# ✅ 正确:显式标注迭代变量
for x: float in [-1.0, 1.0]:
var pos := center + Vector2(x, 0) * radius
# ❌ 错误:字典值类型无法推断
var data = {"a": 1, "b": 2}
var value := data["a"] # 报错!
# ✅ 正确:显式标注或使用 as
var value: int = data["a"]
var value := data["a"] as int
1.3 信号声明
# Godot 4.x 信号语法
signal health_changed(current: int, maximum: int)
signal died
signal damage_taken(amount: int, remaining: int)
signal weapon_changed(weapon_index: int)
1.4 导出变量
# 基础类型
@export var health: int = 100
@export var speed: float = 10.0
# 范围限制
@export_range(0, 100, 1) var health: int = 100
@export_range(0.0, 10.0, 0.1) var speed: float = 5.0
# 枚举
@export_enum("Easy", "Normal", "Hard") var difficulty: int = 1
# 资源
@export var weapon_resource: WeaponResource
@export var projectile_scene: PackedScene
# 分组
@export_group("Combat")
@export var damage: int = 10
@export var fire_rate: float = 0.5
1.5 @onready 和节点引用
# ✅ 推荐:@onready 延迟初始化
@onready var animation_player: AnimationPlayer = $AnimationPlayer
@onready var health_bar: ProgressBar = $UI/HealthBar
# ✅ 推荐:运行时获取(更灵活)
var player: Node3D
func _ready() -> void:
player = get_tree().get_first_node_in_group("player")
# ❌ 避免:硬编码路径(易断裂)
var health_label = $"../UI/GameHUD/HealthPanel/HealthLabel"
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.
- 4d ago First seen · 365 lines · 62 tokens per session scan A 7d23962653da
gdscript-codegen is a skill published in the GitHub repository m1em1e/vibecoding-tools-4codex-cn (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 3,087 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.