Third-Person-MC: Skill for Claude Code

.agent/skills/vtj-camera-system/SKILL.md

vtj-camera-system is a skill for Claude Code, Codex from hexianWeb/Third-Person-MC. It costs 33 tokens per session (2,402 once invoked), scanned A, original, MIT.

A guide for building third-person cameras in a Vite and Three.js game, including camera modes, smooth player following, and obstacle avoidance.

In plain words
What is it for?
Use it when changing follow distance or smoothness, adding camera modes, or detecting caves and obstacles around the player.
Why use it?
It gives the camera behavior a clear structure, helping prevent the view from passing through walls or other terrain.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is hexianWeb/Third-Person-MC's own configuration. It tells Claude Code and Codex how to work on Third-Person-MC itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Third-Person-MC configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hexianWeb/Third-Person-MC. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hexianWeb/Third-Person-MC/main/.agent/skills/vtj-camera-system/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hexianWeb/Third-Person-MC

Made for: Claude Code, Codex.

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 vtj-camera-system

README.md
[![agentmods](https://agentmods.dev/badge/skills/hexianweb/third-person-mc/vtj-camera-system/github.svg)](https://agentmods.dev/skills/hexianweb/third-person-mc/vtj-camera-system)
Your own site
<a href="https://agentmods.dev/skills/hexianweb/third-person-mc/vtj-camera-system"><img src="https://agentmods.dev/badge/skills/hexianweb/third-person-mc/vtj-camera-system/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 vtj-camera-system

Your own site · 80×15
<a href="https://agentmods.dev/skills/hexianweb/third-person-mc/vtj-camera-system"><img src="https://agentmods.dev/badge/skills/hexianweb/third-person-mc/vtj-camera-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,402 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.02402
Opus 5.5 $0.00013 $0.00961
Sonnet 5.5 $0.00007 $0.00480
Haiku 4.5 $0.00003 $0.00240

Measured 2mo ago against content hash da52fc968ca5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vtj-camera-system 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 2mo 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.

.agent/skills/vtj-camera-system/SKILL.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vite-threejs Camera System

Overview

本项目采用 第三人称相机系统,核心组件:

  • Camera:主相机类,管理模式切换
  • CameraRig:第三人称跟随逻辑,处理平滑跟随、避障、bobbing 效果

核心原则:相机通过锚点跟随玩家,使用 lerp 平滑过渡,通过方块检测避免穿模。

When to Use

  • 修改相机跟随行为
  • 调整相机偏移和平滑度
  • 实现新的相机模式
  • 处理相机与地形的碰撞

相机架构

┌─────────────────────────────────────────────────────────────┐
│                         Camera                               │
│  - mode: 'third-person' | 'bird-perspective'                │
│  - perspectiveCamera: THREE.PerspectiveCamera                │
│  - orbitControls: OrbitControls (鸟瞰模式用)                 │
│  - rig: CameraRig (第三人称用)                               │
└─────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────┐
│                       CameraRig                              │
│  - group: THREE.Group (跟随玩家位置)                         │
│  - cameraAnchor: THREE.Object3D (相机位置锚点)               │
│  - targetAnchor: THREE.Object3D (看向目标锚点)               │
│  - _smoothedPosition: 平滑后的位置                           │
│  - _smoothedLookAtTarget: 平滑后的看向点                     │
└─────────────────────────────────────────────────────────────┘

CameraRig 工作原理

锚点系统

// 锚点附着在 group 上,group 跟随玩家
this.group = new THREE.Group()
this.cameraAnchor = new THREE.Object3D()   // 相机实际位置
this.targetAnchor = new THREE.Object3D()   // 相机看向的点

// 锚点相对于玩家的偏移
this.cameraAnchor.position.copy(this.config.follow.offset)       // (2, 1.5, 3)
this.targetAnchor.position.copy(this.config.follow.targetOffset) // (0, 1.5, -5.5)

this.group.add(this.cameraAnchor)
this.group.add(this.targetAnchor)

平滑跟随

update() {
  const playerPos = this.target.position
  const facingAngle = this.target.facingAngle
  
  // 平滑位置插值
  this._smoothedPosition.lerp(playerPos, this.config.follow.smoothSpeed)
  this.group.position.copy(this._smoothedPosition)
  
  // 同步角色朝向
  this.group.rotation.y = facingAngle
  
  // 获取世界坐标
  const cameraPos = this.cameraAnchor.getWorldPosition(new THREE.Vector3())
  const targetPos = this.targetAnchor.getWorldPosition(new THREE.Vector3())
  
  // 平滑看向点
  this._smoothedLookAtTarget.lerp(targetPos, this.config.follow.lookAtSmoothSpeed)
  
  return { cameraPos, targetPos: this._smoothedLookAtTarget, fov: this._currentFov }
}

Read the full file on GitHub · 314 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. 2mo ago First seen · 314 lines · 33 tokens per session scan A da52fc968ca5

Subscribe to this mod's changes

vtj-camera-system is a skill published in the GitHub repository hexianWeb/Third-Person-MC (197 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,402 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 2026-08-30.

Related

Other skills, from other repositories

super-claudio-brothers

Generate a unique themed Super Claudio Brothers platformer. Creates a custom level, colour palette, enemy look, and Claudio costume. Every run produces a different game.

alexconner-79/super-claudio-brothers · 40 tokens

events-system

Use this skill when working with the Phaser 4 event system. Covers EventEmitter, scene events, game events, custom events, and event-driven communication. Triggers on: events, on, emit, EventEmitter, scene events, listeners.

phaserjs/phaser · 52 tokens

game-object-components

Use this skill when working with Phaser 4 game object components and the mixin system. Covers Transform, Alpha, Tint, Origin, Depth, Flip, Mask, GetBounds, Lighting, and other shared component behaviors. Triggers on: component, mixin, transform, mask, bounds, lighting.

phaserjs/phaser · 65 tokens

geometry-and-math

Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.

phaserjs/phaser · 64 tokens

particles

Use this skill when creating particle effects in Phaser 4. Covers ParticleEmitter, emission zones, death zones, particle properties, textures, gravity wells, and particle movement. Triggers on: particles, emitter, particle effect, explosion, fire, smoke.

phaserjs/phaser · 53 tokens

physics-arcade

Use this skill when using Arcade Physics in Phaser 4. Covers enabling physics, velocity, acceleration, gravity, collisions, overlap, world bounds, physics groups, static bodies, and collision categories. Triggers on: physics, arcade, velocity, gravity, collide, overlap, bounce, physics body.

phaserjs/phaser · 65 tokens