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/phaserjs/phaser/camerasnpx skills add phaserjs/phaser --skill camerasgit clone --depth 1 https://github.com/phaserjs/phaserWhat 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 | $0.00064 | $0.04187 |
| Opus 5 | $0.00032 | $0.02093 |
| Sonnet 5 | $0.00013 | $0.00837 |
| Haiku 4.5 | $0.00006 | $0.00419 |
Grade A, and why
cameras 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 yesterday.
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 — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cameras
Camera system in Phaser 4 -- CameraManager, main camera, viewport vs scroll, zoom, bounds, following sprites, camera effects (fade, flash, shake, pan, zoomTo, rotateTo), ignore lists, filters, and keyboard controls.
Key source paths: src/cameras/2d/CameraManager.js, src/cameras/2d/BaseCamera.js, src/cameras/2d/Camera.js, src/cameras/2d/effects/, src/cameras/controls/
Related skills: ../game-setup-and-config/SKILL.md, ../sprites-and-images/SKILL.md, ../filters-and-postfx/SKILL.md
Quick Start
// In a Scene's create() method:
// Access the default camera (created automatically)
const cam = this.cameras.main;
// Scroll the camera to look at a different part of the world
cam.setScroll(200, 100);
// Center camera on a world coordinate
cam.centerOn(400, 300);
// Zoom in (2x) -- values < 1 zoom out, > 1 zoom in
cam.setZoom(2);
// Follow a sprite with smooth lerp
cam.startFollow(player, false, 0.1, 0.1);
// Constrain the camera to the world bounds
cam.setBounds(0, 0, 2048, 2048);
// Fade in from black over 1 second
cam.fadeIn(1000);
// Add a filter to the camera (v4 feature)
cam.filters.external.addBlur(1, 2);
Core Concepts
CameraManager
Every Scene has a CameraManager accessible via this.cameras. It manages all cameras for that Scene and is registered as a plugin under the key 'CameraManager'.
// The manager is at this.cameras (not this.camera)
this.cameras // CameraManager instance
this.cameras.cameras // Array of Camera objects (render order)
this.cameras.main // Reference to the "main" camera (first one by default)
this.cameras.default // Un-transformed utility camera (not in the cameras array)
Key methods on CameraManager:
| Method | Signature | Description |
|---|---|---|
add |
(x?, y?, width?, height?, makeMain?, name?) |
Create a new Camera. Defaults to full game size at 0,0. Returns Camera. |
addExisting |
(camera, makeMain?) |
Add a pre-built Camera instance. Returns the Camera or null if it already exists. |
remove |
(camera, runDestroy?) |
Remove and optionally destroy a Camera or array of Cameras. If main is removed, resets to cameras[0]. |
getCamera |
(name) |
Find a Camera by its name string. Returns Camera or null. |
getTotal |
(isVisible?) |
Count cameras. Pass true to count only visible ones. |
fromJSON |
(config) |
Create cameras from a config object or array. Used for scene-level camera config. |
resetAll |
() |
Destroy all cameras and create one fresh default camera. |
resize |
(width, height) |
Resize all cameras to given dimensions. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 498 lines · 64 tokens per session scan A 3c07e8d97539
cameras is a skill published in the GitHub repository phaserjs/phaser (40,232 stars, last pushed 11d ago), licensed MIT. It adds 64 tokens to every session and 4,187 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 2026-08-30.
Other skills, from other repositories
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
soundclaw
Control Spotify playback, search music, and return shareable music links.
todo
Maintain a shared workspace TODO list with blocked tasks.
onejs-setup-and-overview
Use this skill whenever the user wants to build or set up user interface in a Unity project using OneJS, React, TypeScript, or JSX, e.g. 'add a main menu to my game', 'build a settings screen', 'make a HUD', 'set up OneJS', 'my OneJS panel is blank', 'the UI is not hot reloading'. Covers confirming OneJS is installed…
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
photo-sphere-viewer
Use when displaying 360-degree panoramic images (equirectangular/cubemap/dual-fisheye) in web applications, building virtual tours with markers and transitions, embedding interactive panoramas in Vue/React/vanilla JS, or creating 360-degree video players with gyroscope VR support. Photo-Sphere-Viewer v5: JavaScript…