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 SummerEngine/summer-engine-agent --skill water-ripplegit clone --depth 1 https://github.com/SummerEngine/summer-engine-agentWrote 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/summerengine/summer-engine-agent/water-ripple)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/water-ripple"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/water-ripple/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/summerengine/summer-engine-agent/water-ripple"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/water-ripple.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.05297 |
| Opus 5 | $0.00037 | $0.02648 |
| Sonnet 5 | $0.00015 | $0.01059 |
| Haiku 4.5 | $0.00007 | $0.00530 |
Grade A, and why
water-ripple 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 7d 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
water-ripple — Impact Ripples on a Water Plane
Concentric expanding rings on a water surface, normal-distorted so the ripple actually refracts the reflection. The shader keeps a small ring buffer of (origin, time, amplitude) tuples and renders all of them simultaneously over a base water plane. GDScript exposes add_ripple(world_pos, amplitude) so any system (rain, footsteps, projectile impacts, fish) can spawn one with a single call.
When to use
- "Add ripples when the player walks through the puddle."
- "Rain hitting the lake should make ripples."
- "When the bullet hits the water, ripple."
- "Fish jumping leaves ripples."
- "Footsteps on the wet street should ripple."
- A water plane already exists and looks too static.
When NOT to use
- The user wants the whole water surface to wave (Gerstner / FFT ocean) — that's a separate
ocean-waterrecipe; this is impact ripples on top. - The user wants a 2D top-down ripple effect on a UI map — use
canvas_itemshader, not thisspatialone. - The user wants splash particles flying upward on impact — pair this with
hit-spark(recolor blue) for the droplets; this only handles the ring on the surface. - The user wants the ripple to physically displace floating objects — this is visual only. Use
Area3Dimpulses for the simulation side.
Recipe
1. Files to create
addons/vfx/water-ripple/water_ripple.gdshader # spatial shader on the water plane
addons/vfx/water-ripple/water_ripple_surface.gd # MeshInstance3D controller w/ add_ripple()
addons/vfx/water-ripple/water_ripple.tscn # reusable plane
2. Shader code
addons/vfx/water-ripple/water_ripple.gdshader:
shader_type spatial;
render_mode blend_mix, depth_draw_opaque, cull_disabled;
const int MAX_RIPPLES = 16;
uniform vec4 water_color : source_color = vec4(0.10, 0.30, 0.45, 0.85);
uniform vec4 ripple_color : source_color = vec4(0.85, 0.95, 1.00, 1.0);
uniform float water_metallic : hint_range(0.0, 1.0) = 0.4;
uniform float water_roughness: hint_range(0.0, 1.0) = 0.15;
uniform float fresnel_power : hint_range(0.5, 8.0) = 4.0;
uniform float scroll_speed : hint_range(0.0, 0.5) = 0.05;
uniform sampler2D normal_map : hint_normal;
// Per-ripple data: (origin.xz, start_time, amplitude * (1 if active else 0))
uniform vec4 ripples[MAX_RIPPLES];
// Ripple ages run off the controller's own clock, pushed here every frame. They
// cannot run off TIME: shader TIME wraps at
// rendering/limits/time/time_rollover_secs (3600 by default, verified), which
// would send every live ripple to a negative age once an hour of uptime.
uniform float now = 0.0;
uniform float ripple_speed : hint_range(0.5, 8.0) = 2.5; // m/s expansion
uniform float ripple_wavelength : hint_range(0.05, 1.0) = 0.20; // distance between crests
uniform float ripple_lifetime : hint_range(0.5, 6.0) = 2.5; // seconds visible
uniform float ripple_height : hint_range(0.0, 0.4) = 0.08; // visual normal kick
void vertex() {
// Sample ripples in vertex to displace Y for proper silhouette.
vec3 wpos = (MODEL_MATRIX * vec4(VERTEX, 1.0)).xyz;
float disp = 0.0;
for (int i = 0; i < MAX_RIPPLES; i++) {
vec4 r = ripples[i];
if (r.w <= 0.0) continue;
float age = now - r.z;
if (age < 0.0 || age > ripple_lifetime) continue;
float dist = length(wpos.xz - r.xy);
float front = age * ripple_speed;
float ring = exp(-pow((dist - front) / 0.25, 2.0));
float fade = 1.0 - smoothstep(0.0, ripple_lifetime, age);
disp += sin((dist - front) / ripple_wavelength * 6.2831) * ring * fade * r.w;
}
VERTEX.y += disp * ripple_height;
}
void fragment() {
// Base water normal scroll.
vec2 nuv = UV + vec2(TIME * scroll_speed, TIME * scroll_speed * 0.7);
vec3 base_n = texture(normal_map, nuv).rgb * 2.0 - 1.0;
// Composite ripple normals on top.
vec3 wpos = (INV_VIEW_MATRIX * vec4(VERTEX, 1.0)).xyz;
vec3 ripple_n = vec3(0.0, 0.0, 1.0);
float ripple_glow = 0.0;
for (int i = 0; i < MAX_RIPPLES; i++) {
vec4 r = ripples[i];
if (r.w <= 0.0) continue;
float age = now - r.z;
if (age < 0.0 || age > ripple_lifetime) continue;
vec2 d = wpos.xz - r.xy;
float dist = length(d);
float front = age * ripple_speed;
float ring = exp(-pow((dist - front) / 0.25, 2.0));
float fade = 1.0 - smoothstep(0.0, ripple_lifetime, age);
vec2 dir = (dist > 0.0001) ? (d / dist) : vec2(0.0);
float wave = cos((dist - front) / ripple_wavelength * 6.2831);
ripple_n.xy += dir * wave * ring * fade * r.w * 1.5;
ripple_glow += ring * fade * r.w * 0.5;
}
// NORMAL_MAP is decoded by the engine (scene_forward_clustered.glsl:1427 —
// `normal_map.xy = normal_map.xy * 2.0 - 1.0`), so hand it the RAW [0,1] texel
// encoding. Assigning an already-decoded +/-1 vector makes a flat surface read
// as permanent maximum tilt.
NORMAL_MAP = normalize(base_n + vec3(ripple_n.xy, 0.0)) * 0.5 + 0.5;
NORMAL_MAP_DEPTH = 0.6;
// Fresnel-tinted color.
float fres = pow(1.0 - clamp(dot(NORMAL, VIEW), 0.0, 1.0), fresnel_power);
ALBEDO = mix(water_color.rgb, ripple_color.rgb, ripple_glow);
METALLIC = water_metallic;
ROUGHNESS = water_roughness;
ALPHA = mix(water_color.a, 1.0, fres);
EMISSION = ripple_color.rgb * ripple_glow * 0.4;
}
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.
- 7d ago First seen · 401 lines · 75 tokens per session scan A a3db672027b8
water-ripple is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 5,297 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
artist-self-evolve
Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts. Lead-dispatched only — orchestrator invokes this skill from its self-evolve flow with a game-slug message; do not self-trigger.
vibegame-build
Run VibeGame's standard end-to-end game development workflow with reviewer gates. Use when the user wants to create a game from zero or evolve an existing game across multiple stages.
vibegame-start
Resume a VibeGame orchestrator session after vibegame start. Use at the beginning of a Claude or Codex session to inspect team runtime state, repair missing persistent members, load goal and GDD context, inspect tasks, and ask the user what to do next.
vibegame-edit
Iterate broadly on an existing game, on top of vibegame-build. Use when the user asks to change an existing game's art style, genre, or core rules. Not for local tuning such as numbers or game feel. Orchestrator only.
hearth-art
Give a Hearth game real art and sound — importing and slicing spritesheets, animations, procedural sprites and sounds, autonomous CC0 asset sourcing (Kenney, itch.io, OpenGameArt, Freesound, Google Fonts) with licensing rules, and pixel-art discipline (never stretch; read the art before using it). Use when the game…