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 muzzle-flashgit 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/muzzle-flash)<a href="https://agentmods.dev/skills/summerengine/summer-engine-agent/muzzle-flash"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/muzzle-flash/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/muzzle-flash"><img src="https://agentmods.dev/badge/skills/summerengine/summer-engine-agent/muzzle-flash.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 | $0.00077 | $0.04522 |
| Opus 5 | $0.00039 | $0.02261 |
| Sonnet 5 | $0.00015 | $0.00904 |
| Haiku 4.5 | $0.00008 | $0.00452 |
Grade A, and why
muzzle-flash 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 6d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
muzzle-flash — One-Shot Star-Burst Flare
A muzzle flash is on screen for 60–100 ms. Long enough to read, too short to animate. The recipe: a single billboarded quad with a star-burst gradient shader, fired by restart() on a weapon's fired signal, plus an OmniLight3D snapping on for 60 ms to light the room. Optional: a tiny GPUParticles3D one-shot for sparks. Doom Eternal does this. Half-Life 2 did this. Every shooter does this.
When to use
- "Add a muzzle flash to the rifle / pistol / shotgun."
- "When I fire, the gun should flash."
- "Spell-cast burst at the wizard's palm." (one-shot at hand position)
- "Cannon fires, big flash at the barrel."
- The user just hooked up a weapon and the firing reads as silent / weightless.
When NOT to use
- The user wants a continuous flame (flamethrower) — use
fire, not muzzle-flash. - The user wants the impact spark on the wall the bullet hit — that's
hit-spark. - The user wants a tracer line from barrel to target — use an
ImmediateMeshrecipe, not this. The current Summer build has noLine3D(ClassDB.class_exists("Line3D")isfalse). - The user wants a slow-glowing spell charge-up — use
magic-glowfor the buildup, then this for the release frame.
Recipe
1. Files to create
addons/vfx/muzzle-flash/muzzle_flash.gdshader
addons/vfx/muzzle-flash/muzzle_flash.gd
addons/vfx/muzzle-flash/muzzle_flash.tscn (reusable scene)
2. Shader code
addons/vfx/muzzle-flash/muzzle_flash.gdshader:
shader_type spatial;
render_mode unshaded, blend_add, depth_draw_never, cull_disabled, shadows_disabled;
uniform vec4 flash_color : source_color = vec4(1.0, 0.85, 0.45, 1.0);
uniform vec4 core_color : source_color = vec4(1.0, 1.0, 0.95, 1.0);
uniform float intensity : hint_range(0.0, 1.0) = 1.0; // driven by the controller (1 → 0)
uniform float emission_boost : hint_range(0.0, 12.0) = 6.0;
uniform int ray_count : hint_range(2, 8) = 4;
uniform float ray_sharpness : hint_range(0.5, 32.0) = 8.0;
uniform float random_seed : hint_range(0.0, 6.2831) = 0.0; // rotates the star per shot
void vertex() {
// Billboard toward the camera. The bare mat4(INV_VIEW_MATRIX[0..2], MODEL_MATRIX[3])
// form discards the node's scale, so the per-shot `flash_size` randomisation in
// fire() would never reach the screen — normalize the basis and re-apply scale.
MODELVIEW_MATRIX = VIEW_MATRIX * mat4(
normalize(INV_VIEW_MATRIX[0]),
normalize(INV_VIEW_MATRIX[1]),
normalize(INV_VIEW_MATRIX[2]),
MODEL_MATRIX[3]) * mat4(
vec4(length(MODEL_MATRIX[0].xyz), 0.0, 0.0, 0.0),
vec4(0.0, length(MODEL_MATRIX[1].xyz), 0.0, 0.0),
vec4(0.0, 0.0, length(MODEL_MATRIX[2].xyz), 0.0),
vec4(0.0, 0.0, 0.0, 1.0));
MODELVIEW_NORMAL_MATRIX = mat3(MODELVIEW_MATRIX);
}
void fragment() {
vec2 c = UV - vec2(0.5);
float r = length(c) * 2.0;
float ang = atan(c.y, c.x) + random_seed;
// Soft radial core: hottest at center, falls off to zero at the edge.
float core = smoothstep(1.0, 0.0, r);
core = pow(core, 2.0);
// Star-burst rays: cosine of angle * ray_count gives N spokes.
float rays = pow(max(cos(ang * float(ray_count)), 0.0), ray_sharpness);
rays *= smoothstep(1.05, 0.05, r); // rays fade to edge
float mask = clamp(core + rays * 0.85, 0.0, 1.0);
// Mix core color (white-hot) into flash color at the very center.
vec3 col = mix(flash_color.rgb, core_color.rgb, pow(core, 4.0));
// `render_mode unshaded` outputs ALBEDO and discards EMISSION entirely
// (scene_forward_clustered.glsl:2962 — `frag_color = vec4(albedo, alpha)`
// under MODE_UNSHADED), so the bloom boost has to live in ALBEDO.
ALBEDO = col * emission_boost * intensity;
ALPHA = mask * intensity;
}
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.
- 6d ago First seen · 370 lines · 77 tokens per session scan A d8019c536784
muzzle-flash is a skill published in the GitHub repository SummerEngine/summer-engine-agent (59 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 4,522 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-feel
Make a Hearth game feel good, not just run — the juice stack (hit-stop, screen shake, flash, particle bursts, layered sound), tween easing, camera effects, anticipation/recovery animation idioms, game-UX conventions (menus, pause, onboarding, difficulty, save etiquette), effect-asserting playtests, and the quality bar…