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 amenti-labs/vibecraft --skill creating-shapesgit clone --depth 1 https://github.com/amenti-labs/vibecraftWrote 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/amenti-labs/vibecraft/creating-shapes)<a href="https://agentmods.dev/skills/amenti-labs/vibecraft/creating-shapes"><img src="https://agentmods.dev/badge/skills/amenti-labs/vibecraft/creating-shapes/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/amenti-labs/vibecraft/creating-shapes"><img src="https://agentmods.dev/badge/skills/amenti-labs/vibecraft/creating-shapes.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01390 |
| Opus 5.5 | $0.00022 | $0.00556 |
| Sonnet 5.5 | $0.00011 | $0.00278 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
creating-shapes 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Shapes
MCP Tools
worldedit_generation- sphere, cylinder, pyramid, conebuild(code=...)- Python code that generates commands (RECOMMENDED)worldedit_deform- Math expressions
build() Code Mode (RECOMMENDED)
Sphere
build(code="""
commands = []
cx, cy, cz, radius = 105, 70, 205, 10
for x in range(cx - radius, cx + radius + 1):
for y in range(cy - radius, cy + radius + 1):
for z in range(cz - radius, cz + radius + 1):
if ((x-cx)**2 + (y-cy)**2 + (z-cz)**2)**0.5 <= radius:
commands.append(f'/setblock {x} {y} {z} stone')
""", description="Solid sphere")
Hollow Sphere
# Add: if radius - thickness <= dist <= radius:
Dome (Half Sphere)
# Limit y range: for y in range(base_y, base_y + radius + 1):
# Use: dist = ((x-cx)**2 + (y-base_y)**2 + (z-cz)**2)**0.5
Cylinder
build(code="""
commands = []
cx, cz, base_y, radius, height = 105, 205, 64, 8, 20
for y in range(base_y, base_y + height):
for x in range(cx - radius, cx + radius + 1):
for z in range(cz - radius, cz + radius + 1):
if ((x-cx)**2 + (z-cz)**2)**0.5 <= radius:
commands.append(f'/setblock {x} {y} {z} stone_bricks')
""", description="Solid cylinder")
# Hollow: if radius - thickness <= dist <= radius:
Cone
# Per layer: radius = base_radius * (1 - (y - base_y) / height)
Pyramid
build(code="""
commands = []
cx, cz, base_y, half = 105, 205, 64, 10
for layer in range(half + 1):
size = half - layer
for x in range(cx - size, cx + size + 1):
for z in range(cz - size, cz + size + 1):
commands.append(f'/setblock {x} {base_y + layer} {z} sandstone')
""", description="Pyramid")
Torus (Donut)
build(code="""
commands = []
cx, cy, cz, major_r, minor_r = 105, 70, 205, 12, 4
for x in range(cx - major_r - minor_r, cx + major_r + minor_r + 1):
for y in range(cy - minor_r, cy + minor_r + 1):
for z in range(cz - major_r - minor_r, cz + major_r + minor_r + 1):
dist_xz = ((x-cx)**2 + (z-cz)**2)**0.5
tube_dist = ((dist_xz - major_r)**2 + (y-cy)**2)**0.5
if tube_dist <= minor_r:
commands.append(f'/setblock {x} {y} {z} gold_block')
""", description="Torus")
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.
- 2mo ago First seen · 140 lines · 55 tokens per session scan A 25852ad14b28
creating-shapes is a skill published in the GitHub repository amenti-labs/vibecraft (107 stars, last pushed 9mo ago), licensed MIT. It adds 55 tokens to every session and 1,390 once invoked, about $0.0002 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.
creating-shapes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| creating-shapesamenti-labs/vibecraft | Skill | 107 | 9mo ago | MIT | A | 55 | Claude Code |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |