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 cxcscmu/SkillLearnBench --skill exploded-view-illustrationgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/exploded-view-illustration)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/exploded-view-illustration"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/exploded-view-illustration.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01327 |
| Opus 5 | $0.00016 | $0.00664 |
| Sonnet 5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
exploded-view-illustration 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 3d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exploded-View Illustration Technique
Concept
An exploded-view diagram shows the internal components of a device separated along a common axis (usually vertical for portrait posters), with leader lines and labels identifying each component.
Layout Strategy
Poster (portrait, e.g. 2400x3200)
├── Title block (top-left)
├── Exploded component stack (center)
│ ├── Layer 5: Top Casing ← highest Y offset (top)
│ ├── Layer 4: Thermal Unit
│ ├── Layer 3: PCB Board
│ ├── Layer 2: Battery Pack
│ └── Layer 1: Interface / Bottom ← lowest (bottom)
└── Legend / spec block (bottom)
Isometric Slab Drawing (Pillow)
Each hardware layer is drawn as a parallelogram/trapezoid to suggest 3D depth:
def draw_slab(draw, cx, cy, w, h, depth, fill, outline, line_w=2):
"""
Draw an isometric rectangular slab centered at (cx, cy).
w = width, h = thickness (vertical), depth = isometric depth offset
"""
# Top face (parallelogram)
top = [
(cx - w//2, cy - h//2),
(cx + w//2, cy - h//2),
(cx + w//2 + depth, cy - h//2 - depth//2),
(cx - w//2 + depth, cy - h//2 - depth//2),
]
# Front face
front = [
(cx - w//2, cy - h//2),
(cx + w//2, cy - h//2),
(cx + w//2, cy + h//2),
(cx - w//2, cy + h//2),
]
# Right side face
right = [
(cx + w//2, cy - h//2),
(cx + w//2 + depth, cy - h//2 - depth//2),
(cx + w//2 + depth, cy + h//2 - depth//2),
(cx + w//2, cy + h//2),
]
# Draw back-to-front
draw.polygon(top, fill=lighten(fill), outline=outline, width=line_w)
draw.polygon(right, fill=darken(fill), outline=outline, width=line_w)
draw.polygon(front, fill=fill, outline=outline, width=line_w)
Layer Separation (Explode Axis)
import numpy as np
layers = ["Interface", "Battery", "PCB", "Thermal Unit", "Casing"]
n = len(layers)
explode_gap = 120 # px between layers
center_x = poster_w // 2
base_y = poster_h // 2 + (n * explode_gap) // 2
for i, name in enumerate(layers):
cy = base_y - i * (slab_height + explode_gap)
draw_slab(draw, center_x, cy, ...)
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.
- 3d ago First seen · 126 lines · 33 tokens per session scan A 13d663ef1f2b
exploded-view-illustration is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,327 once invoked, about $0.0002 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
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
agentsop-llm-engine-selection
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.
gemini-count-in-video
Analyze and count objects in videos using Google Gemini API (object counting, pedestrian detection, vehicle tracking, and surveillance video analysis).
video-frame-extraction
Extract frames from video files and save them as images using OpenCV.
gemini-video-understanding
Analyze videos with Google Gemini API (summaries, Q&A, transcription with timestamps + visual context, scene/timeline detection, video clipping, FPS control, multi-video comparison, and YouTube URL analysis).
Automatic Speech Recognition (ASR)
Transcribe audio segments to text using Whisper models. Use larger models (small, base, medium, large-v3) for better accuracy, or faster-whisper for optimized performance. Always align transcription timestamps with diarization segments for accurate speaker-labeled subtitles.