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/cxcscmu/skilllearnbench/d3-force-simulationnpx skills add cxcscmu/SkillLearnBench --skill d3-force-simulationgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWhat 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 | $0.00026 | $0.01221 |
| Opus 5 | $0.00013 | $0.00611 |
| Sonnet 5 | $0.00005 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
d3-force-simulation 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
D3.js Force Simulation
Overview
Force simulation in D3 uses physics-based algorithms to position nodes (bubbles) based on forces. Perfect for creating bubble charts with natural-looking clusters.
Core Concepts
1. Creating a Simulation
const simulation = d3.forceSimulation(nodes)
.force("name", forceFunction)
.on("tick", updatePositions);
// Start simulation (runs in background)
simulation.alpha(1); // reset energy
2. Common Forces
forceX / forceY
Position bubbles toward target x/y coordinates (creates clustering):
// Group by sector - each sector gets target x position
const sectors = Array.from(new Set(data.map(d => d.sector)));
const sectorX = d3.scalePoint()
.domain(sectors)
.range([0, width]);
const simulation = d3.forceSimulation(nodes)
.force("x", d3.forceX()
.x(d => sectorX(d.sector)) // each sector pulled to its x position
.strength(0.05) // weak force (allows spreading)
)
.force("y", d3.forceY()
.y(height / 2) // all centered vertically
.strength(0.03)
);
forceCollide
Prevents bubbles from overlapping:
.force("collide", d3.forceCollide()
.radius(d => radiusScale(d.marketCap) + 2) // add padding
.strength(0.5) // collision strength (0-1)
)
forceManyBody
Repulsive or attractive force between all nodes:
.force("charge", d3.forceManyBody()
.strength(-50) // negative = repulsion, positive = attraction
)
3. Tick Events
Update positions on each simulation frame:
simulation.on("tick", () => {
// Update circles
circles
.attr("cx", d => d.x)
.attr("cy", d => d.y);
// Update text
labels
.attr("x", d => d.x)
.attr("y", d => d.y);
});
4. Preventing Bubbles from Moving Off-Screen
Fix nodes to boundaries:
simulation.on("tick", () => {
nodes.forEach(d => {
// Clamp positions within bounds
d.x = Math.max(d.radius, Math.min(width - d.radius, d.x));
d.y = Math.max(d.radius, Math.min(height - d.radius, d.y));
});
// Update positions
circles.attr("cx", d => d.x).attr("cy", d => d.y);
});
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 · 178 lines · 26 tokens per session scan A 060ecc19e3cb
d3-force-simulation is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,221 once invoked, about $0.0001 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
gpt-multimodal
Analyze images and multi-frame sequences using OpenAI GPT series.
Speaker Clustering Methods
Choose and implement clustering algorithms for grouping speaker embeddings after VAD and embedding extraction. Compare Hierarchical clustering (auto-tunes speaker count), KMeans (fast, requires known count), and Agglomerative clustering (fixed clusters). Use Hierarchical clustering when speaker count is unknown…
mhc-algorithm
Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).
nanogpt-training
Train GPT-2 scale models (124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
agentsop-dspy
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts…
agentsop-per-model-artifacts
Lifecycle SOP for per-model prompt artifacts — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when…