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/nirholas/three.ws/recommendation-algorithm-designnpx skills add nirholas/three.ws --skill recommendation-algorithm-designgit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/recommendation-algorithm-design)<a href="https://agentmods.dev/skills/nirholas/three.ws/recommendation-algorithm-design"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/recommendation-algorithm-design.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 | $0.00088 | $0.04492 |
| Opus 5 | $0.00044 | $0.02246 |
| Sonnet 5 | $0.00018 | $0.00898 |
| Haiku 4.5 | $0.00009 | $0.00449 |
Grade A, and why
recommendation-algorithm-design 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 yesterday.
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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommendation Algorithm Design — From First Principles
This skill teaches you to build recommendation systems that surface the right content to the right person at the right time. You'll learn the full pipeline — from candidate generation to final ranking — and understand why feeds feel the way they do.
The Recommendation Pipeline
Every major social platform follows the same high-level architecture:
┌─────────────────────────────────────────────────────────────┐
│ THE RECOMMENDATION PIPELINE │
├─────────────────────────────────────────────────────────────┤
│ │
│ ALL CONTENT (millions) │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ CANDIDATE │ Filter: ~10,000 posts worth considering │
│ │ GENERATION │ (follows, topics, graph neighbors) │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ RANKING │ Score each candidate: P(engagement) │
│ │ MODEL │ (neural network, 100+ features) │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ ┌─────────────┐ │
│ │ FILTERING │ Remove: spam, duplicates, policy │
│ │ & MIXING │ Inject: diversity, exploration, ads │
│ └──────┬──────┘ │
│ │ │
│ ▼ │
│ FINAL FEED (~50 posts for this session) │
│ │
└─────────────────────────────────────────────────────────────┘
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.
- yesterday First seen · 513 lines · 88 tokens per session scan A d02f10d9edbe
recommendation-algorithm-design is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 4,492 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
tao-train-nvpanoptix3d
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running…
tao-train-pointpillars
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and robotics. Use when training, evaluating, exporting, pruning, retraining, or running inference for a TAO PointPillars…
tao-train-sparse4d
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end 3D perception, with an instance bank for temporal tracking. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Sparse4D model.…
tao-train-bevfusion
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evaluating, or running inference for a TAO BEVFusion model. Trigger phrases include "train BEVFusion", "LiDAR + camera…
photo-sphere-viewer
Use when displaying 360-degree panoramic images (equirectangular/cubemap/dual-fisheye) in web applications, building virtual tours with markers and transitions, embedding interactive panoramas in Vue/React/vanilla JS, or creating 360-degree video players with gyroscope VR support. Photo-Sphere-Viewer v5: JavaScript…
data-pipelines
Create animated data pipeline and ETL flow diagrams using the Excalimate MCP server. Use when asked to visualize data pipelines, ETL/ELT processes, streaming architectures, data warehousing flows, ML pipelines, Kafka/event streaming topologies, or any data transformation workflow — even if the user just says "data…