servicenow-atlas: Skill for Claude Code

.agents/skills/embedding-strategies/SKILL.md

embedding-strategies is a skill for Claude Code, Codex from sagar-shirwalkar/servicenow-atlas. It costs 37 tokens per session (4,310 once invoked), scanned A, a copy of embedding-strategies, Apache-2.0.

A guide to choosing and tuning embedding models, which turn text into numeric representations so related documents can be found by meaning. It also covers how to split documents into pieces for search and retrieval-augmented generation (RAG), where an AI answers using a document collection.

In plain words
What is it for?
Use it to compare embedding models, design chunking and preprocessing, support multiple languages, reduce vector size, and adapt semantic search or RAG to a specific subject area.
Why use it?
It helps you choose a suitable model and document-splitting approach instead of relying on search results that miss relevant context or use unnecessary computing resources.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sagar-shirwalkar/servicenow-atlas's own configuration. It tells Claude Code and Codex how to work on servicenow-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything servicenow-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sagar-shirwalkar/servicenow-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sagar-shirwalkar/servicenow-atlas/main/.agents/skills/embedding-strategies/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sagar-shirwalkar/servicenow-atlas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for embedding-strategies

README.md
[![agentmods](https://agentmods.dev/badge/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies/github.svg)](https://agentmods.dev/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies)
Your own site
<a href="https://agentmods.dev/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies/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.

agentmods 80×15 button for embedding-strategies

Your own site · 80×15
<a href="https://agentmods.dev/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/servicenow-atlas/embedding-strategies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,310 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.04310
Opus 5 $0.00018 $0.02155
Sonnet 5 $0.00007 $0.00862
Haiku 4.5 $0.00004 $0.00431

Measured 12d ago against content hash d949436dadf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

embedding-strategies 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 12d 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.

Origin

This is a copy

89% identical to embedding-strategies — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/embedding-strategies/SKILL.md · 601 lines

How it starts

The opening of the file, as written. The whole thing — 601 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

When to Use This Skill

  • Choosing embedding models for RAG
  • Optimizing chunking strategies
  • Fine-tuning embeddings for domains
  • Comparing embedding model performance
  • Reducing embedding dimensions
  • Handling multilingual content

Core Concepts

1. Embedding Model Comparison (2026)

Model Dimensions Max Tokens Best For
voyage-3-large 1024 32000 Claude apps (Anthropic recommended)
voyage-3 1024 32000 Claude apps, cost-effective
voyage-code-3 1024 32000 Code search
voyage-finance-2 1024 32000 Financial documents
voyage-law-2 1024 32000 Legal documents
text-embedding-3-large 3072 8191 OpenAI apps, high accuracy
text-embedding-3-small 1536 8191 OpenAI apps, cost-effective
bge-large-en-v1.5 1024 512 Open source, local deployment
all-MiniLM-L6-v2 384 256 Fast, lightweight
multilingual-e5-large 1024 512 Multi-language

2. Embedding Pipeline

Document → Chunking → Preprocessing → Embedding Model → Vector
                ↓
        [Overlap, Size]  [Clean, Normalize]  [API/Local]

Templates

Template 1: Voyage AI Embeddings (Recommended for Claude)

from langchain_voyageai import VoyageAIEmbeddings
from typing import List
import os

# Initialize Voyage AI embeddings (recommended by Anthropic for Claude)
embeddings = VoyageAIEmbeddings(
    model="voyage-3-large",
    voyage_api_key=os.environ.get("VOYAGE_API_KEY")
)

def get_embeddings(texts: List[str]) -> List[List[float]]:
    """Get embeddings from Voyage AI."""
    return embeddings.embed_documents(texts)

def get_query_embedding(query: str) -> List[float]:
    """Get single query embedding."""
    return embeddings.embed_query(query)

# Specialized models for domains
code_embeddings = VoyageAIEmbeddings(model="voyage-code-3")
finance_embeddings = VoyageAIEmbeddings(model="voyage-finance-2")
legal_embeddings = VoyageAIEmbeddings(model="voyage-law-2")

Read the full file on GitHub · 601 lines

Changes

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.

  1. 12d ago First seen · 601 lines · 37 tokens per session scan A d949436dadf3

Subscribe to this mod's changes

embedding-strategies is a skill published in the GitHub repository sagar-shirwalkar/servicenow-atlas (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 4,310 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to embedding-strategies, differing in 8 lines, and is treated as a copy.

Related

Other skills, from other repositories

graph-retrieval

Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.

study8677/repobrain · 46 tokens

rag-perf

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

NVIDIA-AI-Blueprints/rag · 56 tokens

rag-blueprint

NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion…

NVIDIA-AI-Blueprints/rag · 92 tokens

rag-eval

Filesystem RAG benchmarks: corpus/, train.json, evaluaterag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.

NVIDIA-AI-Blueprints/rag · 48 tokens

knowledge-layer

High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.

study8677/repobrain · 42 tokens

rag-evaluate-quality

Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…

lyonzin/knowledge-rag · 78 tokens