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 G1Joshi/Agent-Skills --skill cosmosdbgit clone --depth 1 https://github.com/G1Joshi/Agent-SkillsWrote 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/g1joshi/agent-skills/cosmosdb)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/cosmosdb"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/cosmosdb/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/g1joshi/agent-skills/cosmosdb"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/cosmosdb.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 | $0.00041 | $0.01161 |
| Opus 5.5 | $0.00016 | $0.00464 |
| Sonnet 5.5 | $0.00008 | $0.00232 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
cosmosdb 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 23d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Cosmos DB
Cosmos DB is Azure's planetary-scale database. It supports multiple APIs: NoSQL (Core/JSON), MongoDB, PostgreSQL, Cassandra, Gremlin (Graph), and Table.
When to Use
- Global Enterprise Applications on Azure: Fully managed NoSQL database with turnkey multi-region replication and single-digit millisecond latency SLAs.
- Multi-Model API Compatibility: Using existing MongoDB, Apache Cassandra, Gremlin (Graph), or PostgreSQL skills via native Cosmos DB APIs.
- Dynamic Scale & Autoscale Request Units (RU/s): Applications with seasonal traffic spikes scaling compute and throughput instantly.
- Guaranteed Consistency Options: Tuning consistency across 5 distinct levels (Strong, Bounded Staleness, Session, Consistent Prefix, Eventual).
Quick Start
Container container = database.GetContainer("Items");
Item item = new Item
{
Id = "1",
Category = "Personal",
Name = "Groceries"
};
await container.CreateItemAsync(item, new PartitionKey(item.Category));
Core Concepts
Request Units (RU/s) Throughput Currency
Throughput is normalized into Request Units; a 1KB point read costs 1 RU:
// Azure Cosmos DB Node.js SDK (NoSQL API)
import { CosmosClient } from "@azure/cosmos";
const client = new CosmosClient({
endpoint: process.env.COSMOS_ENDPOINT!,
key: process.env.COSMOS_KEY!,
});
const container = client.database("CommerceDb").container("Orders");
// Point read with exact partition key (Cost: 1 RU)
const { resource, requestCharge } = await container
.item("order_415", "customer_99")
.read();
console.log(`Retrieved order. Request Charge: ${requestCharge} RUs`);
Partition Key Selection (Physical vs Logical Partitions)
The partition key determines how items are distributed across physical servers; high-cardinality keys ensure even distribution:
// Items must include the partition key property
{
"id": "order_415",
"customerId": "customer_99", // Partition Key
"totalAmount": 149.5,
"orderStatus": "SHIPPED"
}
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.
- 23d ago Changed c11949c0d9e6
- 27d ago Changed · +76 lines · +23 tokens per session 19b3af5b2f9b
- 1mo ago First seen · 60 lines · 18 tokens per session scan A 21fc601bc0d3
cosmosdb is a skill published in the GitHub repository G1Joshi/Agent-Skills (15 stars, last pushed 24d ago), licensed MIT. It adds 41 tokens to every session and 1,161 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 2026-09-03.
Other skills, from other repositories
deprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset…
saas-multi-tenant
Design and implement multi-tenant SaaS architectures with RLS, tenant isolation, and PostgreSQL / Desain dan implementasikan arsitektur SaaS multi-tenant dengan RLS, isolasi tenant, dan PostgreSQL.
vector-db-rag-expert
Expert guide for high-performance Vector Databases, Deep RAG architectures, pgvector 0.8+ HNSW, Reciprocal Rank Fusion (RRF), Cross-Encoder Re-ranking, and Late Chunking / Panduan ahli Vector DB, arsitektur Deep RAG, pgvector HNSW, RRF, dan Re-ranking.
backup-restore
PostgreSQL backup and restore with pgBackRest — full/incremental/WAL, PITR, K8s CronJob scheduling, and restore verification.
db-performance
PostgreSQL query performance — EXPLAIN ANALYZE, index design, pgstatstatements, slow query detection, connection pool tuning.
postgres-operations
PostgreSQL operational runbooks — health checks, vacuum, bloat, locks, PITR, connection pool management.