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 jnPiyush/AgentX --skill cosmos-dbgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/cosmos-db)<a href="https://agentmods.dev/skills/jnpiyush/agentx/cosmos-db"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cosmos-db/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/jnpiyush/agentx/cosmos-db"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/cosmos-db.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00075 | $0.03011 |
| Opus 5.5 | $0.00030 | $0.01204 |
| Sonnet 5.5 | $0.00015 | $0.00602 |
| Haiku 4.5 | $0.00007 | $0.00301 |
Grade A, and why
cosmos-db 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 1mo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure Cosmos DB
Globally distributed, multi-model database. This skill emphasizes the Gremlin (Graph) API and covers cross-API design rules: partitioning, request units, consistency, security, and change feed.
When to Use
- Modeling highly connected data (social, fraud rings, recommendations, knowledge graphs, IT/asset topology) with the Gremlin API
- Designing partition keys and estimating RU/s for a new container
- Choosing a consistency level and multi-region write strategy
- Securing accounts with Entra ID (RBAC) and disabling key-based auth
- Implementing change feed processors, TTL-based purges, or analytical store (Synapse Link)
- Migrating between APIs (e.g., adjacency-list NoSQL graph -> Gremlin)
Decision Tree
Pick the right Cosmos DB API
+-- Highly connected data, multi-hop traversals -> Gremlin (Graph) API
+-- JSON documents, flexible schema, point reads -> NoSQL (SQL) API
+-- Existing MongoDB driver / wire protocol -> API for MongoDB (vCore or RU)
+-- Wide-column, time-series -> API for Cassandra
+-- Key-value with table semantics -> API for Table
Picked Gremlin? Then:
+-- Vertex count >> edge count, shallow traversals -> NoSQL with adjacency list MAY be cheaper
+-- Deep multi-hop / pattern matching -> Gremlin (this skill)
+-- Need ACID across many vertices -> Re-evaluate; Cosmos has scope limits
Core Concepts
| Concept | Summary |
|---|---|
| Account | Top-level resource; pinned to one API family (Gremlin, NoSQL, Mongo, ...) |
| Database | Logical grouping; can hold provisioned-throughput shared by graphs |
| Graph (container) | Holds vertices and edges; analogous to a NoSQL container |
| Logical partition | All vertices/edges sharing the same partition key value; 20 GB hard limit per logical partition |
| Physical partition | Cosmos-managed shard; ~50 GB and ~10k RU/s soft cap per partition |
| RU/s | Normalized cost unit; provisioned (manual/autoscale) or serverless |
| Consistency | Strong, Bounded Staleness, Session (default), Consistent Prefix, Eventual |
| Change Feed | Ordered log of inserts/updates per logical partition |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/cosmos_gremlin_account.bicep 4.1 KB
- assets/gremlin_python_client.py 4.6 KB runs code
- assets/gremlin_traversals.groovy 3.0 KB
- references/change-feed-and-ttl.md 2.2 KB
- references/consistency-and-global-distribution.md 2.0 KB
- references/graph-data-modeling.md 3.0 KB
- references/gremlin-graph-api.md 3.5 KB
- references/partitioning-and-ru.md 2.1 KB
- references/security-and-rbac.md 2.3 KB
- references/sql-nosql-api.md 2.4 KB
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.
- 1mo ago Changed 6fbdcb6bc989
- 1mo ago First seen · 212 lines · 75 tokens per session scan A 27f7705f27de
cosmos-db is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 75 tokens to every session and 3,011 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
dbx
Use the DBX CLI to inspect DBX-managed database connections, explore schemas, run bounded read-only queries, generate DBML or schema documentation, and open tables in DBX Desktop. Use when the user asks to work with a database configured in DBX from a shell-capable AI agent. Never enable writes unless the user…
azure-mgmt-mongodbatlas-dotnet
Manage MongoDB Atlas Organizations as Azure ARM resources using Azure.ResourceManager.MongoDBAtlas SDK. Use when creating, updating, listing, or deleting MongoDB Atlas organizations through Azure Marketplace integration. This SDK manages the Azure-side organization resource, not Atlas clusters/databases directly.
nosqli
NoSQL injection — MongoDB operator injection ($ne, $gt, $where, $regex), CouchDB / Firebase / Redis attack patterns, auth bypass, blind extraction.
prisma-mongodb-upgrade
Decision and migration guide for Prisma ORM MongoDB projects on v6, which have no upgrade path to v7. Use when a MongoDB project asks about upgrading Prisma, when "upgrade to prisma 7" comes up in a project with provider = "mongodb", or when evaluating a move to Prisma Next. Triggers on "upgrade prisma mongodb"…
byted-volcengine-mongodb
An operations tool for Volcengine MongoDB, a document database that stores data in flexible, JSON-like records. It can query managed MongoDB instances and return details for further explanation or diagnosis.
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…