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 commands/azurecosmosdb/cosmosdb-claude-code-plugin/cosmos-setupgit clone --depth 1 https://github.com/AzureCosmosDB/cosmosdb-claude-code-pluginWrote 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/commands/azurecosmosdb/cosmosdb-claude-code-plugin/cosmos-setup)<a href="https://agentmods.dev/commands/azurecosmosdb/cosmosdb-claude-code-plugin/cosmos-setup"><img src="https://agentmods.dev/badge/commands/azurecosmosdb/cosmosdb-claude-code-plugin/cosmos-setup.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 | $0.00014 | $0.00449 |
| Opus 5 | $0.00007 | $0.00225 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
cosmos-setup 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 5d 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.
What it actually says
Cosmos DB MCP Setup
Help the user configure the optional Azure Cosmos DB MCP Toolkit connection. This enables live database operations (queries, schema discovery, vector search) but is not required — the plugin's skills, agent, and commands work without it.
For detailed instructions, see SETUP.md.
Steps
-
Check prerequisites:
- Ask if they have an Azure Cosmos DB account. If not, direct them to: https://learn.microsoft.com/azure/cosmos-db/nosql/quickstart-portal
- Ask if they have deployed the MCP Toolkit. If not, direct them to: https://github.com/AzureCosmosDB/MCPToolKit#quick-start
-
Get connection details:
- Ask for their deployed MCP Toolkit URL (from
deployment-info.jsonin the MCPToolKit output) - Ask for their Entra App Client ID (also from
deployment-info.json) - Help them get a JWT token by running:
az login az account get-access-token --resource "YOUR-ENTRA-APP-CLIENT-ID" --query accessToken -o tsv - The
--resourcevalue is the Entra App Client ID from the MCPToolKit deployment output
- Ask for their deployed MCP Toolkit URL (from
-
Set environment variables:
- Guide them to set
COSMOSDB_MCP_SERVER_URLto their toolkit URL - Guide them to set
COSMOSDB_MCP_JWT_TOKENto their JWT token - Note: JWT tokens expire after ~1 hour and need to be refreshed
- Guide them to set
-
Create MCP config:
- Guide them to copy
.mcp.example.jsonto.mcp.jsonin their project root - The config references the environment variables set above
- Guide them to copy
-
Verify connection:
- Restart Claude Code after adding
.mcp.json - Try listing databases using the MCP tools
- If connection fails, refer to troubleshooting in SETUP.md
- Restart Claude Code after adding
$ARGUMENTS
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.
- 5d ago First seen · 44 lines · 14 tokens per session scan A 32515af2999b
cosmos-setup is a command published in the GitHub repository AzureCosmosDB/cosmosdb-claude-code-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 449 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 commands, from other repositories
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
volume-admin-set-status
Changes the operational status of a named volume.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.