generate-skills

generate-skills is a command for Claude Code from AzureCosmosDB/cosmosdb-claude-code-plugin. It costs 14 tokens per session (475 once invoked), scanned A, original, MIT.

A command that refreshes a local set of Cosmos DB best-practice rules from Microsoft's public cosmosdb-agent-kit repository. Cosmos DB is Microsoft's cloud database service.

In plain words
What is it for?
Downloading rule files, comparing them with local copies, updating the rule index, and reporting the changes.
Why use it?
It keeps the local guidance aligned with the upstream rule files and shows which rules were added, changed, or removed.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the cosmosdb-claude-code-plugin plugin — 1 skill, 3 commands, 1 agent shipped together

Good fit Downloading rule files, comparing them with local copies, updating the rule index, and reporting the changes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/azurecosmosdb/cosmosdb-claude-code-plugin/generate-skills
Install

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.

Clone the repo
git clone --depth 1 https://github.com/AzureCosmosDB/cosmosdb-claude-code-plugin

Made for: Claude Code.

Or install cosmosdb-claude-code-plugin, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 agent.

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 generate-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/azurecosmosdb/cosmosdb-claude-code-plugin/generate-skills.svg)](https://agentmods.dev/commands/azurecosmosdb/cosmosdb-claude-code-plugin/generate-skills)
Your own site
<a href="https://agentmods.dev/commands/azurecosmosdb/cosmosdb-claude-code-plugin/generate-skills"><img src="https://agentmods.dev/badge/commands/azurecosmosdb/cosmosdb-claude-code-plugin/generate-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 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 original No closer match found 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 $0.00014 $0.00475
Opus 5 $0.00007 $0.00237
Sonnet 5 $0.00003 $0.00095
Haiku 4.5 $0.00001 $0.00047

Measured 8d ago against content hash 6e60f534c1f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

generate-skills 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 8d 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.

commands/generate-skills.md · 40 lines

What it actually says

Sync Cosmos DB Best Practices Rules

Fetch the latest individual rule files from the AzureCosmosDB/cosmosdb-agent-kit repository and update the local rule files.

Steps

  1. Fetch the file listing from the GitHub API: https://api.github.com/repos/AzureCosmosDB/cosmosdb-agent-kit/contents/skills/cosmosdb-best-practices/rules

  2. For each .md file returned, download it from: https://raw.githubusercontent.com/AzureCosmosDB/cosmosdb-agent-kit/main/skills/cosmosdb-best-practices/rules/{filename}

  3. Save each file to: skills/cosmosdb-best-practices/rules/{filename}

  4. Compare files before and after. Report:

    • New rules added
    • Existing rules updated (content changed)
    • Rules removed upstream (exist locally but not in API response)
  5. Update skills/cosmosdb-best-practices/SKILL.md:

    • Add any new rules to the appropriate category in the Rule Index section
    • Remove any rules that were deleted upstream
    • Update the total rule count in the description
  6. Report a summary of what changed.

Notes

  • The source of truth is: https://github.com/AzureCosmosDB/cosmosdb-agent-kit/tree/main/skills/cosmosdb-best-practices/rules
  • Rules are individual markdown files named by {prefix}-{topic}.md (e.g., model-embed-related.md, sdk-singleton-client.md)
  • The prefix determines the category: model- → Data Modeling, partition- → Partition Key, query- → Query Optimization, sdk- → SDK, index- → Indexing, throughput- → Throughput, global- → Global Distribution, monitoring- → Monitoring, pattern- → Design Patterns, vector- → Vector Search
  • Files starting with _ (like _sections.md, _template.md) are metadata, not rules

$ARGUMENTS

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. 8d ago First seen · 40 lines · 14 tokens per session scan A 6e60f534c1f8

Subscribe to this mod's changes

generate-skills is a command published in the GitHub repository AzureCosmosDB/cosmosdb-claude-code-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 475 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.