design-weaviate-collection

design-weaviate-collection is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 48 tokens per session (524 once invoked), scanned A, original, MIT.

A command that generates Python code for creating a Weaviate collection, a structured store for searchable data and its vector representations. It configures properties, vector search, optional named vectors, multi-tenancy, and batch loading from the supplied requirements.

In plain words
What is it for?
Use it to define a collection's fields, embedding setup, distance metric, tenant support, generated search queries, secure connection handling, and repeatable batch inserts.
Why use it?
It helps ensure the collection's settings are declared correctly when it is created, including choices that cannot be changed later.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to define a collection's fields, embedding setup, distance metric, tenant support, generated search queries, secure connection handling, and repeatable batch inserts.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kumaran-is/claude-code-onboarding/design-weaviate-collection
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/kumaran-is/claude-code-onboarding

Made for: Claude Code.

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 design-weaviate-collection

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection/github.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection/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 design-weaviate-collection

Your own site · 80×15
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/design-weaviate-collection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 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 $0.00048 $0.00524
Opus 5 $0.00024 $0.00262
Sonnet 5 $0.00010 $0.00105
Haiku 4.5 $0.00005 $0.00052

Measured 6d ago against content hash 02cd312381dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

design-weaviate-collection 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 6d 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.

.claude/commands/design-weaviate-collection.md · 49 lines

What it actually says

Design Weaviate Collection

Generate production-ready Weaviate Python client v4 collection code.

Input: $ARGUMENTS

Steps

  1. Load the vector-database skill — read SKILL.md and references/weaviate-collection-patterns.md for templates and anti-patterns.

  2. Gather requirements — Extract from $ARGUMENTS or ask:

    • Collection name (PascalCase)
    • Use case (determines property types and vectorizer choice)
    • Embedding model / vectorizer (from skill model table)
    • Distance metric (cosine default; L2 or dot-product if specified)
    • Multi-tenancy: required? (set now — CANNOT change post-creation)
    • Named vectors: multiple embedding spaces needed?
    • Generative RAG: will this collection use .generate.* queries?
  3. Generate collection code including:

    • Correct weaviate.connect_to_*() (v4 API, NOT deprecated weaviate.Client())
    • API keys from os.environ["..."] — NEVER hardcoded
    • client.close() in finally block
    • Configure.multi_tenancy(enabled=True/False) — explicitly declared
    • Configure.VectorIndex.hnsw(distance_metric=...) — explicit, not default
    • All properties with explicit DataType
    • generate_uuid5(stable_id) for batch inserts (idempotent)
    • collection.batch.failed_objects check after batch
  4. Generate helper functions:

    • create_collection_if_not_exists() — checks existence before creating
    • batch_insert(items) — with error checking
    • Query example matching the use case (nearText / hybrid / bm25)
  5. Run weaviate-schema-reviewer agent on the generated code before presenting.

  6. Save file to appropriate location (infer from project structure or use src/vector/ as default).

  7. Report generated files and any reviewer findings.

$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. 6d ago First seen · 49 lines · 48 tokens per session scan A 02cd312381dc

Subscribe to this mod's changes

design-weaviate-collection is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 524 once invoked, about $0.0002 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 2026-09-03.