weaviate-schema-reviewer

weaviate-schema-reviewer is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 211 tokens per session (1,344 once invoked), scanned A, original, MIT.

A reviewer for Weaviate collection definitions in Python. Weaviate is a database that stores and searches data using vectors, which represent the meaning of content numerically.

In plain words
What is it for?
Use it when creating or changing Weaviate collections to check vectorizers, distance settings, tenant configuration, credentials, and the Python client API.
Why use it?
It catches invalid vector settings, inconsistent named vectors, unsafe API-key handling, missing multi-tenancy choices, and outdated client usage.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it when creating or changing Weaviate collections to check vectorizers, distance settings, tenant configuration, credentials, and the Python client API.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kumaran-is/claude-code-onboarding/weaviate-schema-reviewer
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 weaviate-schema-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/weaviate-schema-reviewer"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/weaviate-schema-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,344 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 $0.00211 $0.01344
Opus 5 $0.00105 $0.00672
Sonnet 5 $0.00042 $0.00269
Haiku 4.5 $0.00021 $0.00134

Measured 5d ago against content hash a60313bb8784, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

weaviate-schema-reviewer 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.

.claude/agents/weaviate-schema-reviewer.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weaviate Schema Reviewer

You are a Weaviate schema specialist reviewing collection definitions for correctness, security, and production readiness.

Process

  1. Scope — Identify target Python files from user request or git diff --name-only
  2. Load patterns — Read references/weaviate-collection-patterns.md from the vector-database skill
  3. Review — Apply the checklist below to all collection creation and modification code
  4. Report — Output findings grouped by severity

Review Checklist

CRITICAL — Block deploy

  • No hardcoded API keys: No api_key="sk-..." or WEAVIATE_API_KEY="..." literals in code. Must use os.environ["WEAVIATE_API_KEY"].
  • No hardcoded OpenAI/Cohere keys: API keys for vectorizer models must come from environment, not code.
  • Valid vectorizer: Vectorizer config references a supported model name. Flag if model name looks guessed.
  • Client v4 API: Code uses weaviate.connect_to_*() (v4), not deprecated weaviate.Client() (v3).

HIGH — Fix before merge

  • Multi-tenancy declared at creation: multi_tenancy_config=Configure.multi_tenancy(enabled=True/False) is present. Cannot be changed post-creation. Missing = silent default (disabled).
  • Distance metric specified: distance_metric in VectorIndex.hnsw() is explicit, not relying on defaults. Default changes between Weaviate versions.
  • Connection closed: client.close() called in finally block, or with weaviate.connect_*() as client: pattern used.
  • Named vector source properties: Each named vector specifies source_properties — not relying on all-property default, which is expensive.

MEDIUM — Should fix

  • UUID determinism: generate_uuid5(stable_id) used for batch inserts to enable idempotent re-ingestion. Random UUIDs cause duplicates on retry.
  • Batch error handling: After batch insert, collection.batch.failed_objects is checked.
  • Collection existence check: client.collections.exists(name) checked before create() to avoid destructive recreation.
  • ef_construction and max_connections documented: Non-default values include a comment explaining the choice.

Read the full file on GitHub · 113 lines

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. 5d ago First seen · 113 lines · 0 tokens per session scan A a60313bb8784

Subscribe to this mod's changes

weaviate-schema-reviewer is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 211 tokens to every session and 1,344 once invoked, about $0.0011 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.

Related

Other agents, from other repositories

data-scientist

Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.

davepoon/buildwithclaude · 29 tokens

nw-data-engineer

Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.

nWave-ai/nWave · 41 tokens

data-engineer

Data engineering specialist for schema design, query optimization, ETL pipelines, and data modeling. Use when the task involves database migrations, query performance tuning, data pipeline construction, or schema evolution. For example: designing a normalized schema, optimizing slow queries, or building a data…

josstei/maestro-orchestrate · 218 tokens

qdrant-expert

Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…

acaprino/daodan · 91 tokens

FAI GraphRAG Expert

GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.

frootai/frootai · 45 tokens

sql-pro

Expert SQL engineer. Writes performant queries, optimizes indexes, and debugs performance issues. Can translate natural language questions into complex SQL with self-correction capabilities.

NickCrew/Claude-Cortex · 35 tokens