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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/design-weaviate-collection)<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.
<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>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 | $0.00048 | $0.00524 |
| Opus 5 | $0.00024 | $0.00262 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
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.
What it actually says
Design Weaviate Collection
Generate production-ready Weaviate Python client v4 collection code.
Input: $ARGUMENTS
Steps
-
Load the
vector-databaseskill — readSKILL.mdandreferences/weaviate-collection-patterns.mdfor templates and anti-patterns. -
Gather requirements — Extract from
$ARGUMENTSor 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?
-
Generate collection code including:
- Correct
weaviate.connect_to_*()(v4 API, NOT deprecatedweaviate.Client()) - API keys from
os.environ["..."]— NEVER hardcoded client.close()infinallyblockConfigure.multi_tenancy(enabled=True/False)— explicitly declaredConfigure.VectorIndex.hnsw(distance_metric=...)— explicit, not default- All properties with explicit
DataType generate_uuid5(stable_id)for batch inserts (idempotent)collection.batch.failed_objectscheck after batch
- Correct
-
Generate helper functions:
create_collection_if_not_exists()— checks existence before creatingbatch_insert(items)— with error checking- Query example matching the use case (nearText / hybrid / bm25)
-
Run
weaviate-schema-revieweragent on the generated code before presenting. -
Save file to appropriate location (infer from project structure or use
src/vector/as default). -
Report generated files and any reviewer findings.
$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.
- 6d ago First seen · 49 lines · 48 tokens per session scan A 02cd312381dc
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.
Other commands, from other repositories
ingest
Manually add knowledge to the Weaviate store.
laravel-vector-search
Add semantic/vector search with pgvector (Laravel 13+); use the laravel:vector-search skill exactly as written.
vector-search
Generate Oracle Database 23ai Vector Search implementation.
vector.batch_exists
Check existence for multiple vector keys.
vector.batch_upsert
Upsert multiple vectors in one itemwise batch.
vector.batch_delete
Delete multiple vectors by key.