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/weaviate/agent-skills/importgit clone --depth 1 https://github.com/weaviate/agent-skillsWhat 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 | $0.00017 | $0.00948 |
| Opus 5 | $0.00009 | $0.00474 |
| Sonnet 5 | $0.00003 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade B, and why
import scanned grade B with 1 finding 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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Ubuntu/Debian: `sudo apt-get install poppler-utils` How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import Data
Import one or more CSV, JSON, JSONL, or PDF files into a Weaviate collection with automatic type conversion. Multiple files of the same format can be passed in a single invocation.
Usage
/weaviate:import file "data.csv" collection "CollectionName"
/weaviate:import file "data.csv" collection "CollectionName" mapping '{"src_col": "prop"}'
/weaviate:import file "document.pdf" collection "PDFDocuments"
/weaviate:import file "a.csv extra.jsonl" collection "CollectionName" skip-fields "id"
Workflow
-
CSV / JSON / JSONL — collection must already exist. Create one first with
/weaviate:collectionsif needed.uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py FILE --collection "CollectionName" -
PDF — collection is created automatically on first run (multimodal schema with
ModernVBERT/colmodernvbert); subsequent runs append to it.uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py FILE.pdf --collection "CollectionName" -
With mapping (rename columns to match property names):
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py FILE --collection "CollectionName" \ --mapping '{"old_col": "new_prop"}' -
Skip reserved fields (
id,_additionalcause failures — drop or rename them):uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py FILE --collection "CollectionName" \ --skip-fields "id" -
Multi-tenant collection:
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py FILE --collection "CollectionName" \ --tenant "tenant1" -
Multiple files — same format:
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py a.csv b.csv c.csv \ --collection "CollectionName" -
Multiple files — mixed formats (CSV, JSON, and JSONL can be freely combined as long as their properties match the collection schema):
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/import.py records.csv extra.jsonl patch.json \ --collection "CollectionName"PDFs cannot be mixed with CSV/JSON/JSONL — import them in a separate run.
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.
- 3d ago First seen · 98 lines · 17 tokens per session scan B 9bd89e5ba02d
import is a command published in the GitHub repository weaviate/agent-skills (103 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 17 tokens to every session and 948 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
bucket-vector
Performs vector similarity search on a bucket using a vector index backed by JVector, with optional post-filtering to combine similarity ranking with structured query predicates.
rag-publish-requirements
Command "rag-publish-requirements" from lucky-aeon/AgentX, covering rag 发布功能需求规划, 1. 核心设计原则, 1.1 快照机制设计, 1.2 审核机制设计 and 2. 数据库设计.
corpus
Manage dual-index corpora (recommended).
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.