agentmods.dev

search

search is a command for coding agents from weaviate/agent-skills. It costs 14 tokens per session (432 once invoked), scanned A, original, BSD-3-Clause.

A command for searching a Weaviate collection, which is a stored group of data items such as articles or products. It supports meaning-based, exact-word, or combined searches.

In plain words
What is it for?
Use it to find relevant articles, products, or other records in Weaviate. You can choose the search type and limit the number of results.
Why use it?
It avoids writing separate search code for different kinds of queries. It also helps when you need to search data by meaning instead of only matching exact words.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agent-skills plugin — 2 skills, 9 commands shipped together

not rated 104 2mo ago A scan 14 tokens original BSD-3-Clause
View the source file weaviate/agent-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.

agentmods
npx agentmods add commands/weaviate/agent-skills/search
Clone the repo
git clone --depth 1 https://github.com/weaviate/agent-skills

Or install agent-skills, the plugin that ships this one along with the rest of its 2 skills, 9 commands.

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 search

README.md
[![agentmods](https://agentmods.dev/badge/commands/weaviate/agent-skills/search.svg)](https://agentmods.dev/commands/weaviate/agent-skills/search)
Your own site
<a href="https://agentmods.dev/commands/weaviate/agent-skills/search"><img src="https://agentmods.dev/badge/commands/weaviate/agent-skills/search.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 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00432
Opus 5 $0.00007 $0.00216
Sonnet 5 $0.00003 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured 4d ago against content hash 5609460c07cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search 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 4d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • search — 94% identical, 1 lines differ
commands/search.md · 56 lines

What it actually says

Search Weaviate

Perform hybrid, semantic, or keyword search on a collection.

Usage

/weaviate:search query "your query" collection "CollectionName" [type "hybrid"] [alpha "0.5"] [limit "10"]

Workflow

When necessary, use AskUserQuestion to make entering arguments easier.

  1. Parse arguments
  2. If collection is missing:
    • Run /weaviate:collections to list available collections
    • Use AskUserQuestion to prompt user to select
  3. If type is not specified, default to hybrid
  4. Run the appropriate script based on type:

Hybrid (default)

uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/hybrid_search.py --query "USER_QUERY" --collection "COLLECTION_NAME" --alpha 0.7 --limit 10

Semantic

uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/semantic_search.py --query "USER_QUERY" --collection "COLLECTION_NAME" --limit 10

Keyword

uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/keyword_search.py --query "USER_QUERY" --collection "COLLECTION_NAME" --limit 10

Examples

/weaviate:search query "machine learning" collection "Articles"
/weaviate:search query "SKU-12345" collection "Products" type "keyword"
/weaviate:search query "similar concepts" collection "Documents" type "semantic"

Environment

Requires:

  • WEAVIATE_URL: Weaviate Cloud cluster URL
  • WEAVIATE_API_KEY: API key for authentication
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. 4d ago First seen · 56 lines · 14 tokens per session scan A 5609460c07cf

Subscribe to this mod's changes

search is a command published in the GitHub repository weaviate/agent-skills (104 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 14 tokens to every session and 432 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.

Data and AIRAG and vectors
Related

Other commands, from other repositories

agent-brain-index

Index documents for semantic search.

SpillwaveSolutions/agent-brain · 10 tokens

agent

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

get-convex/convex-agent-plugins · 21 tokens

rag-publish-todo-list

Command "rag-publish-todo-list" from lucky-aeon/AgentX, covering rag 发布功能 todo list, 阶段一：数据库设计和基础架构 🗄️ ✅ 已完成, 1. 数据库表创建, 2. 领域层实现 and 3. 基础领域服务.

lucky-aeon/AgentX · 0 tokens

ingest

Manually add knowledge to the Weaviate store.

Galbaz1/video-research-mcp · 10 tokens

rag-retrieval

RAG pipeline patterns for grounded LLM responses. Use when building a Q&A system, adding citations, implementing a knowledge base, or preventing hallucinations. Triggers on RAG, retrieval augmented, knowledge base, Q&A pipeline, citations, hybrid search, context retrieval, hallucination prevention.

ArieGoldkin/claude-forge · 58 tokens

refine

Run manual sanity checks on the RAGgrep search system to ensure ranking quality.

conradkoh/raggrep · 0 tokens