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/fetchgit 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 | $0.00009 | $0.00568 |
| Opus 5 | $0.00005 | $0.00284 |
| Sonnet 5 | $0.00002 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
fetch 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 2d 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
Fetch and Filter Objects
Fetch specific objects by ID or filter them using complex logic (AND/OR). Always use this command after exploring the collection using /weaviate:explore command.
Usage
/weaviate:fetch collection "CollectionName" filters '{"property": "prop", "operator": "equal", "value": "val"}'
/weaviate:fetch collection "CollectionName" id "UUID"
Workflow
-
Fetch by ID:
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/fetch_filter.py "COLLECTION_NAME" --id "UUID" -
Fetch with Filters:
uv run ${CLAUDE_PLUGIN_ROOT}/skills/weaviate/scripts/fetch_filter.py "COLLECTION_NAME" --filters 'JSON_STRING' --limit 10
Filter Syntax
Filters must be a JSON string.
Simple Filter:
[{"property": "category", "operator": "equal", "value": "Science"}]
OR Logic:
{
"operator": "or",
"filters": [
{"property": "word_count", "operator": "greater_than", "value": 1000},
{"property": "title", "operator": "like", "value": "*Research*"}
]
}
Complex Nesting:
{
"operator": "and",
"filters": [
{"property": "is_published", "operator": "equal", "value": true},
{
"operator": "or",
"filters": [
{"property": "author", "operator": "equal", "value": "Jane Doe"},
{"property": "views", "operator": "greater_than", "value": 5000}
]
}
]
}
Operators
equal,not_equalless_than,less_or_equalgreater_than,greater_or_equallike(use*for wildcards)contains_any,contains_all(value must be a list)is_none(value must be boolean)
Environment
Requires:
WEAVIATE_URL: Weaviate Cloud cluster URLWEAVIATE_API_KEY: API key for authentication
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.
- 2d ago First seen · 81 lines · 9 tokens per session scan A 15bd8b2ea13d
fetch is a command published in the GitHub repository weaviate/agent-skills (103 stars, last pushed 2mo ago), licensed BSD-3-Clause. It adds 9 tokens to every session and 568 once invoked, about $0.0000 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.
Other commands, from other repositories
ai-pipeline
RAG/embedding pipeline scaffolding — delegates to ai-data-engineer agent.
agent-brain-index
Index documents for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
status
Show index status including document counts, vector counts, and embedding configuration.
ingest
Manually add knowledge to the Weaviate store.
build-search-index
Build or refresh a vault's LOCAL BM25 search index (wiki-meta/search-index.json) — a deterministic, plugin-free search tier that works on every vault, including those without Smart Connections. Idempotent (fingerprint check → no rewrite). (Skill build-search-index handles natural-language triggers.).