vault-semantic-search

vault-semantic-search is a skill for Claude Code, Codex from allenhutchison/obsidian-gemini. It costs 44 tokens per session (757 once invoked), scanned A, original, MIT.

A meaning-based search skill for finding information across a collection of notes. It uses semantic search, which looks for related ideas rather than requiring the exact words to appear.

In plain words
What is it for?
It helps discover notes about a concept, gather related information across a vault, and search by natural-language questions.
Why use it?
It helps when you remember a topic but not the wording or filename used in your notes. This can find relevant material when ordinary keyword search misses it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps discover notes about a concept, gather related information across a vault, and search by natural-language questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/allenhutchison/obsidian-gemini/vault-semantic-search
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.

Any agent
npx skills add allenhutchison/obsidian-gemini --skill vault-semantic-search
Clone the repo
git clone --depth 1 https://github.com/allenhutchison/obsidian-gemini

Made for: Claude Code, Codex.

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 vault-semantic-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/vault-semantic-search/github.svg)](https://agentmods.dev/skills/allenhutchison/obsidian-gemini/vault-semantic-search)
Your own site
<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/vault-semantic-search"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/vault-semantic-search/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 vault-semantic-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/vault-semantic-search"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/vault-semantic-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 757 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.00757
Opus 5 $0.00022 $0.00378
Sonnet 5 $0.00009 $0.00151
Haiku 4.5 $0.00004 $0.00076

Measured 12d ago against content hash a6d35c8e2d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vault-semantic-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 12d 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.

prompts/bundled-skills/vault-semantic-search/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find vault content by meaning rather than exact keywords using the vault_semantic_search tool. This uses RAG (Retrieval-Augmented Generation) to search indexed vault files semantically.

Use vault_semantic_search when... Use keyword tools (search_vault) when...
The user asks about concepts or topics The user wants an exact filename or string
The query is "find notes about..." or "what do I have on..." The query is "find the file called..."
The user doesn't remember exact words The user knows the exact term to search
You need to discover related content across the vault You need to find a specific known file
Keyword search returned poor or no results You know the exact path or filename

Try semantic search first for concept-based queries. Fall back to keyword tools if semantic search isn't available or returns insufficient results.

How to Use

Call the vault_semantic_search tool with these parameters:

  • query (required) — The search question, topic, or concept. Natural language queries work best.
  • maxResults (optional) — Number of results to return, 1-20. Default is 5. Increase for broad surveys.
  • folder (optional) — Limit results to files within a specific folder path.
  • tags (optional) — Filter results by Obsidian tags. Uses OR logic — any matching tag qualifies.

Search Strategies

  • Broad discovery — Use a conceptual query with higher maxResults (10-15): vault_semantic_search("project management methodologies", maxResults=10)
  • Focused search — Narrow with folder when the user mentions a specific area: vault_semantic_search("meeting notes about budget", folder="Work/Meetings")
  • Tag-filtered search — Use tags when the user references tagged content: vault_semantic_search("design patterns", tags=["programming", "architecture"])
  • Follow-up reading — After finding relevant results, use read_file on promising matches to get full note content

Read the full file on GitHub · 57 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. 12d ago First seen · 57 lines · 44 tokens per session scan A a6d35c8e2d1d

Subscribe to this mod's changes

vault-semantic-search is a skill published in the GitHub repository allenhutchison/obsidian-gemini (524 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 757 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 2026-08-30.