A search command that first looks for relevant information in a Qdrant vector database and then searches the local codebase if needed. Qdrant is a database for finding text by meaning, while ripgrep-style code search looks for matching file content.

Use it to find related files, explain their relevance, identify key sections or functions, and report similarity or confidence scores when available.

It provides a fallback when the semantic search service is unavailable or does not return enough relevant results.

How tomdwipo/claude-soul configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/search.md

Clone the repo

git clone --depth 1 https://github.com/tomdwipo/claude-soul

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/tomdwipo/claude-soul/search/github.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/search)

Your own site

<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/search"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/search"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 260 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00260
Opus 5	$0.00000	$0.00130
Sonnet 5	$0.00000	$0.00052
Haiku 4.5	$0.00000	$0.00026

Measured 9d ago against content hash 56d4f5a46d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

.claude/commands/search.md · 32 lines

What it actually says

Advanced Search Command

Search and analyze: $ARGUMENTS

Search Strategy (in order of priority):

1. Vector Database Search

Database: Qdrant vector collection ws-99ba28f992cd224e
Model: Ollama
Parameters:
- Limit: 50 results
- Similarity threshold: 0.55

2. Fallback to Codebase Search

If Qdrant MCP server is unavailable or returns insufficient results:

Search local codebase for relevant files
Use pattern matching and content analysis
Focus on files related to the query context

Execution Steps:

Parse Query: Understand what the user is asking for
Vector Search: Query Qdrant database using semantic similarity
Validate Results: Check if results meet relevance threshold
Fallback Search: If needed, search local files using grep/ripgrep
Compile Results: Present the most relevant files and their context

Output Format:

List relevant files found
Include brief description of why each file is relevant
Show confidence/similarity scores where available
Highlight key sections or functions within files

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.

9d ago First seen · 32 lines · 0 tokens per session scan A 56d4f5a46d16

Subscribe to this mod's changes

search is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 260 tokens. 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.

Databases Research

claude-soul: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Advanced Search Command

Search Strategy (in order of priority):

1. Vector Database Search

2. Fallback to Codebase Search

Execution Steps:

Output Format:

What this file has done since we first saw it

Other commands, from other repositories

init

database-setup

ingest

json.batch_delete

json.batch_get

json.index.drop