search

search is a command for coding agents from cwensel/arcaneum. It costs 3 tokens per session (581 once invoked), scanned A, original, MIT.

A command that searches content collections by meaning or by exact keywords.

In plain words
What is it for?
Use semantic search for concepts such as authentication logic, or full-text search for an exact term or code fragment.
Why use it?
It helps find relevant information across indexed documents and code without opening files one by one.

Command

Part of the arc plugin — 5 skills, 10 commands shipped together

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/cwensel/arcaneum/search
Clone the repo
git clone --depth 1 https://github.com/cwensel/arcaneum

Or install arc, the plugin that ships this one along with the rest of its 5 skills, 10 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/cwensel/arcaneum/search.svg)](https://agentmods.dev/commands/cwensel/arcaneum/search)
Your own site
<a href="https://agentmods.dev/commands/cwensel/arcaneum/search"><img src="https://agentmods.dev/badge/commands/cwensel/arcaneum/search.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 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 $0.00003 $0.00581
Opus 5 $0.00002 $0.00291
Sonnet 5 $0.00001 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 4d ago against content hash e133bcead48c, 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.

commands/search.md · 92 lines

What it actually says

Search your indexed content using semantic search (most common) or full-text search.

Quick Start - Most Common Usage:

arc search semantic "your query here" --corpus CorpusName

IMPORTANT: The subcommand (semantic or text) comes BEFORE the query.

Subcommands (required):

  • semantic: Vector-based semantic search (Qdrant)
  • text: Keyword-based full-text search (MeiliSearch)

Examples:

# Semantic search (most common)
/arc:search semantic "identity proofing" --corpus Standards
/arc:search semantic "authentication logic" --corpus MyCode --limit 5

# Multi-corpus search
/arc:search semantic "authentication" --corpus Code --corpus Docs

# Full-text keyword search
/arc:search text "def authenticate" --corpus MyCode

Common Options:

  • --corpus: Corpus/collection to search (can specify multiple times)
  • --limit: Number of results to return (default: 10)
  • --offset: Number of results to skip for pagination (default: 0)
  • --filter: Metadata filter (key=value or JSON)
  • --json: Output in JSON format
  • --verbose: Show detailed information

Semantic Search Options:

  • --vector-name: Vector name (auto-detected if not specified)
  • --score-threshold: Minimum similarity score

Execution:

arc search $ARGUMENTS

When to Use Each:

Semantic Search (vector-based):

  • Finding conceptually similar code/documents
  • Cross-language semantic matching
  • "What does this" or "How to" questions
  • Fuzzy concept matching

Full-Text Search (keyword-based):

  • Exact keyword or phrase matching
  • Function/variable name search
  • Quoted phrase search
  • Boolean operators (AND, OR, NOT)

Result Format:

Both commands show:

  • Relevance score (similarity for semantic, rank for text)
  • Source file path
  • Matching content snippet
  • Metadata (git info for code, page numbers for PDFs)

Related Commands:

  • /arc:corpus create - Create corpus for dual indexing (recommended)
  • /arc:corpus sync - Index content to both systems
  • /arc:corpus list - List available corpora
  • /arc:collection list - See available collections (semantic only)

Implementation:

  • RDR-007: Semantic search via Qdrant
  • RDR-012: Full-text search via MeiliSearch
  • RDR-006: Claude Code integration
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 · 92 lines · 3 tokens per session scan A e133bcead48c

Subscribe to this mod's changes

search is a command published in the GitHub repository cwensel/arcaneum (7 stars, last pushed 8d ago), licensed MIT. It adds 3 tokens to every session and 581 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 2026-08-31.