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 instructions/cwensel/arcaneum/claude-mdgit clone --depth 1 https://github.com/cwensel/arcaneumWrote 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.
[](https://agentmods.dev/instructions/cwensel/arcaneum/claude-md)<a href="https://agentmods.dev/instructions/cwensel/arcaneum/claude-md"><img src="https://agentmods.dev/badge/instructions/cwensel/arcaneum/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01041 | $0.01041 |
| Opus 5 | $0.00521 | $0.00521 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
arcaneum CLAUDE.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Arcaneum is a CLI tool for semantic and full-text search across Qdrant and MeiliSearch vector databases. It provides Claude Code integration through slash commands and plugins.
This repository uses Recommendation Decisioning Records (RDRs) for detailed technical planning before implementation.
Recommendation Decisioning Records (RDRs)
RDRs are specification prompts built through iterative research and refinement. They evolve during planning and become locked specifications for implementation.
- Location:
docs/rdr/ - Template:
docs/rdr/TEMPLATE.md - Complete guide:
docs/rdr/README.md
When to Use RDRs
Create an RDR for complex implementations, architectural decisions, framework workarounds, or when you want to iterate on an approach before committing to code.
Quick RDR Workflow
- Create (Draft) — Document problem, constraints, technical environment
- Research (Draft) — Investigate, add findings, label as Verified/Documented/Assumed
- Decide (Draft) — Select approach, document rationale, complete Finalization Gate
- Lock (Final) — All gate items answered; RDR is the spec for implementation
- Implement (Final) — Use locked RDR as spec; do not edit during implementation
- Close — Update status; create post-mortem in
docs/rdr/post-mortem/
IMPORTANT: RDRs are immutable once locked (Final). They are specification documents that show what was planned and why. If implementation reveals the RDR is wrong, abandon implementation, iterate on the RDR with lessons learned, and start fresh.
See docs/rdr/README.md for complete RDR workflow, format details, and usage guidelines.
Markdown Files
When creating or modifying markdown files in this project:
- ALWAYS run
markdownlint <file>to validate markdown formatting before completing the task - Fix any linting errors reported by markdownlint
- Follow the project's markdown style guidelines enforced by markdownlint
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.
- 5d ago First seen · 123 lines · 1,041 tokens per session scan A 1d6394c2d7c8
arcaneum CLAUDE.md is an instructions file published in the GitHub repository cwensel/arcaneum (7 stars, last pushed yesterday), licensed MIT. It adds 1,041 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.