agentmods.dev

arcane: Instructions file for Claude Code

CLAUDE.md

arcane CLAUDE.md is an instructions file for Claude Code from Edition-X/arcane. It costs 1,200 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code describe Arcane, a local server that stores and searches engineering memories, decisions, and project artifacts. They also define development and memory-handling practices for this project.

In plain words
What is it for?
Use them when working on Arcane with Claude Code, including saving or finding memories, reviewing decisions, importing CI, Linear, or Git data, and creating blog posts or architecture decision records.
Why use it?
They give the coding agent the project context and working rules it needs to act consistently. They also explain how to use the project's persistent memory instead of losing useful decisions between sessions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is Edition-X/arcane's own configuration. It tells Claude Code how to work on arcane itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything arcane configures →

not rated 0repo changed 13d ago A scan 1,200 tokens original MIT
View source ↗ Edition-X/arcane
Reuse

Borrowing it

Nothing to install: this file belongs to Edition-X/arcane. 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/Edition-X/arcane/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Edition-X/arcane

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.

agentmods badge for arcane CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edition-x/arcane/claude-md/github.svg)](https://agentmods.dev/instructions/edition-x/arcane/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edition-x/arcane/claude-md"><img src="https://agentmods.dev/badge/instructions/edition-x/arcane/claude-md/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 arcane CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/edition-x/arcane/claude-md"><img src="https://agentmods.dev/badge/instructions/edition-x/arcane/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,200 This file is loaded in full into every session.
When invoked 1,200 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01200 $0.01200
Opus 5.5 $0.00480 $0.00480
Sonnet 5.5 $0.00240 $0.00240
Haiku 4.5 $0.00120 $0.00120

Measured 13d ago against content hash 871481245ac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arcane 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 13d 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.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arcane — Project Instructions for Claude Code

What This Project Is

Arcane is a personal engineering memory MCP server. It exposes tools for saving/searching memories, tracking decision journeys, ingesting artifacts from CI/Linear/Git, and generating blog posts or ADRs. The canonical data store is SQLite with FTS5 + sqlite-vec for hybrid search.

MCP Server

The MCP server is the primary interface for AI agents. Run it with:

arcane mcp

It communicates via stdio (JSON-RPC). For Claude Desktop / Claude Code integration, add it to your MCP config:

{
  "mcpServers": {
    "arcane": {
      "command": "arcane",
      "args": ["mcp"]
    }
  }
}

Development Priorities

  • No regressions: always run pytest before committing
  • Type safety: new public functions must have type annotations; run mypy src/arcane after changes
  • DRY: check existing services and repos before adding new logic
  • Test end to end: new tests drive the real arcane mcp server or CLI against a real temp store (tests/e2e/). No mocked unit tests; fake the network only for GitHub, Linear and Ollama (tests/plugins/, tests/unit/test_embeddings.py)

Arcane Memory Discipline (for Claude Code)

Arcane is the persistent memory system for this project. Use it automatically — do not wait to be asked.

At the start of every session

  1. Call memory_context for the current project to load recent decisions, bugs, and context.
  2. If the request references prior work, past decisions, or "last time", call memory_search with task-specific terms.
  3. If the task sounds like an ongoing investigation or spike, call journey_list to find active journeys.

Before researching anything

  • Call memory_search first — the answer may already be stored.

When to save memories (after every git commit)

  • Decision made → memory_save with category: "decision"
  • Bug fixed → memory_save with category: "bug", including root cause and how to recognise it
  • Pattern discovered → memory_save with category: "pattern" or "learning"
  • Milestone shipped → memory_save with category: "milestone"

Read the full file on GitHub · 104 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. 13d ago Changed · -1 lines · +46 tokens per session 871481245ac3
  2. 1mo ago Changed · +1 lines · +35 tokens per session c67e90a99d44
  3. 2mo ago Changed · +1 lines · +41 tokens per session 877e64cb2372
  4. 2mo ago First seen · 103 lines · 1,078 tokens per session scan A dff7763ebb7e

Subscribe to this mod's changes

arcane CLAUDE.md is an instructions file published in the GitHub repository Edition-X/arcane (0 stars, last pushed 12d ago), licensed MIT. It adds 1,200 tokens to every session, about $0.0048 per session on Opus 5.5. 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.

Memory and context
Related

arcane CLAUDE.md compared with instructions from other repositories

arcane CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
arcane CLAUDE.mdEdition-X/arcaneInstructions file012d agoMITA1,200Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode