What is mcp-arango-mind CLAUDE.md?

A set of instructions for working on the mcp-arango-mind codebase, including its master, release and async worktrees. A worktree is a separate working copy of a Git repository.

Use it when developing mcp-arango-mind, especially when deciding which files to read, which worktree to change and how the MCP interface connects to ArangoDB.

It helps the coding agent edit the intended copy and consult the project's documented source of truth before changing behaviour. It also records the current runtime tools and project status.

How woolkingx/mcp-arango-mind configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to woolkingx/mcp-arango-mind. 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/woolkingx/mcp-arango-mind/release/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/woolkingx/mcp-arango-mind

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/instructions/woolkingx/mcp-arango-mind/claude-md/github.svg)](https://agentmods.dev/instructions/woolkingx/mcp-arango-mind/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/woolkingx/mcp-arango-mind/claude-md"><img src="https://agentmods.dev/badge/instructions/woolkingx/mcp-arango-mind/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/woolkingx/mcp-arango-mind/claude-md"><img src="https://agentmods.dev/badge/instructions/woolkingx/mcp-arango-mind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,202 This file is loaded in full into every session.

When invoked 1,202 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.

Model	Per session	Once invoked
Fable 5.1	$0.01202	$0.01202
Opus 5.5	$0.00481	$0.00481
Sonnet 5.5	$0.00240	$0.00240
Haiku 4.5	$0.00120	$0.00120

Measured 2mo ago against content hash eeb457889d1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-arango-mind 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 2mo 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-arango-mind Master Worktree

This file is the local boot card for the master worktree. It is not the architecture handbook.

Worktree Role

master/ is the development source of truth.
release/ is the published remote-synced line.
async/ is the currently used older implementation line and may contain unrelated dirty work.
Do not edit release/ or async/ while working on master/ unless the user explicitly redirects the target.

Source Of Truth

Read in this order before changing behavior:

docs/handbook/index.html
docs/plan/*.md
mcp/schema/*.json, tools/schema/*.json, arango/schema/*.json, config/*.json
src/**/*.mjs
tests/*.test.mjs

The handbook owns architecture, boundaries, acceptance gates, and known risks. README.md is a public quick entrypoint only.

Current Status

Date: 2026-05-23.
Current runtime tools: mcp.mcp, mcp.help, mcp.arango, mcp.tool.template, mcp.tool.database, mcp.tool.collection, mcp.tool.view, mcp.tool.graph, mcp.tool.admin, mcp.tool.atlas.
Current master topology: MCP interface -> current tool runtime -> ArangoDB API owner.
Handbook target topology: MCP interface -> surface root -> tool owners -> ArangoDB API owner.
Target MCP-visible surfaces are documented as mcp.mcp, mcp.help, mcp.arango, and mcp.tool.*.
Tool categories are documented as mcp.tool.database, mcp.tool.collection, mcp.tool.view, mcp.tool.graph, mcp.tool.admin, mcp.tool.template, and mcp.tool.atlas.
Target surface split (mcp.mcp, mcp.arango, mcp.tool.*) is fully landed across schema, runtime, tests, and docs.
Five mcp.tool.* category owners share src/tool-category-owner.mjs with per-category OpenAPI tag whitelists; template and atlas keep dedicated handlers.

Next Work

The target surface taxonomy is now realised. Pending items live in handbook risk and roadmap chapters:

Live ArangoDB integration tests per mcp.tool.<cat> owner (env-gated under ARANGO_URL).
Mature template catalog (port more async templates as needed).
Decide on mcp.tool.admin scope expansion (currently 4 tags; Replication/Cluster/Users/etc. wait for explicit need).

Read the full file on GitHub · 72 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.

2mo ago First seen · 72 lines · 1,202 tokens per session scan A eeb457889d1b

Subscribe to this mod's changes

mcp-arango-mind CLAUDE.md is an instructions file published in the GitHub repository woolkingx/mcp-arango-mind (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,202 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.

arangodb mcp model-context-protocol nodejs openapi schema-driven

mcp-arango-mind CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-arango-mind CLAUDE.mdwoolkingx/mcp-arango-mind	Instructions file	0	5mo ago	MIT	A	1,202	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-arango-mind: Instructions file for Claude Code