loxone-datamanager: Instructions file for Claude Code

CLAUDE.md

loxone-datamanager CLAUDE.md is an instructions file for Claude Code from andileeb/loxone-datamanager. It costs 2,691 tokens per session, scanned A, original, MIT.

Instructions for Loxone DataManager, a desktop app for viewing and editing statistics from a Loxone Miniserver, a home-automation controller. The app downloads binary monthly files over FTP or FTPS, lets users change them, and uploads them again.

In plain words
What is it for?
Use them when developing, testing, building, or releasing the Electron and Vue application, especially its file parsing and FTP features.
Why use it?
They give coding agents the project’s required commands, architecture, file-handling boundaries, testing expectations, and release details.

Instructions file for Claude Code

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

This is andileeb/loxone-datamanager's own configuration. It tells Claude Code how to work on loxone-datamanager 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 loxone-datamanager configures →

Reuse

Borrowing it

Nothing to install: this file belongs to andileeb/loxone-datamanager. 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/andileeb/loxone-datamanager/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/andileeb/loxone-datamanager

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 loxone-datamanager CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andileeb/loxone-datamanager/claude-md.svg)](https://agentmods.dev/instructions/andileeb/loxone-datamanager/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andileeb/loxone-datamanager/claude-md"><img src="https://agentmods.dev/badge/instructions/andileeb/loxone-datamanager/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,691 This file is loaded in full into every session.
When invoked 2,691 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02691 $0.02691
Opus 5 $0.01345 $0.01345
Sonnet 5 $0.00538 $0.00538
Haiku 4.5 $0.00269 $0.00269

Measured 8d ago against content hash a3c2697c5066, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

loxone-datamanager CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -X POST http://127.0.0.1:12009/mcp -H "Authorization: Bearer <token>" …`
CLAUDE.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Loxone DataManager

Electron desktop app (100% TypeScript) to view and edit Loxone Miniserver statistics: browse /stats via FTP/FTPS, chart/edit the binary monthly files, upload them back. Heavily inspired by LoxStatEdit (Windows/.NET). User-facing docs live in README.md; this file is for working on the code.

Commands (pnpm only — packageManager is pinned)

pnpm install          # pnpm 10: build scripts allowlisted via pnpm.onlyBuiltDependencies
pnpm run dev          # Electron + Vue with HMR
pnpm test             # vitest: parser round-trip, validation, formula, FTP date parsing
pnpm run build        # typecheck (node + web) + electron-vite build
pnpm run lint         # eslint + prettier rules
pnpm run build:mac    # package .dmg (build:win / build:linux)

Release: push a v* tag → .github/workflows/release.yml builds macOS universal .dmg + Windows NSIS setup.exe (unsigned) and drafts a GitHub Release.

Architecture

  • src/main/ — Node/Electron main process. ALL FTP + file I/O lives here.
    • ftp.ts — one basic-ftp Client in a module singleton; every op serialized through a promise queue (run()) with one auto-reconnect retry; TLS auto-detect = try FTPS (secure: true, rejectUnauthorized: false — Miniserver certs are self-signed) then fall back to plain. LIST dates have no year → parseListDate heuristic (assume this year unless future).
    • statfile.ts — binary parser/serializer, pure TS, no Electron imports (unit-testable). See "Binary format" below.
    • cache.ts — per-host download cache in userData/stats-cache/<host>/. cachePath() validates names against STAT_FILENAME_RE (path-traversal guard).
    • store.ts — saved connections: plain JSON in userData + passwords encrypted with Electron safeStorage (no keychain → password simply not stored).
    • stats-service.ts — shared session logic for IPC and MCP so they can't diverge: CodedError/toApiError, the parsedFiles Map (serialization re-emits the original header bytes verbatim), saveRecords, buildCsv, MCP-side dirty tracking.
    • ipc.ts — all handlers, thin over stats-service. Every response is IpcResult<T> = {ok,data}|{ok,error} with typed ApiError.code (e.g. FTP_REFUSED triggers the "enable FTP" hint in the UI).
    • mcp.ts + mcp-tools.ts — embedded MCP server (@modelcontextprotocol/sdk v1, stateless Streamable HTTP: fresh McpServer + transport per POST) on http://127.0.0.1:<port>/mcp, default port 12009. Bearer-token auth (token generated in Settings, safeStorage-encrypted in store.ts, plain: prefix fallback); 20 tools + fix-statistics prompt share ftp/cache/stats-service with the UI. Edits are in-memory until save_stat_file; mcp:activity events tell the renderer to refresh (EditorView shows a reload banner — last-save-wins, no merging). Lifecycle: start on app ready if enabled, mcp:configure IPC restarts, EADDRINUSE lands in McpState.error.
    • updates.ts — release-notification only, no Electron imports (takes the current version as an argument, so it unit-tests). One fetch of GitHub's /releases/latest per launch; every failure (offline, 403 rate-limit, no published release) resolves as latest: null — a failed check must never surface as an app error. See "Auto-update" below for why there's no installer.
  • src/preload/index.ts — contextBridge exposing window.api, typed by the single contract interface in src/shared/api.ts (preload implements it, renderer consumes it — extend the interface first when adding IPC).
  • src/shared/ — types + time.ts (Loxone epoch helpers, multi-format timestamp parsing) + formula.ts (hand-rolled CSP-safe parser) + records.ts (pure record transforms: dominantInterval, fillGaps, summarizeRecords, statusOf, isCurrentMonth — used by the editor store AND the MCP tools; put new record logic here, not in a Pinia action).
  • src/renderer/src/ — Vue 3 + Pinia + PrimeVue 4 + uPlot + vue-i18n. Views: Connection → Browser (file list w/ sync status) → Editor (chart + virtualized grid + problems panel), plus Settings (Cmd/Ctrl+, or gear icon). Router guard: everything except /connect and /settings needs a connection.
  • i18n: en + de catalogs in renderer/src/locales/ (de.ts is typed typeof en so missing keys fail typecheck). ALL user-facing strings go through t(); error codes map to errors.* keys via errorText() in i18n.ts; validation problems translate by rule code in ProblemsPanel. Main-process messages stay English (fallback only).
  • Prefs (renderer/src/prefs.ts, localStorage): date format (default DD.MM.YYYY) + time format (default 24h for every language — never let a locale silently switch to AM/PM). Editor-grid timestamps always render 24h so they stay parseable; displayToLox accepts all three date formats by separator. Theme lives in renderer/src/theme.ts (.app-dark class = PrimeVue darkModeSelector; chart palette watches isDark).

Read the full file on GitHub · 155 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. 8d ago First seen · 155 lines · 2,691 tokens per session scan A a3c2697c5066

Subscribe to this mod's changes

loxone-datamanager CLAUDE.md is an instructions file published in the GitHub repository andileeb/loxone-datamanager (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,691 tokens to every session, about $0.0135 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens