taiwan-data-hub: Instructions file for Claude Code

CLAUDE.md

taiwan-data-hub CLAUDE.md is an instructions file for Claude Code from hydai/taiwan-data-hub. It costs 4,296 tokens per session, scanned B, original, Apache-2.0.

Project memory and instructions for Taiwan Data Hub, an open-source service that collects Taiwan public data and makes it available to AI agents through the Model Context Protocol.

In plain words
What is it for?
Use them when planning or implementing this service, especially its Rust backend, Svelte frontend, data systems, authentication, and Docker deployment.
Why use it?
They preserve important project context, pinned technology versions, repository layout, and known mistakes to avoid across coding sessions.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is hydai/taiwan-data-hub's own configuration. It tells Claude Code how to work on taiwan-data-hub 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 taiwan-data-hub configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hydai/taiwan-data-hub. 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/hydai/taiwan-data-hub/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hydai/taiwan-data-hub

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 taiwan-data-hub CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hydai/taiwan-data-hub/claude-md.svg)](https://agentmods.dev/instructions/hydai/taiwan-data-hub/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hydai/taiwan-data-hub/claude-md"><img src="https://agentmods.dev/badge/instructions/hydai/taiwan-data-hub/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,296 This file is loaded in full into every session.
When invoked 4,296 The same file — it is already loaded in full.
Security scan B 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 $0.04296 $0.04296
Opus 5 $0.02148 $0.02148
Sonnet 5 $0.00859 $0.00859
Haiku 4.5 $0.00430 $0.00430

Measured 8d ago against content hash 04985dd1047f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

taiwan-data-hub CLAUDE.md scanned grade B 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

A PreToolUse hook in `~/.claude/settings.json` auto-runs these before `git commit`.
CLAUDE.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Project memory for Taiwan Data Hub

Per-project guidance for Claude Code (and any agentic coding assistant) working in this repository. Loaded into every Claude session — keep short and high-signal.

Project context

Taiwan Data Hub is a fully open-source, self-hostable MCP (Model Context Protocol) service hub that aggregates Taiwan public data sources and exposes them to AI agents like Claude Desktop, Cursor, and Cline.

  • Status: pre-alpha · design phase (no implementation code yet)
  • License: Apache-2.0
  • Canonical design: docs/DESIGN.md — read this first
  • Roadmap: Project #2 · 80 sub-issues across 9 milestones
  • MVP (v0.1) = M0 + M1 + M2 → 28 P0 issues

Tech stack (versions pinned as of 2026-05-18)

Layer Stack
Backend Rust · axum 0.8.8 · sqlx 0.8.6 · polars 0.53 · rmcp 1.7
Frontend SvelteKit 2.59 · Svelte 5.55 (Runes) · Tailwind 4.3 (CSS-first) · shadcn-svelte 1.2
Data PostgreSQL 18 (UUIDv7) · Parquet · SeaweedFS (S3-compat) · DragonflyDB · Meilisearch 1.15
Spec MCP 2025-11-25 · OAuth 2.1 + PKCE · OpenAPI 3.1 (utoipa 5.5)
Deploy Docker Compose (profiles: default / full / obs / dev) · Caddy 2.11

Full version table and rationale: docs/DESIGN.md §5.

Critical gotchas (do NOT copy from old examples)

These libraries had breaking changes within the last 12 months. Always check versions before copy-pasting from blog posts or AI training data:

  1. axum 0.8 — path syntax /:id panics at startup; use /{id}.
  2. Tailwind v4 — no tailwind.config.js; use @theme block in CSS, @import "tailwindcss", plugin @tailwindcss/postcss. shadow renamed: shadow-smshadow-xs.
  3. Svelte 5 Runes — use $state / $derived / $effect / $props; never $: or export let.
  4. rmcp 1.x — not 0.x; trait signatures and imports changed completely.
  5. utoipa 5.x — use OpenApiRouter, OpenAPI 3.1 schema paths.
  6. oauth2 / openidconnect 5.x — async client now trait-based.
  7. thiserror 2.0 — most cases rebuild fine; check changelog for #[backtrace].
  8. Paraglide-JS v2 — API renamed: getLocale() / setLocale() / locales (NOT languageTag() / availableLanguageTags); server middleware moved to server.js as paraglideMiddleware.
  9. MapLibre GL v5 — style spec & worker config changed.
  10. echarts v6 — v5 → v6 not fully compatible; do NOT use svelte-echarts (stale 1.0.0); write a 30-line wrapper.
  11. MinIO is archived (2026-04-25) — use SeaweedFS or Garage instead.
  12. PostgreSQL 18 — has native uuidv7(); prefer over manual UUID generation for sortable ids.

Read the full file on GitHub · 392 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 · 392 lines · 4,296 tokens per session scan B 04985dd1047f

Subscribe to this mod's changes

taiwan-data-hub CLAUDE.md is an instructions file published in the GitHub repository hydai/taiwan-data-hub (1 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 4,296 tokens to every session, about $0.0215 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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