What is mini-taiwan-pulse CLAUDE.md?

Development rules for Mini Taiwan Pulse, a React and TypeScript map application using Vite, Mapbox GL, Three.js, and Supabase. It also describes project memory files and commands for development, type checking, testing, and adding map layers.

Use it when adding map layers, checking TypeScript, running tests or the development server, inspecting RPC performance, or consulting recorded project pitfalls.

It records local rules that may differ from general React practice, including required validation and data-access boundaries.

How ianlkl11234s/mini-taiwan-pulse configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ianlkl11234s/mini-taiwan-pulse. 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/ianlkl11234s/mini-taiwan-pulse/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ianlkl11234s/mini-taiwan-pulse

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/ianlkl11234s/mini-taiwan-pulse/claude-md/github.svg)](https://agentmods.dev/instructions/ianlkl11234s/mini-taiwan-pulse/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ianlkl11234s/mini-taiwan-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/ianlkl11234s/mini-taiwan-pulse/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/ianlkl11234s/mini-taiwan-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/ianlkl11234s/mini-taiwan-pulse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,764 This file is loaded in full into every session.

When invoked 2,764 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	$0.02764	$0.02764
Opus 5.5	$0.01106	$0.01106
Sonnet 5.5	$0.00553	$0.00553
Haiku 4.5	$0.00276	$0.00276

Measured yesterday against content hash aad2996cd3b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mini-taiwan-pulse 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 yesterday.

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 · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mini Taiwan Pulse — 開發規則

React 19 + TypeScript + Vite (port 3721) · Mapbox GL + Three.js · Supabase (gis-platform)

詳細版規則見 docs/development-rules.md

與全域準則的優先級：全域 ~/.claude/CLAUDE.md 已含通用開發準則（Think Before Coding / Simplicity / Surgical / Goal-Driven）；本檔為專案具體化規則，衝突時以下方為準（特別是 Simplicity 對「新增 Layer 7 步驟 + UX 四鐵則」、Surgical 對「跨檔 register 多處」的例外）。不確定算不算違反專案鐵則時，先問用戶。

Session 記憶迴圈

主題經驗總集（踩坑、best practice、網站哲學、小實驗）先看 docs/LESSONS.md，新教訓寫進正本後在那裡加一行。SessionStart hook 只提供短路由，不預載 STATUS／BACKLOG／PRINCIPLES。有接手需求才依 .claude/memory/README.md 查相關段落；似曾相識的 bug 搜 .claude/pitfalls/。明確收尾時依 wrap-up 的 scope/evidence/release matrix 留本次紀錄，提交／發布沿用各自授權。框架機制按需查 .claude/FRAMEWORK.md。

常用指令

指令	用途
`npm run dev`	啟動 dev server (port 3721)
`npm run check`	commit／PR 前必跑：依序跑 CI 的全部檢查（lint、build、test、樣式盤點、coral）
`npm run lint`	只跑 ESLint 守門規則（自訂規則見 development-rules §6）；修掉既有違規後跑 `npm run lint:prune`
`npx tsc -b`	TypeScript 驗證（禁用 `--noEmit`）
`npm test`	跑測試（含 `layerConsistency` 擋漏接圖例；owner-local 測試用 `npm run test:owner`）
`/new-layer <name>`	新增 layer 骨架（強烈建議走，免漏 manifest/spec/邏輯檔三步 + 四鐵則）
`/check-rpc <name>`	自動 EXPLAIN 判斷 RPC 效能

必守規則

1. TypeScript 驗證

commit 前必跑 npm run check（與 CI 同一組檢查，其中 build 含 tsc -b；project references，禁用 --noEmit）。

2. 資料來源管理

資料來源契約（動態走 public.* RPC / Statistics 一律走 R2 snapshot / 靜態走 CDN 資產 / 禁前端直打 live.*（舊 realtime schema 已併入 live））→ docs/development-rules.md §1

統計新增／整合／UI 調整另見統計圖層規則：配色與 icon 使用共用規則，保留來源語意，同步補齊資料來源總覽，包含原始與衍生選項。

3. 資料載入必須有 Loading UI ⚠️

所有非同步載入必註冊 loadingRegistry，禁靜默 .rpc().then() → development-rules §2

4. 資料庫優化（Pre-aggregate Pattern）

RPC >1s 或 >10k rows 必套 pre-aggregate → docs/supabase-optimization.md + /supabase-optimize skill + /check-rpc

Read the full file on GitHub · 118 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.

yesterday Changed · +1 lines · +37 tokens per session aad2996cd3b3
14d ago Changed · +20 tokens per session 49226eb8e546
19d ago Changed · +2 lines · +116 tokens per session ba19de8da0f0
21d ago Changed · +1 lines · +136 tokens per session de69ab0a642b
1mo ago Changed · +15 tokens per session c84549f326af
1mo ago Changed 74bbbf114830
1mo ago Changed · +2 lines · +154 tokens per session 912b59744ffc
1mo ago Changed · +2 tokens per session 76d1b05d29eb
1mo ago Changed · +3 lines · +115 tokens per session 39e8cd2a0b96
1mo ago First seen · 109 lines · 2,169 tokens per session scan A c6ab7ed3405a

Subscribe to this mod's changes

mini-taiwan-pulse CLAUDE.md is an instructions file published in the GitHub repository ianlkl11234s/mini-taiwan-pulse (543 stars, last pushed yesterday), licensed MIT. It adds 2,764 tokens to every session, about $0.0111 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 2026-08-30.

mini-taiwan-pulse CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mini-taiwan-pulse CLAUDE.mdianlkl11234s/mini-taiwan-pulse	Instructions file	543	yesterday	MIT	A	2,764	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	today	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

mini-taiwan-pulse: Instructions file for Claude Code