agentmods.dev

tw-formal-writing: Instructions file for Claude Code

CLAUDE.md

tw-formal-writing CLAUDE.md is an instructions file for Claude Code from Imbad0202/tw-formal-writing. It costs 2,482 tokens per session, scanned B, original, MIT.

A set of instructions for Claude Code in a repository that maintains formal Taiwanese Chinese documents. The repository uses one source folder to generate versions for several AI tools.

In plain words
What is it for?
Use it when editing the repository’s writing rules, rebuilding its standalone document and skills, or checking generated files for consistency.
Why use it?
It explains the repository structure, where content should be edited, and which generation step is required after changing reference files.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Imbad0202/tw-formal-writing's own configuration. It tells Claude Code how to work on tw-formal-writing 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 tw-formal-writing configures →

not rated 169repo +2 changed 4d ago B scan 2,482 tokens original MIT
View source ↗ Imbad0202/tw-formal-writing buymeacoffee.com
Reuse

Borrowing it

Nothing to install: this file belongs to Imbad0202/tw-formal-writing. 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/Imbad0202/tw-formal-writing/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Imbad0202/tw-formal-writing

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 tw-formal-writing CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/imbad0202/tw-formal-writing/claude-md/github.svg)](https://agentmods.dev/instructions/imbad0202/tw-formal-writing/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/imbad0202/tw-formal-writing/claude-md"><img src="https://agentmods.dev/badge/instructions/imbad0202/tw-formal-writing/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 tw-formal-writing CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/imbad0202/tw-formal-writing/claude-md"><img src="https://agentmods.dev/badge/instructions/imbad0202/tw-formal-writing/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,482 This file is loaded in full into every session.
When invoked 2,482 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 $0.02482 $0.02482
Opus 5 $0.01241 $0.01241
Sonnet 5 $0.00496 $0.00496
Haiku 4.5 $0.00248 $0.00248

Measured 4d ago against content hash 445a5b2f9353, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

tw-formal-writing 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 4d 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.

這是公開 repo。動 spec 前先 grep 維護者機構內部的機密字眼（清單見本機 `~/.claude/personal-boundary/deny_list.yaml`，不入庫），命中即停、預設動作是去識別化改寫（既存 public 含某字眼 ≠ 授權重複使用）。推送前確認不含個資（校名、人名、內部 URL）。
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.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

這個 repo 是什麼

一個「內容型」skill，不是程式碼專案。核心產物是中文正式文件撰寫規範（台灣政府公文、政府機關其他文件、法律文件、人民對政府文書四類），以多種入口分發給不同 AI 工具（Claude Code / ChatGPT / Gemini / Codex）。Python 腳本只負責從單一來源組裝各版本、並在 CI gate 一致性。這是 public repo——動任何內容前先讀下方「Public repo 紀律」。

內容架構：單一真實來源 → 多入口

規範的唯一真實來源是 references/。所有對外版本都從它衍生，改規範一律改 references/，不要直接編對外檔。

references/              ← SSOT（唯一手動編輯處）
  _header.md               類別判斷 / 三個把關 / 共通原則 / 互動流程（STANDALONE 的頭部）
  official-letter.md       類別1 政府公文（《公文程式條例》《文書處理手冊》）
  terminology-tables.md    公文用語詳細對照表
  gov-documents.md         類別2 政府其他文件
  legal-documents.md       類別3 法律文件
  civil-petition.md        類別4 人民對政府文書
  official-scenarios.md    公文案件場景補充（按需選讀）
        │
        ├─ build.py ──→ STANDALONE.md   ← 生成產物，禁止手動編輯（單檔完整版）
        │
        ├─ build.py ──→ skills/tw-formal-writing/  ← 生成產物，禁止手動編輯
        │                 SKILL.md + references/ + examples/ 的實體複本
        │
        ├─ build.py ──→ AGENTS.md / GEMINI.md      ← 生成產物，禁止手動編輯
        │                 STANDALONE.md 的實體複本（Codex / Gemini CLI 入口）
        │
   （手動維護，check_consistency 只查錨點）
        └───────────→ LITE.md           ← 手動維護的有損壓縮版（ChatGPT GPTs 字數限制用）

SKILL.md                  ← Claude Code 入口（多檔案模式，執行期讀 references/）
.claude-plugin/plugin.json      ← Claude Code plugin manifest
.claude-plugin/marketplace.json ← 本 repo 自身即 plugin marketplace 的清單
dist/*.zip                ← claude.ai / cowork 上傳用打包（gitignore，由 build 產）

各版本的分工：

  • SKILL.md：執行期由 Claude Code 讀取，再依判斷結果動態 Read 對應的 references/*.md。SKILL.md 本身只有類別判斷邏輯與載入指引，規範內容不在 SKILL.md 裡。
  • STANDALONE.md：_header.md + 6 個 reference 檔組裝而成的單檔（各 reference 的 H1 降級為「附錄一～六」，跨檔指涉改寫為附錄指涉，見 build.py 的 APPENDICES 與 CROSS_REF_FIXES）。
  • skills/tw-formal-writing/：Claude Code plugin 的 skill 目錄。官方規格要求 SKILL.md 與它引用的 references/、examples/ 同層（相對路徑相對 skill 目錄解析），而 SSOT 在 repo 根目錄，故此處放實體複本。v1.4.0 前這裡只有一個 SKILL.md symlink、沒有 references/，plugin 模式下規範全數讀取失敗。
  • AGENTS.md / GEMINI.md：Codex / Gemini CLI 的自動讀取入口，內容即 STANDALONE.md。

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. 4d ago Changed · +1 lines · +55 tokens per session 445a5b2f9353
  2. 10d ago First seen · 103 lines · 2,427 tokens per session scan B bc4fbfd8b5f5

Subscribe to this mod's changes

tw-formal-writing CLAUDE.md is an instructions file published in the GitHub repository Imbad0202/tw-formal-writing (169 stars, last pushed 4d ago), licensed MIT. It adds 2,482 tokens to every session, about $0.0124 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 2026-08-30.

Writing and docsai-skillchineseclaudeformal-writinggeminigovernment
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

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

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