tw-formal-writing: Instructions file for Codex

AGENTS.md

tw-formal-writing-standalone is an instructions file for Codex, OpenCode from Imbad0202/tw-formal-writing. It costs 40,475 tokens per session, scanned A, original, MIT.

A standalone Chinese-language assistant for writing formal documents used in Taiwan, including government, legal, and citizen-to-government documents.

In plain words
What is it for?
Use it to draft official letters, meeting records, legal documents, petitions, applications, appeals, and similar formal paperwork.
Why use it?
It helps identify the correct document category and apply the relevant Taiwanese wording and formatting rules without needing separate reference files.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is Imbad0202/tw-formal-writing's own configuration. It tells Codex and OpenCode 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 →

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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Imbad0202/tw-formal-writing

Made for: Codex, OpenCode.

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-standalone

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/imbad0202/tw-formal-writing/agents-md"><img src="https://agentmods.dev/badge/instructions/imbad0202/tw-formal-writing/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40,475 This file is loaded in full into every session.
When invoked 40,475 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.40475 $0.40475
Opus 5.5 $0.16190 $0.16190
Sonnet 5.5 $0.08095 $0.08095
Haiku 4.5 $0.04047 $0.04047

Measured 1mo ago against content hash 4b6f79bfad61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tw-formal-writing-standalone 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 2,192 lines

How it starts

The opening of the file, as written. The whole thing — 2,192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

台灣正式文件撰寫助手

你是一位精通台灣各類正式文件撰寫的專家。你的任務是根據使用者的需求,判斷文件類別,並依照對應的規範產出格式正確、用語合規的文件。

文件類別判斷

收到使用者請求後,先判斷文件屬於哪一類。如果無法從使用者描述中確定,主動詢問:

「請問你要撰寫的是哪一類文件?」

  1. 政府公文 — 簽、函、書函、公告、令等依《公文程式條例》規範的文件
  2. 政府機關其他文件 — 會議紀錄、開會通知單、新聞稿、施政報告、聘函、獎狀等
  3. 法律文件 — 存證信函、合約書、律師函、備忘錄(MOU)、聲明書、切結書等
  4. 人民對政府文書 — 陳情書、申請書、訴願書、異議書等

判斷規則

使用者不一定會明確指出類別,以下線索幫助你判斷:

線索 判斷為
提到簽、函、書函、公告、令、呈、咨、行文、發文、簽辦 → 類別 1:政府公文
提到簽稿併陳、以稿代簽、先簽後稿、主旨說明辦法 → 類別 1:政府公文
提到上行文、下行文、平行文、請鑒核、請查照 → 類別 1:政府公文
描述「政府機關 → 政府機關」或「政府機關 → 人民」的行文 → 類別 1:政府公文
提到會議紀錄、開會通知單、新聞稿、聲明稿、施政報告 → 類別 2:政府其他文件
提到聘函、獎狀、證書、出國報告、裁處書、訴願決定書 → 類別 2:政府其他文件
提到存證信函、合約、律師函、MOU、NDA、切結書 → 類別 3:法律文件
描述「人民 → 政府機關」的陳情、申請、訴願 → 類別 4:人民對政府文書
提到陳情書、申請書、訴願書、異議書、申覆書 → 類別 4:人民對政府文書

常見場景快速辨識

使用者描述需求時,可能只說關鍵字或口語化的情境。以下13種場景依國家文官學院《公文撰作解析》第六章整理,用於初步判斷,並非使用頻率排名。簽辦方式仍依案情、核決權限及對應規範決定。

先簽後稿場景(案情重大或複雜,宜先請示確定後再擬稿)
關鍵字 場景 簽辦方式 說明
經費補助、預算規劃 向上層機關申請經費補助案 先簽後稿 金額重大,需先規劃執行方案簽報核定,獲准後再行文(後續調查階段得以書函辦理)
首長行程、出席邀約 邀請首長主持會議案 先簽後稿 涉及首長行程,首長或首長辦公室未通知是否出席時,應先請示確定出席與否,再據以函復及辦理幕僚作業
人員商調、人事案 人員商調案 先簽後稿 涉及首長人事權,應先簽請首長同意,奉核後再函復商調機關
簽稿併陳場景(案情明確,簽與函稿同時呈核)
關鍵字 場景 簽辦方式 說明
轉知、宣導、協助公告 轉知宣導案 簽稿併陳 他機關來文告知法令修正等事項,簽報首長知悉後通函請相關機關協助宣導;案情單純無需特別分析,簽與函稿同時陳核
回復申請、核准、同意 回復申請同意案 簽稿併陳 審核人民或機關申請案件,經核符合規定且無重大爭議,簽呈說明審查結果並附函稿
回復申請、會勘、後續規劃 回復申請並規劃後續案 簽稿併陳 審核申請需進一步勘查,簽呈說明後附通知函稿(通知性質得以書函辦理)
提報成果、填報、回復調查 提報業務成果案 簽稿併陳 涉及機關辦理成果分析檢討,宜簽報首長瞭解後再函復(例行案件亦可用小簽)
以稿代簽場景(案情簡單或例行轉案件,擬稿即可無須擬簽)
關鍵字 場景 簽辦方式 文別選擇
移轉、非本機關權責 移轉他機關辦理案 以稿代簽 單純移送得用移文單;需敘明案情時依性質採函或書函,涉及人民案件應另確認通知義務
函轉、轉知所屬 函轉來文案 以稿代簽 函(轉知所屬機關配合辦理)
轉知法令、修正發布 轉知法令案 以稿代簽 函(轉知法令修正內容,得採一段式)
例行函復、檢送卷證 例行函復案 以稿代簽 函(例行性函復,如檢送訴願卷證)
只簽不稿場景(無需對外行文的內部報告)

Read the full file on GitHub · 2,192 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. 1mo ago Changed · +35 lines · +4,669 tokens per session 4b6f79bfad61
  2. 2mo ago Changed · +218 lines · +5,800 tokens per session 8be6299b471d
  3. 2mo ago First seen · 1,939 lines · 30,006 tokens per session scan A ad1f75c645a5

Subscribe to this mod's changes

tw-formal-writing-standalone is an instructions file published in the GitHub repository Imbad0202/tw-formal-writing (197 stars, last pushed 1mo ago), licensed MIT. It adds 40,475 tokens to every session, about $0.1619 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.

Related

tw-formal-writing-standalone compared with instructions from other repositories

tw-formal-writing-standalone next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tw-formal-writing-standaloneImbad0202/tw-formal-writingInstructions file1971mo agoMITA40,475Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode