Borrowing it
Nothing to install: this file belongs to nagameTW/humanizer-zh-tw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nagameTW/humanizer-zh-tw/main/AGENTS.mdgit clone --depth 1 https://github.com/nagameTW/humanizer-zh-twWrote 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.
[](https://agentmods.dev/instructions/nagametw/humanizer-zh-tw/agents-md)<a href="https://agentmods.dev/instructions/nagametw/humanizer-zh-tw/agents-md"><img src="https://agentmods.dev/badge/instructions/nagametw/humanizer-zh-tw/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.
<a href="https://agentmods.dev/instructions/nagametw/humanizer-zh-tw/agents-md"><img src="https://agentmods.dev/badge/instructions/nagametw/humanizer-zh-tw/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01295 | $0.01295 |
| Opus 5 | $0.00647 | $0.00647 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
humanizer-zh-tw AGENTS.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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
給在此 repo 工作的 AI 編碼代理（Claude Code、Codex、Warp 等）的指引。改編自 blader/humanizer 的 AGENTS.md。
這個 repo 是什麼
一個完全以 Markdown 實作的可攜 agent skill。執行時的產物是 SKILL.md：agent
讀它的 YAML frontmatter 和底下的編輯指令。沒有 build 步驟，用字不要把支援範圍
限縮到某一兩個 harness。
關鍵檔案
SKILL.md— 技能本體。可攜的 YAML frontmatter（name、description、license、metadata.version）後接編號的模式清單（每個模式只留「需要注意的 詞彙」「問題」與一行指向 PATTERNS.md 的指標）。這是唯一的真相來源（source of truth）。 技能是 model-invoked，SKILL.md 全文每次相關輪次都會載入，所以 保持精簡：規則與偵測要點留這裡，完整範例放 PATTERNS.md。PATTERNS.md— 每個模式的改寫前後範例，編號與 SKILL.md 一致。只在校準改寫 尺度或需要對照時查閱，不參與日常偵測。新增或修改模式時，SKILL.md 的偵測要點 與 PATTERNS.md 的範例要一起更新。references/zh-cn-glossary.md— 模式 34 的完整中國用語對照表（資訊科技、日常 與職場、自媒體與網路用語、動詞慣用法、商業黑話、語感層）。SKILL.md 模式 34 只 留問題描述與一行指標，實際詞表在此。改動兩岸對照詞時只動這裡，SKILL.md 不重複。README.md— 給人看：安裝、使用、模式總覽表、版本歷史。CHANGELOG.md— 依 Keep a Changelog，每次改行為都要記。.claude-plugin/plugin.json— Claude Code 外掛 manifest，含version。.claude-plugin/marketplace.json— 單一 repo 的 marketplace 進入點；刻意 不放 version，讓plugin.json當套件版本的唯一來源。scripts/validate-package.py— 無外部相依的同步檢查，本地與 CI 都跑。
維護契約（改東西前先讀）
SKILL.md、PATTERNS.md、README.md、CHANGELOG.md、plugin.json 必須保持
同步。改行為或內容時，在同一次改動裡一起更新，不要分開：
- 模式： 新增、刪除或重編號任何模式時，同一次要更新 SKILL.md 的偵測要點與
指標、PATTERNS.md 對應編號的範例（兩檔模式編號必須完全一致，validate 會擋）、
README 的「N 種模式總覽」標題數字與總覽表對應分類列、SKILL frontmatter
description 與 plugin.json description 裡的「N 種模式」、以及所有交叉引用
（「見模式 X」）。編號從 1 連續，非必要不重編。改動模式 34 的中國用語詞條時，
詞表在
references/zh-cn-glossary.md，改那裡；SKILL.md 模式 34 只留指標，不放表。 - 版本： 版本存在三處——SKILL frontmatter 的
metadata.version、README 版本歷史、plugin.json 的version。一起 bump。版本放在metadata底下； top-levelversionkey 不可攜，別用。marketplace.json 不放 version。 版本號依 SemVer：新增模式或規則是 MINOR，修正是 PATCH。 - 相容性： 安裝與使用的措辭保持 harness 中立。技能應能在任何載得動 Markdown
技能指令的 agent harness 運作；Claude Code、Codex 等只是例子，不是限制。
frontmatter 不要加
compatibility:或allowed-tools:（不可攜，validate 會擋）。 - 驗證： 發布前跑
python3 scripts/validate-package.py（檢查版本一致、模式 編號連續、README 數字對得上），以及npx skills add . --list、claude plugin validate .。 - 非顯而易見的修正： 若為了處理棘手的失敗模式（反覆改錯、語氣跑掉）而改了 提示詞，在 CHANGELOG 加一行說明改了什麼、為什麼。
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.
- 8d ago First seen · 62 lines · 1,295 tokens per session scan A 98db854f1399
humanizer-zh-tw AGENTS.md is an instructions file published in the GitHub repository nagameTW/humanizer-zh-tw (8 stars, last pushed 1mo ago), licensed MIT. It adds 1,295 tokens to every session, about $0.0065 per session on Opus 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 2026-08-31.
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.
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.
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).
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).
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.
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.