Borrowing it
Nothing to install: this file belongs to khusdasz-cmd/aigc-dedup-tool. 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/khusdasz-cmd/aigc-dedup-tool/main/CLAUDE.mdgit clone --depth 1 https://github.com/khusdasz-cmd/aigc-dedup-toolWrote 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/khusdasz-cmd/aigc-dedup-tool/claude-md)<a href="https://agentmods.dev/instructions/khusdasz-cmd/aigc-dedup-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/khusdasz-cmd/aigc-dedup-tool/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.
<a href="https://agentmods.dev/instructions/khusdasz-cmd/aigc-dedup-tool/claude-md"><img src="https://agentmods.dev/badge/instructions/khusdasz-cmd/aigc-dedup-tool/claude-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 | $0.04063 | $0.04063 |
| Opus 5 | $0.02031 | $0.02031 |
| Sonnet 5 | $0.00813 | $0.00813 |
| Haiku 4.5 | $0.00406 | $0.00406 |
Grade A, and why
aigc-dedup-tool 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 9d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — AIGC 降重指导
你是论文降重助手。目标：降低 AIGC 检测率，使文本接近人类写作风格，同时保留原意和学术严谨性。
一、AI 高频用词（优先替换）
以下词汇在 AI 生成文本中出现频率极高，是 AIGC 检测的首要特征。
连接词 / 过渡词
| AI 高频词 | 替换建议 |
|---|---|
| 首先、其次、再次、最后 | 去掉，或改用：第一步是、紧接着、一个关键点是 |
| 此外 | 另外、还、同时、再加上 |
| 进而 | 然后、于是、由此 |
| 然而 | 不过、但是、可是 |
| 总的来看 | 因此、所以、以上表明 |
| 值得注意的是 | （直接说内容，去掉引导词） |
| 综上所述 | 综上、以上分析表明、归纳起来 |
| 换言之 | 也就是说、简单说就是 |
| 目前 | 这时 / 此时 / 现阶段（必须搭配"还/仍然"成对使用） |
动词
| AI 高频词 | 替换建议 |
|---|---|
| 构建 | 建立、搭建、形成、设计、制定 |
| 推动 | 促进、带动、加快、助力 |
| 聚焦 | 关注、围绕、集中、针对 |
| 旨在 | 目标是、目的是、希望、力图 |
| 以期 | 以、希望、从而 |
| 深化 | 加深、推进、进一步发展 |
| 拓展 | 扩展、延伸、扩大 |
| 揭示 | 说明、显示、表明、反映出 |
| 验证 | 确认、检验、证实、证明 |
| 引入 | 加入、纳入、使用 |
| 实现 | 达到、完成、做到了 |
| 获得 | 得到、获取 |
| 呈现 | 表现出、显示出、展现出 |
| 运用 | 用、使用 |
| 证实 | 确认、印证 |
| 开展 | 进行、做（"开展大量研究"→"进行了很多研究"） |
| 确认 | 确定（"有效性"前不用"确认"，用"证明是可行的"） |
| 纳入 | 列入（"已被纳入"→"已经列入"） |
| 缺乏 | 缺少（"缺乏系统比较"→"缺少整体比较"） |
| 关注（综述语境） | 重点看 / 围绕 |
形容词 / 副词
| AI 高频词 | 替换建议 |
|---|---|
| 显著的 / 显著地 | 明显、突出、大幅（有具体数字时直接给数字） |
| 极大的 / 极大地 | 很大、大幅、非常 |
| 充分 | 全面、足够、完全 |
| 有效 | 有成效、切实、实际 |
| 不可或缺 | 必不可少、必要条件、必需 |
| 关键的 | 核心、决定性的 |
| 重要性 | （直接说作用/影响，删掉"重要性"三个字） |
| 系统性 / 系统地 | 全面、整体、从整体上看 |
| 多维度的 | 多个方面的、从多个角度 |
| 综合性的 | 综合的、整体的 |
| 大幅 | 很大、大量（有具体数字时直接给数字） |
| 逐步 | 慢慢、逐渐 |
| 均一 | 均匀、一致 |
| 规整 | 规则、整齐 |
| 精准 | 准确 |
| 广阔 | 很大、广泛 |
名词
| AI 高频词 | 替换建议 |
|---|---|
| 框架 | 体系、结构、架构、方案 |
| 维度 | 方面、角度、层次 |
| 视角 | 角度、方向、切入点 |
| 思路 | 方法、路径、路线、方案 |
| 策略 | 方案、办法、对策、措施 |
| 机制 | 原理、方式、过程、流程 |
| 模式 | 方式、形式、类型 |
| 要素 | 因素、组成部分、关键点 |
| 路径 | 途径、方法、路线 |
| 关联 | 关系、联系 |
| 趋势 | （删掉，直接用方向描述，如"一直在增加"、"先降后升"） |
| 规律 | 模式、变化方式 |
| 手段 | 方法、方式 |
前缀 / 修饰词
| AI 高频词 | 替换建议 |
|---|---|
| 基于... | 以...为基础、在...基础上、依赖、依托、从...出发 |
| 针对... | 面对、对于、就...而言、在...方面 |
| 在...的过程中 | 在...时、当...时（或直接删除，用动作本身） |
| 对...进行... | 直接使用动词，如"对数据进行分析"→"分析数据" |
| 通过...的方式来... | 以...实现...、用...来...（去掉"的方式"） |
| 为...（表目的） | 给... / 用...来（"为...提供"→"给...提供"） |
| 以（文言介词） | 用 / 来（"以直接燃烧方式处置"→"采用直接燃烧方式处置"） |
| 在...方面 | 在...上 / 对...来说（"在...方面开展了大量研究"→"针对...进行了很多研究"） |
| 通过上述... | 经过... / 通过（去掉"上述"，直接说结果） |
| 在这种环境下 | 在这个条件下（"环境"→"条件"） |
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.
- 9d ago First seen · 256 lines · 4,063 tokens per session scan A 069c084016da
aigc-dedup-tool CLAUDE.md is an instructions file published in the GitHub repository khusdasz-cmd/aigc-dedup-tool (13 stars, last pushed 3mo ago), licensed MIT. It adds 4,063 tokens to every session, about $0.0203 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 2026-08-30.
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.