ai-pulse: Instructions file for Claude Code

CLAUDE.md

ai-pulse CLAUDE.md is an instructions file for Claude Code from DaiOwen/ai-pulse. It costs 1,359 tokens per session, scanned A, original, MIT.

A set of instructions for building a daily Chinese-language roundup of artificial-intelligence news from several news sites and developer sources.

In plain words
What is it for?
It helps produce an AI news digest with real source links, duplicate removal, source labels, Chinese summaries, and a notice when the page uses older archived news.
Why use it?
It gives the agent a fixed process for collecting, checking, translating, combining, and ranking stories, including a fallback when live fetching fails.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is DaiOwen/ai-pulse's own configuration. It tells Claude Code how to work on ai-pulse 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 ai-pulse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DaiOwen/ai-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/DaiOwen/ai-pulse/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/DaiOwen/ai-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.

agentmods badge for ai-pulse CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daiowen/ai-pulse/claude-md/github.svg)](https://agentmods.dev/instructions/daiowen/ai-pulse/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/daiowen/ai-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/daiowen/ai-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.

agentmods 80×15 button for ai-pulse CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daiowen/ai-pulse/claude-md"><img src="https://agentmods.dev/badge/instructions/daiowen/ai-pulse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,359 This file is loaded in full into every session.
When invoked 1,359 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 $0.01359 $0.01359
Opus 5 $0.00679 $0.00679
Sonnet 5 $0.00272 $0.00272
Haiku 4.5 $0.00136 $0.00136

Measured 9d ago against content hash dbc83b1905f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-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 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.

CLAUDE.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI 脉搏 · AI热点速览

面向中国 AI 开发者每日 AI 新闻聚合。Claude Code CLI 驱动,零外部依赖。

快速执行(每次 /ai-digest 的标准流程)

不要读旧 index.html,不要 CronList 自检。直接开始。

⚠️ 重要:必须读取 template.html 获取完整样式框架!

第1步:抓取新闻(本地 Python 脚本)

关键原则:优先本地抓取,每条新闻必须标注来源。URL 必须真实,禁止 # 占位。

抓取方式:

# 主抓取(优先)
python3 fetch_news.py > news.json

# 如果脚本失败,生成「回顾版」

支持的信源(10个):

信源 类型 状态 备注
量子位 国内AI快讯 直接HTML抓取
36氪 国内科技商业 RSS抓取(修复JS渲染问题)
Solidot 开源科技新闻 替代机器之心
雷锋网 AI/硬件新闻 替代澎湃新闻
钛媒体 国内科技商业 新增
IT之家 科技资讯 新增
TechCrunch 海外科技 直接HTML抓取
The Verge 海外科技 ⚠️ 偶发超时 直接HTML抓取
Ars Technica 海外深度 直接HTML抓取
Hacker News 开发者社区 Algolia API(修复超时问题)

抓取容错机制:

  1. 主抓取:python3 fetch_news.py → 输出 JSON
  2. 如果失败或结果为空:生成「回顾版」页面
  3. 回顾版从最近 3 天归档中抽取热门内容
  4. 页面顶部显示「网络受限模式」提示

第2步:去重 + 评分

去重: 标题相似度 > 80% 视为重复 → 保留评分高者。同一事件不同角度报道 → 合并为一条,标注多来源。

评分(每条新闻打分,入选板块按分数排序):

总分 = 热度信号×0.4 + 时效信号×0.3 + 来源质量×0.3

热度信号:多源交叉验证(+5) / 优先信源首发(+3) / 社区讨论热度高(+1)
时效信号:6h内(+5) / 12h内(+3) / 24h内(+1) / 48h内(+0)
来源质量:量子位/36氪/TechCrunch(+3) / 机器之心/澎湃新闻/Ars Technica(+2) / 其他(+1)

翻译规范(海外内容): 原文标题 + 中文翻译。摘要全中文 2-3 句。关键数据(金额、百分比、版本号)原文照搬。

第3步:生成 HTML

⚠️ 必须先读取 template.html 获取完整 CSS/JS 框架!

  1. 读取 template.html 获取样式框架
  2. 替换模板变量:
    • {{DATE}} → 完整日期(如 "2026年6月25日")
    • {{EDITION}} → 版次(morning/noon/evening)
    • {{TLDR_CONTENT}} → TL;DR 摘要
    • {{NEWS_CONTENT}} → 新闻内容 HTML
    • {{ARCHIVE_MAP}} → 归档映射 JSON
    • {{NEWS_COUNT}} → 头条新闻数量
    • {{SOURCE_COUNT}} → 信源覆盖数量
    • {{PROJECT_COUNT}} → 热门项目数量(开源热度板块项目数,每天必须有)
    • {{PAPER_COUNT}} → 精选论文数量(论文速递板块论文数,每天必须有)
    • {{SOURCE_LIST}} → 信源列表(如 "量子位、36氪、Solidot、雷锋网...")
  3. 保持所有样式完整:日历弹窗、收藏功能、返回顶部、亮暗主题等

第4步:写入文件(3 个文件)

# 写入 HTML(直接写,不用 tmp 文件)
Write: index.html(完整 HTML)
cp     archive/YYYY-MM-DD-{edition}.html(同内容)

# 更新 feed.xml:在 <lastBuildDate> 后插入新 <item>,保留最近 10 条
# 无需更新其他 archive 文件的 archiveMap

# 提交推送
git add index.html archive/ feed.xml
git commit -m "auto: {edition} — {date} ({top3-news-keywords})"
git push origin master

Read the full file on GitHub · 112 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. 9d ago First seen · 112 lines · 1,359 tokens per session scan A dbc83b1905f0

Subscribe to this mod's changes

ai-pulse CLAUDE.md is an instructions file published in the GitHub repository DaiOwen/ai-pulse (5 stars, last pushed today), licensed MIT. It adds 1,359 tokens to every session, about $0.0068 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.

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens