Glean 拾遗
中 EN
Submit a link
Daily · timeline

A few picks a day.

Sat, Jul 25, 2026 3picks
← 07-24
Calendar ▾
2026 · 07
MoTuWeThFrSaSu ··12345678910111213141516171819202122232425262728293031
has picks today
06:00

Caveman: Slash AI Coding Agent Output Tokens by ~65% While Keeping Technical Accuracy

Caveman：让 AI 编程助手闭上话痨嘴，输出 token 直降 65% 的压缩技能包

A skill/plugin for 30+ AI coding agents (Claude Code, Codex, Cursor, etc.) that compresses agent output by ~65% by stripping filler words while preserving full technical accuracy. Offers multiple compression levels, plus tools for commit messages, PR reviews, memory file compression, and MCP middleware. Solves context pollution, slow response times, and high token costs for developers who interact heavily with coding agents.

github.com · 10 min · Agents · AI · LLM
06:00

Stop Installing Plugins on Claude Code: Everything You Need Is Built In

别再给 Claude Code 装插件了：你需要的一切都在内置命令里

The author installed 23 Claude Code plugins, found baseline overhead of 62,000 tokens before the first prompt. After removing almost all, session length tripled, output quality improved, and token spend halved. This post walks through built-in commands that replaced each plugin: /context for token diagnostics, /compact for conversation compression, /resume for session recovery, Esc Esc for checkpoint restore, /cost for real-time spending, /model for switching models mid-session, /init for project setup, /review for code audits, and custom /.claude/commands/ for zero-overhead workflows. Only three extensions survived the purge, reducing baseline overhead to ~6k tokens. Actionable for any Claude Code user slowed by plugins.

x.com · 16 min · Agents · LLM · Performance
06:00

MarkItDown: Microsoft's Swiss-Army Knife for Converting Any File to LLM-Ready Markdown

MarkItDown：微软开源的万能文件转 Markdown 工具，为 LLM 做数据预处理

MarkItDown is a lightweight Python utility by Microsoft's AutoGen team that converts various file types—PDF, Office docs, images, audio, HTML, etc.—into structured Markdown, optimized for LLM consumption and text analysis pipelines. It emphasizes preserving document structure (headings, tables, links) in a token-efficient format while keeping the output machine-friendly. With a clean CLI, Python API, plugin system, and optional Azure cloud enhancements, it serves as a practical pre-processing tool for RAG and data extraction workflows.

github.com · 16 min · AI · LLM · TypeScript