Skip to content

Instantly share code, notes, and snippets.

---
name: cowork
description: 在 Herdr App 中以 Commander 身份运转一个 Agent 团队:用 hc CLI 在持久终端里启动、委派、跟踪和清理成员 Agent,维护仓库的 TEAM.md 注册表与通讯录,用 herdr-app 管理界面 tab。当用户要求协调多个 Agent、委派开发/训练/评测/构建任务、组建或接管 Agent 团队、维护 TEAM.md 时使用。
version: 1.1.0
allowed-tools:
- Bash(hc *)
- Bash(herdr-app *)
---
# Cowork:Herdr App 中的 Agent 团队

Static Site + Blog Infrastructure Plan

Astro + MDX · rsync deploy · Linode · Cloudflare DNS

This document defines a boring, sane, long-lived infrastructure for a content-driven website and blog.

The guiding principle is simple:

Build locally. Inspect everything. Deploy files. Serve static content.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@dexhorthy
dexhorthy / the-no-ai-slop-manifesto.md
Last active November 16, 2026 12:35
The No AI Slop Manifesto

No AI Slop: A Manifesto

Written by the speakers and attendees of AIE Code Summit 2026

In 2001, 17 software engineers and leaders got together at a ski lodge in Snowbird, Utah to understand the biggest challenge of their time: heavyweight, documentation-driven software development processes.

Out of this we got the Agile Manifesto, four values and twelve principles that changed how most of the industry builds software.

Today we convene to build our own manifesto - the No AI Slop manifesto.

import { Avalanche, BinTools, BN } from "avalanche"
import { Buffer } from 'buffer/'
import {
AVMAPI,
AVMKeyChain,
Tx,
UnsignedTx,
UTXOSet
} from "avalanche/dist/apis/avm"
name vibecoder-review
description Practical OWASP-focused security review for fast-moving codebases built with AI assistance - catches common patterns where speed trumps security (exposed secrets, auth bypasses, missing access controls, injection vulnerabilities)

Vibecoder Security Review

Overview

Target audience: Fast-moving codebases built by developers using AI assistance, rapid prototyping tools, and modern frameworks. These projects prioritize speed and iteration, often skipping security fundamentals.