onevcat

基本设定

• 服务对象为 onevcat：资深 iOS 开发者，技术力爆炸，所以不需要废话。重视 “Slow is Fast”、推理质量、抽象与长期可维护性。github.com/onevcat, onevcat.com, onev.cat, onev.dev, x.com/onevcat 等都视为用户相关
• 代码、注释、标识符、提交信息及代码块内容用标准/简洁/明确的 English。技术文档优先使用 English；若文档现有中文语境，则正文中文、代码块 English。English 遵守 ASD-STE100 Simplified Technical English (STE)。
• 对需要说明结论、方案或决策的任务，按“直接结论 → 简要推理 → 可选方案 → 可执行下一步”组织，不要长篇大论，不要事无巨细；简单确认、闲聊或一行答案直接回答。
• 在修改文件时，使用待修改文件中使用的语言，切忌中英文混杂。
• 处理 GitHub 相关操作优先使用 gh CLI。
• 目标：作为强推理、强规划的编码助手，首要目标是完成任务。尽量一次到位，减少无谓澄清，只在明确被提问时才解释技术细节。

人设

patleeman

Codex /goal Implementation

How OpenAI's Codex CLI implements the /goal slash command for persisted long-running task objectives.

The /goal command sets a persisted objective for a long-running task. It's a five-layer system: a SQLite table stores one goal per thread with status (active/paused/budget_limited/complete), optional token budget, and running usage counters. The app-server exposes thread/goal/set/get/clear JSON-RPC methods. The model sees three tools — create_goal, update_goal(complete), and get_goal — but can't pause/resume; those are system-controlled. A runtime event bus hooks into turn lifecycle to track token + wall-clock deltas for accounting, auto-pauses on interrupt, auto-reactivates paused goals on thread resume, and injects budget-limit steering into the model's response stream. The TUI handles the /goal slash command and displays goal state in the status bar.

Author: etraut-openai | 5 PRs, ~15K additions, landed in ~10 days (Apr 16–25, 2026)

---

karpathy

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.

ljw1004

#!/bin/bash
set -euo pipefail
trap 'echo "at line $LINENO, exit code $? from $BASH_COMMAND" >&2; exit 1' ERR

# This is a Claude Code hook to stop it saying "you are right".
#
# Installation:
# 1. Save this script and chmod +x it to make it executable.
# 2. Within Claude Code, /hooks / UserPromptSubmit > Add a new hook (this file)
#

Fadi002

import sys
import os

NOP = 0x90
offsets_and_values = {
    0x00030170: 0x00,
    0x000A94D0: NOP, 0x000A94D1: NOP, 0x000A94D2: NOP, 0x000A94D3: NOP, 0x000A94D4: NOP, 0x000A94D5: NOP, 0x000A94D6: NOP, 0x000A94D7: NOP, 0x000A94D8: NOP, 0x000A94D9: NOP, 0x000A94DA: NOP, 0x000A94DB: NOP, 0x000A94DC: NOP, 0x000A94DD: NOP, 0x000A94DE: NOP, 0x000A94DF: NOP, 0x000A94E0: NOP, 0x000A94E1: NOP, 0x000A94E2: NOP, 0x000A94E3: NOP, 0x000A94E4: NOP, 0x000A94E5: NOP, 0x000A94E6: NOP, 0x000A94E7: NOP, 0x000A94E8: NOP, 0x000A94E9: NOP, 0x000A94EA: NOP, 0x000A94EB: NOP, 0x000A94EC: NOP, 0x000A94ED: NOP, 0x000A94EE: NOP, 0x000A94EF: NOP, 0x000A94F0: NOP, 0x000A94F1: NOP, 0x000A94F2: NOP, 0x000A94F3: NOP, 0x000A94F4: NOP, 0x000A94F5: NOP, 0x000A94F6: NOP, 0x000A94F7: NOP, 0x000A94F8: NOP, 0x000A94F9: NOP, 0x000A94FA: NOP, 0x000A94FB: NOP, 0x000A94FC: NOP, 0x000A94FD: NOP, 0x000A94FE: NOP, 0x000A94FF: NOP, 0x000A9500: NOP, 0x000A9501: NOP, 0x000A9502: NOP, 0x000A9503: NOP, 0x000A9504: NOP, 0x000A9505: NOP, 0x000A9506: NO

jahirfiquitiva

{
  "breadcrumbs.enabled": false,
  "editor.fontFamily": "'MonoLisa', 'Dank Mono', 'Operator Mono Lig', 'Operator Mono', Menlo, Monaco, 'Courier New', monospace",
  "editor.fontWeight": "400",
  "editor.cursorBlinking": "smooth",
  "editor.cursorSmoothCaretAnimation": "explicit",
  "editor.stickyScroll.enabled": true,
  "explorer.sortOrder": "type",
  "workbench.editor.enablePreview": false,
  "workbench.editor.highlightModifiedTabs": true,

yorickdowne

Debian 13 "Trixie"

To start, read the official release notes.

If your system is "vanilla Debian plus maybe a handful of 3rd-party repos", then this guide for a simple upgrade to Debian 13 "trixie" from Debian 12 "bookworm" can be helpful. 3rd-party repos are handled with a find command.

If you are on a fork of Debian such as RasPI OS, use their instructions, not this gist.

Note upgrade is only supported from Debian 12 to Debian 13. If you are on Debian 11, upgrade to Debian 12 first. Then once on Debian 12, you can upgrade to Debian 13.

dbilanoski

hyperupcall

// I'm tired of extensions that automatically:
// - show welcome pages / walkthroughs
// - show release notes
// - send telemetry
// - recommend things
//
// This disables all of that stuff.
// If you have more config, leave a comment so I can add it!!

{

hyoban

[user]
	name = Stephen Zhou
	email = 38493346+hyoban@users.noreply.github.com
	signingkey = ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIDg/3T8nsnp4yqbQ0PFTs2rFZZZ7z6WFzIkp+r5EXdQB
[init]
	defaultBranch = main
[gpg]
	format = ssh
[commit]
	gpgsign = true