One shell script that makes a rooted LG webOS TV lighter and quieter:
Nothing is deleted and the root filesystem is never touched. It only edits
Instructions for a coding agent. Apply them on the user's Mac only when the user has asked for it. They remove OpenAI's default confirmation policies, OpenAI's secure-login flow, and a frame blocker in the ChatGPT browser extension that hides password-manager menus. After this, Codex follows the user's own instructions (AGENTS.md) instead of OpenAI's rules.
Tradeoff. These layers exist to blunt prompt injection and accidental side effects. Without them, the agent will send, delete, buy, and log in
| # meaningful contribution | |
| Based on embarassing feedback on a bad PR for AXM-10598, and written from my beliefs; with only a little bit of copy pasting, because to be human is to copy from a shitload of places until it becomes your own. | |
| ## A contribution is not code, it's proven working code | |
| > "your job is to deliver code you have proven to work." — [simon willison](https://simonwillison.net/2025/Dec/18/code-proven-to-work/) | |
| agent-generated code is cheap. anyone can prompt an LLM to produce a thousand-line patch. that's not valuable. what's valuable is contributing code that demonstrably works, has been tested, and doesn't shift burden to reviewers. |
A nice, quick way to launch precise amp review code reviews. Created for Amp.
SKILL.md — the skill body. Drop it into any agent skills directory (e.g. ~/.config/agents/skills/amp-review/SKILL.md).skill-invoker.ts — an Amp plugin that lets you trigger a skill from the command palette (or via the $skill-name token in a message). It injects an explicit prompt to properly nudge the agent to invoke the selected skill(s). Tested in deep and glm agent modes.
| import { DynamicWorkerExecutor } from "@cloudflare/codemode"; | |
| import { openApiMcpServer } from "@cloudflare/codemode/mcp"; | |
| import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; | |
| import { | |
| createFetchYnabApiClient, | |
| createYnabOpenApiRequestHandler, | |
| type YnabApiClient, | |
| } from "./ynab-client.ts"; | |
| import ynabOpenApi from "./ynab-openapi.json"; |
| import type { PluginAPI } from '@ampcode/plugin' | |
| const OPUS_4_8_AGENT_PROMPT = ` | |
| You are Amp running in Claude Opus 4.8 mode. You are a senior coding agent paired with the user to solve software engineering tasks end-to-end. Treat every user message as a refinement of the current task, adapt immediately to corrections, and keep working until the requested outcome is implemented, verified, and clearly reported. | |
| <operating_principles> | |
| - Prefer the smallest correct change that satisfies the user. | |
| - Read the relevant code before making claims or edits. Never guess about files you have not inspected. | |
| - Use the repository's existing patterns, helpers, naming, and tests instead of inventing new structure. | |
| - Avoid unrelated cleanup, speculative abstractions, broad refactors, or defensive handling for impossible internal states. |
| (() => { | |
| const host = () => document.querySelector('uidotsh-picker'); | |
| const btn = dir => host()?.shadowRoot?.querySelector(`button[data-nav][data-${dir}]`); | |
| const cycle = dir => { | |
| const b = btn(dir); | |
| if (!b) return; | |
| b.dispatchEvent(new MouseEvent('click', { bubbles: true, cancelable: true, composed: true })); | |
| }; | |
| window.uiNext = () => cycle('next'); |
This language is a new statically typed, functional, macro-capable language with Elixir-like syntax and a native backend strategy built around lowering through a Zig-oriented compiler pipeline.
It is:
| #!/usr/bin/env bash | |
| set -euo pipefail | |
| bold() { printf "\033[1m%s\033[0m\n" "$*"; } | |
| info() { printf "• %s\n" "$*"; } | |
| warn() { printf "\033[33m! %s\033[0m\n" "$*"; } | |
| err() { printf "\033[31m✗ %s\033[0m\n" "$*" >&2; } | |
| ok() { printf "\033[32m✓ %s\033[0m\n" "$*"; } | |
| require_macos() { |
