Nat nazt

type	workshop-script
event	MIdS Training — Guide to AI Tools for Research and Publication
date	2026-04-29 (พุธ) 13:30-15:30 GMT+7
speaker	ดร.ฮัยศัม สาแม
slot	~45 นาที (13:35-14:20, ก่อน Nat)
audience	20 PhD students, MIdS @ CMU, ภาษาไทย
intent	SCAFFOLDING for ดร.ฮัยศัม สาแม — drafted by Nat's Oracle for coordination
status	DRAFT — for ดร.ฮัยศัม สาแม to adapt with his own voice + examples

marp: true theme: default paginate: true backgroundColor: '#fff' header: 'MIdS Training | 29 เม.ย. 2569 | ณัฐ วีระวรรณ์' footer: '🤖 Drafted by hermes-mids 2026-04-25 · Rule 6: Oracle never pretends to be human' style: | section { font-family: 'Noto Sans Thai', 'Sarabun', sans-serif; font-size: 24px; line-height: 1.55; } h1 { color: #1a4d8c; }

type: workshop-script event: MIdS Training — Guide to AI Tools for Research and Publication date: 2026-04-29 (พุธ) 13:30-15:30 GMT+7 speaker: ณัฐ วีระวรรณ์ slot: ~45 นาที (14:30-15:15 หลัง ดร.ฮัยศัม สาแม) audience: 20 PhD students, MIdS @ CMU, ภาษาไทย intent: prose script — narrowed focus per Nat's request focus_tools: [Gemini, Claude (chat), Claude Code, Agentic AI vs LLM concept, NotebookLM] status: DRAFT v2 — narrowed focus

installer	timekeeper-oracle
origin	Nat Weerawan's brain, digitized — how one human works with AI, captured as code — Soul Brews Studio
name	seek
description	[core] G-SKLL \| Unified deep investigation — combines /trace (find) + /dig (mine sessions) + /time-travel (prove) into one command. Use when user says "seek", "find everything about", "investigate", "full picture", "what do we know about", or needs complete reconstruction of a topic across all sources. Modes: --quick (surface), default (smart escalation), --deep (parallel agents), --full (deep + verbatim evidence + narrative). Do NOT trigger for simple file search (use grep), current session status (use /recap), or repo study (use /learn).
argument-hint	<query> [--quick \| --deep \| --full] [--prove] [--timeline] [--back]

/seek — Unified Deep Investigation

A minimal Telegram bot from scratch — polling + webhook + mock, in Bun/TS

Zero dependencies. Every line readable in one sitting. What grammY wraps. 2026-04-21 · openclaw-learner-oracle · Angle D of 4

Three files. Each runs with nothing but Bun installed. No npm deps, no framework. Read end-to-end to demystify every SDK wrapper you've ever used.

bot-polling.ts (153 lines) — long-polling bot
bot-webhook.ts (148 lines) — webhook bot, same logic

Telegram bot security — who can reach you, how you're defended, how tokens leak

The access-control layer in hermes vs channels, plus the operational security that no bot framework covers 2026-04-21 · openclaw-learner-oracle · Angle C of 4

Three things that together determine whether your bot is actually secure: how it gates inbound, how it defends against prompt injection in replies, and what happens to the token outside the bot process.

Telegram bot configuration — the full knob inventory

Every setting, where it lives, what it does — hermes vs Claude channels vs raw Bot API 2026-04-21 · openclaw-learner-oracle · Angle B of 4

A complete reference of what you can tune on a Telegram bot, organized by which layer exposes it. Three layers: hermes-agent, Claude channels plugin, and raw Bot API / BotFather (the gap neither covers).

For each knob: what it is · where it lives · what it does.

Telegram bot delivery — polling vs push, answered from source

Reading hermes-agent and the Claude Code telegram plugin side-by-side 2026-04-21 · openclaw-learner-oracle

Both hermes-agent (Python, launchd daemon) and the Claude Code telegram plugin (Bun, in-process MCP server) default to long-polling, not webhooks. This is the "Angle A" answer from a multi-part telegram configuration study.

The one-liner

Proof: Anthropic's Claude Code Telegram plugin uses long-polling (not push)

A source-cited walkthrough of external_plugins/telegram/server.ts in anthropics/claude-plugins-official, showing every link in the chain from bot.start() to GET /getUpdates?timeout=30.

Repo: anthropics/claude-plugins-official (external_plugins/telegram/)
Plugin version: 0.0.1 (per package.json)
Library: grammy@^1.21.0 — pinned in package.json
Question: Is it push (setWebhook) or poll (getUpdates)?
Answer: Long-polling via getUpdates. Never setWebhook.

	#!/bin/bash
	# Setup new Mac — run ON the machine itself
	# curl -fsSL https://gist.githubusercontent.com/.../setup.sh \| bash
	# Or: bash setup-m5.sh

	set -e
	echo "🖥️ Setting up $(hostname)..."

	# ── 1. Hostname ───────────────────────────────────────────────────
	echo ""