Nat nazt

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.

Claude Code Telegram Plugin — Architecture

What It Is

The Telegram plugin bridges Telegram bots to Claude Code via an MCP server. "The MCP server logs into Telegram as a bot and provides tools to Claude to reply, react, or edit messages. When you message the bot, the server forwards the message to your Claude Code session." (README.md) Users pair via 6-character codes, switch to allowlist mode for security, and support single-user DMs plus group mentions.

Plugin manifest (.claude-plugin/plugin.json):

{
 "name": "telegram",

Claude channels — the 6 cool things

The only system in this stack that doesn't try to be an agent 2026-04-20 · openclaw-learner-oracle

After wiring up all four — openclaw, hermes, maw-js, Claude channels — and poking at the seams for a day, Claude channels keeps surprising me. Here's what actually stands out.

1. Zero daemon

hermes MCP — the big picture

The architectural move in one line: fat agent → thin tool provider 2026-04-20 · openclaw-learner-oracle

One-sentence takeaway

hermes mcp serve turns hermes from a monolithic agent into a composable capability layer — any MCP client can borrow hermes's 15+ messaging platforms, SQLite FTS5 persistence, and 73-skill tool surface without running

	#!/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 ""