diff --git a/wizard-work/quill/hermes-quick-ref-draft-2026-10-28.md b/wizard-work/quill/hermes-quick-ref-draft-2026-10-28.md
new file mode 100644
index 0000000..30afd89
--- /dev/null
+++ b/wizard-work/quill/hermes-quick-ref-draft-2026-10-28.md
@@ -0,0 +1,45 @@
+# Hermes Agent Quick-Reference Draft
+Generated: 2026-10-28
+Author: quill (Draft lane)
+
+---
+
+## What it is
+Hermes Agent is an autonomous agent, not a coding copilot or chatbot wrapper.
+Exact quote from docs:
+  "It's not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. It's an autonomous agent that gets more capable the longer it runs."
+
+## Install (Linux / macOS / WSL2)
+curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
+
+Exact quote from docs:
+  "For Linux / macOS / WSL2, run: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash"
+
+## Fastest path after install
+hermes setup --portal
+
+Exact quote from docs:
+  "After installing, run `hermes setup --portal` — one OAuth covers a model plus all four Tool Gateway tools (web search, image generation, TTS, browser)."
+
+## Key feature: built-in learning loop
+Exact quote from docs:
+  "The only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, and builds a deepening model of who you are across sessions."
+
+## Platforms
+CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, DingTalk, Feishu, WeCom, Weixin, QQ Bot, Yuanbao, BlueBubbles, Home Assistant, Microsoft Teams, Google Chat, and more.
+
+Exact quote from docs:
+  "CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, DingTalk, Feishu, WeCom, Weixin, QQ Bot, Yuanbao, BlueBubbles, Home Assistant, Microsoft Teams, Google Chat, and more — 20+ platforms from one gateway"
+
+## LLM-readable docs
+- `/llms.txt` — curated index, ~17 KB
+- `/llms-full.txt` — every doc page concatenated, ~1.8 MB
+
+Exact quote from docs:
+  "`/llms.txt` — curated index of every doc page with short descriptions. ~17 KB, safe to load into an LLM context."
+  "`/llms-full.txt` — every doc page concatenated into a single markdown file for one-shot ingestion. ~1.8 MB."
+
+---
+
+VERDICT: Draft is evidence-backed with exact quotes from the official docs page at https://hermes-agent.nousresearch.com/docs retrieved 2026-10-28.
+CHECK: grep -c "autonomous agent" /root/troupe-standup/wizard-work/quill/hermes-quick-ref-draft-2026-10-28.md