add-emacs

name	add-emacs
description	Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NinjaClaw from within Emacs (Doom, Spacemacs, or vanilla). Uses a local HTTP bridge — no bot token or external service needed.

Add Emacs Channel

This skill adds Emacs support to NinjaClaw, then walks through interactive setup. Works with Doom Emacs, Spacemacs, and vanilla Emacs 27.1+.

What you can do with this

• Ask while coding — open the chat buffer (C-c n c / SPC N c), ask about a function or error without leaving Emacs
• Code review — select a region and send it with NinjaClaw-org-send; the response appears as a child heading inline in your org file
• Meeting notes — send an org agenda entry; get a summary or action item list back as a child node
• Draft writing — send org prose; receive revisions or continuations in place
• Research capture — ask a question directly in your org notes; the answer lands exactly where you need it
• Schedule tasks — ask Andy to set a reminder or create a scheduled NinjaClaw task (e.g. "remind me tomorrow to review the PR")

Phase 1: Pre-flight

Check if already applied

Check if src/channels/emacs.ts exists:

test -f src/channels/emacs.ts && echo "already applied" || echo "not applied"

If it exists, skip to Phase 3 (Setup). The code changes are already in place.

Phase 2: Apply Code Changes

Ensure the upstream remote

git remote -v

If an upstream remote pointing to https://github.com/OfirGavish/NinjaClaw-Nano.git is missing, add it:

git remote add upstream https://github.com/OfirGavish/NinjaClaw-Nano.git

Merge the skill branch

git fetch upstream skill/emacs
git merge upstream/skill/emacs

If there are merge conflicts on package-lock.json, resolve them by accepting the incoming version and continuing:

git checkout --theirs package-lock.json
git add package-lock.json
git merge --continue

For any other conflict, read the conflicted file and reconcile both sides manually.

This adds:

• src/channels/emacs.ts — EmacsBridgeChannel HTTP server (port 8766)
• src/channels/emacs.test.ts — unit tests
• emacs/NinjaClaw.el — Emacs Lisp package (NinjaClaw-chat, NinjaClaw-org-send)
• import './emacs.js' appended to src/channels/index.ts

If the merge reports conflicts, resolve them by reading the conflicted files and understanding the intent of both sides.

Validate code changes

npm run build
npx vitest run src/channels/emacs.test.ts

Build must be clean and tests must pass before proceeding.

Phase 3: Setup

Configure environment (optional)

The channel works out of the box with defaults. Add to .env only if you need non-defaults:

EMACS_CHANNEL_PORT=8766     # default — change if 8766 is already in use
EMACS_AUTH_TOKEN=<random>   # optional — locks the endpoint to Emacs only

If you change or add values, sync to the container environment:

mkdir -p data/env && cp .env data/env/env

Configure Emacs

The NinjaClaw.el package requires only Emacs 27.1+ built-in libraries (url, json, org) — no package manager setup needed.

AskUserQuestion: Which Emacs distribution are you using?

• Doom Emacs - config.el with map! keybindings
• Spacemacs - dotspacemacs/user-config in ~/.spacemacs
• Vanilla Emacs / other - init.el with global-set-key

Doom Emacs — add to ~/.config/doom/config.el (or ~/.doom.d/config.el):

;; NinjaClaw — personal AI assistant channel
(load (expand-file-name "~/src/NinjaClaw/emacs/NinjaClaw.el"))

(map! :leader
      :prefix ("N" . "NinjaClaw")
      :desc "Chat buffer"  "c" #'NinjaClaw-chat
      :desc "Send org"     "o" #'NinjaClaw-org-send)

Then reload: M-x doom/reload

Spacemacs — add to dotspacemacs/user-config in ~/.spacemacs:

;; NinjaClaw — personal AI assistant channel
(load-file "~/src/NinjaClaw/emacs/NinjaClaw.el")

(spacemacs/set-leader-keys "aNc" #'NinjaClaw-chat)
(spacemacs/set-leader-keys "aNo" #'NinjaClaw-org-send)

Then reload: M-x dotspacemacs/sync-configuration-layers or restart Emacs.

Vanilla Emacs — add to ~/.emacs.d/init.el (or ~/.emacs):

;; NinjaClaw — personal AI assistant channel
(load-file "~/src/NinjaClaw/emacs/NinjaClaw.el")

(global-set-key (kbd "C-c n c") #'NinjaClaw-chat)
(global-set-key (kbd "C-c n o") #'NinjaClaw-org-send)

Then reload: M-x eval-buffer or restart Emacs.

If EMACS_AUTH_TOKEN was set, also add (any distribution):

(setq NinjaClaw-auth-token "<your-token>")

If EMACS_CHANNEL_PORT was changed from the default, also add:

(setq NinjaClaw-port <your-port>)

Restart NinjaClaw

npm run build
launchctl kickstart -k gui/$(id -u)/com.NinjaClaw  # macOS
# Linux: systemctl --user restart NinjaClaw

Phase 4: Verify

Test the HTTP endpoint

curl -s "http://localhost:8766/api/messages?since=0"

Expected: {"messages":[]}

If you set EMACS_AUTH_TOKEN:

curl -s -H "Authorization: Bearer <token>" "http://localhost:8766/api/messages?since=0"

Test from Emacs

Tell the user:

1. Open the chat buffer with your keybinding (SPC N c, SPC a N c, or C-c n c)
2. Type a message and press RET
3. A response from Andy should appear within a few seconds

For org-mode: open any .org file, position the cursor on a heading, and use SPC N o / SPC a N o / C-c n o

Check logs if needed

tail -f logs/NinjaClaw.log

Look for Emacs channel listening at startup and Emacs message received when a message is sent.

Troubleshooting

Port already in use

Error: listen EADDRINUSE: address already in use :::8766

Either a stale NinjaClaw process is running, or 8766 is taken by another app.

Find and kill the stale process:

lsof -ti :8766 | xargs kill -9

Or change the port in .env (EMACS_CHANNEL_PORT=8767) and update NinjaClaw-port in Emacs config.

No response from agent

Check:

1. NinjaClaw is running: launchctl list | grep NinjaClaw (macOS) or systemctl --user status NinjaClaw (Linux)
2. Emacs group is registered: sqlite3 store/messages.db "SELECT * FROM registered_groups WHERE jid = 'emacs:default'"
3. Logs show activity: tail -50 logs/NinjaClaw.log

If the group is not registered, it will be created automatically on the next NinjaClaw restart.

Auth token mismatch (401 Unauthorized)

Verify the token in Emacs matches .env:

;; M-x describe-variable RET NinjaClaw-auth-token RET

Must exactly match EMACS_AUTH_TOKEN in .env.

NinjaClaw.el not loading

Check the path is correct:

ls ~/src/NinjaClaw/emacs/NinjaClaw.el

If NinjaClaw is cloned elsewhere, update the load/load-file path in your Emacs config.

After Setup

If running npm run dev while the service is active:

# macOS:
launchctl unload ~/Library/LaunchAgents/com.NinjaClaw.plist
npm run dev
# When done testing:
launchctl load ~/Library/LaunchAgents/com.NinjaClaw.plist

# Linux:
# systemctl --user stop NinjaClaw
# npm run dev
# systemctl --user start NinjaClaw

Agent Formatting

The Emacs bridge converts markdown → org-mode automatically. Agents should output standard markdown — not org-mode syntax. The conversion handles:

Markdown	Org-mode
**bold**	*bold*
*italic*	/italic/
~~text~~	+text+
`code`	~code~
```lang	#+begin_src lang

If an agent outputs org-mode directly, bold/italic/etc. will be double-converted and render incorrectly.

Removal

To remove the Emacs channel:

1. Delete src/channels/emacs.ts, src/channels/emacs.test.ts, and emacs/NinjaClaw.el
2. Remove import './emacs.js' from src/channels/index.ts
3. Remove the NinjaClaw block from your Emacs config file
4. Remove Emacs registration from SQLite: sqlite3 store/messages.db "DELETE FROM registered_groups WHERE jid = 'emacs:default'"
5. Remove EMACS_CHANNEL_PORT and EMACS_AUTH_TOKEN from .env if set
6. Rebuild: npm run build && launchctl kickstart -k gui/$(id -u)/com.NinjaClaw (macOS) or npm run build && systemctl --user restart NinjaClaw (Linux)