imsg
iMessage
Read and send iMessages and SMS from the terminal via the imsg CLI.
Setup (Panda)
- Messages.app signed in as: the agent Apple ID (see USER.md)
- Joel's iMessage address: see USER.md →
imessage - Full Disk Access must be granted to the terminal for read operations (
chats,history,watch) - Automation permission for Messages.app required for send
imsg sendreturns"sent"optimistically — this means AppleScript fired, not delivery confirmed
Commands
List chats
imsg chats --limit 10 --json
Read history
imsg history --chat-id <id> --limit 20 --attachments --json
Watch for new messages
imsg watch --chat-id <id> --attachments
Send
# By email (iMessage)
imsg send --to "user@example.com" --text "hello"
# By phone number (iMessage or SMS)
imsg send --to "+18005551234" --text "hello"
# With file attachment
imsg send --to "user@example.com" --text "see attached" --file /path/to/file.jpg
Delivery Notes
"sent"from CLI = AppleScript successfully handed off to Messages.app- "Not delivered" in Messages.app = actual delivery failure (auth issue, recipient offline, etc.)
- Full Disk Access missing = read commands fail with
permissionDenied; send still works via AppleScript - Messages appear as coming from the agent Apple ID, not from Joel
Sending to Joel
Joel's iMessage address is in USER.md (imessage field). Use it to notify him directly:
imsg send --to "<joel-imessage>" --text "your message"
Safety
- Read-only by default — use
chatsandhistorybefore sending - Always confirm recipient and message text before
imsg send --jsonflag preferred for all read operations (deterministic parsing)
Install
brew install steipete/tap/imsg
Credit
CLI by steipete. Adopted per ADR-0067.
More from joelhooks/joelclaw
cli-design
Design and build agent-first CLIs with HATEOAS JSON responses, context-protecting output, and self-documenting command trees. Use when creating new CLI tools, adding commands to existing CLIs (joelclaw, slog), or reviewing CLI design for agent-friendliness. Triggers on 'build a CLI', 'add a command', 'CLI design', 'agent-friendly output', or any task involving command-line tool creation.
129k8s
>-
88docker-sandbox
Create, manage, and execute agent tools (claude, codex) inside Docker sandboxes for isolated code execution. Use when running agent loops, spawning tool subprocesses, or any task requiring process isolation. Triggers on "sandbox", "isolated execution", "docker sandbox", "safe agent execution", or when working on agent loop infrastructure.
86joel-writing-style
Joel's writing voice and style guide for joelclaw.com content. Use when writing, editing, or reviewing any blog post, essay, book chapter, or prose content for joelclaw.com. Also use when asked to 'write like Joel,' 'match Joel's voice,' 'draft a post,' 'write content for the blog,' or 'review this for voice.' This skill captures Joel's specific writing patterns derived from ~90,000 words of published content spanning 2012–2026. Cross-reference with copy-editing and copywriting skills for marketing-specific copy.
81task-management
Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it.
54skill-review
Audit and maintain the joelclaw skill inventory. Use when checking skill health, fixing broken symlinks, finding stale skills, or running the skill garden. Triggers: 'skill audit', 'check skills', 'stale skills', 'skill health', 'skill garden', 'broken skill', 'skill review', 'fix skills', 'garden skills', or any task involving skill inventory maintenance.
49