Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/esaruoho/apple/imessagegit clone --depth 1 https://github.com/esaruoho/appleWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00088 | $0.00561 |
| Opus 5 | $0.00044 | $0.00280 |
| Sonnet 5 | $0.00018 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
imessage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/imessage
Send an iMessage to yourself (or anyone) from the terminal — text or files.
/imessage "yo yo yo hi hi hi"
/imessage file.pdf
/imessage --text "see attached" file.pdf
/imessage --to +358401234567 "hello"
/imessage --to [email protected] ~/Downloads/foo.shortcut
Detection
- If the positional argument is an existing file path → attach as file.
- Otherwise → send as text.
- Use
--textor--fileto force a mode explicitly.
Why files need a different path than text
tell application "Messages" to send (POSIX file "...") to buddy ... reliably no-ops on macOS Sequoia (the call succeeds but no attachment renders). The only working path is:
- Set the macOS clipboard to a file reference via Finder
open imessage://<buddy>to focus that thread- UI-script Cmd-V then Return via System Events
The CLI does all three transparently.
First-run setup
The first imessage <file> invocation triggers an Accessibility TCC prompt for the terminal app (Terminal, iTerm, or whatever your shell runs in). Accept it once — System Settings → Privacy & Security → Accessibility → add the terminal app. Subsequent calls are silent.
Default buddy
[email protected]. Override per-call with --to, or set IMESSAGE_TO in your shell profile.
Troubleshooting
- "UI-script paste failed: AppleEvent timed out" — System Events is wedged.
killall "System Events"to restart its daemon, retry. - File "sent" but no attachment — Messages's own Apple-Event handler was busy. Wait a few seconds and retry; the script has a
with timeoutguard so it won't hang forever. - Text-only sends fine, files fail — Accessibility permission missing for the terminal app.
Source: bin/imessage. See also: wiki/concepts/imessage-from-terminal.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 50 lines · 88 tokens per session scan A d68f7b4e0ca0
imessage is a command published in the GitHub repository esaruoho/apple (11 stars, last pushed 6d ago), licensed MIT. It adds 88 tokens to every session and 561 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.