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 skills/dvdsgl/claude-imessage/imessagenpx skills add dvdsgl/claude-imessage --skill imessagegit clone --depth 1 https://github.com/dvdsgl/claude-imessageWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dvdsgl/claude-imessage/imessage)<a href="https://agentmods.dev/skills/dvdsgl/claude-imessage/imessage"><img src="https://agentmods.dev/badge/skills/dvdsgl/claude-imessage/imessage.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00026 | $0.01561 |
| Opus 5 | $0.00013 | $0.00781 |
| Sonnet 5 | $0.00005 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iMessage Management Skill
This skill provides comprehensive Messages app interaction capabilities through command-line tools.
Available Tools
All tools are located in .claude/skills/imessage/ and use either AppleScript or direct SQLite database access to interact with the Messages app.
Database vs AppleScript Approach
- Database tools (
*-db.sh): Read messages directly from the Messages SQLite database (~/Library/Messages/chat.db). More reliable and faster, supports full message history including sent messages with proper text extraction. - AppleScript tools (original): Use AppleScript automation. Sending works reliably, but reading messages may have permission issues on some macOS systems.
Recommended: Use database tools for reading (read-messages-db.sh, check-new-messages-db.sh) and AppleScript for sending (send-message.sh, send-to-chat.sh).
1. Read Messages from Database (read-messages-db.sh) ⭐ RECOMMENDED
Read messages directly from the Messages SQLite database. This is the most reliable method for reading message history.
Usage:
# Read recent messages by phone number
.claude/skills/imessage/read-messages-db.sh "1234567890" --limit 10
# Read recent messages (all conversations)
.claude/skills/imessage/read-messages-db.sh --limit 20
Features:
- Reads both incoming and outgoing messages
- Extracts text from outgoing messages (stored in attributedBody)
- Fast and reliable
- Shows formatted timestamps
- No permission issues
2. Check New Messages from Database (check-new-messages-db.sh) ⭐ RECOMMENDED
Check for recent incoming messages from the database. Used by the iMessage auto-reply daemon.
Usage:
# Check recent messages from specific number
.claude/skills/imessage/check-new-messages-db.sh "1234567890"
# Check all recent incoming messages
.claude/skills/imessage/check-new-messages-db.sh
Output Format:
MSG_ID: <unique_hash>
ROWID: <message_id>
DATE: <readable_timestamp>
TEXT: <message_text>
FROM: <phone_number>
CHAT: <chat_identifier>
---
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- check-new-messages-db.sh 2.2 KB runs code
- check-new-messages.sh 2.0 KB runs code
- daemon/imessage-auto-reply-daemon.sh 10 KB runs code
- daemon/README.md 10 KB
- get-message-attachments.sh 2.1 KB runs code
- list-conversations.sh 2.7 KB runs code
- read-messages-db.sh 2.9 KB runs code
- read-messages.sh 2.4 KB runs code
- send-file.sh 898 B runs code
- send-message.sh 1.7 KB runs code
- send-to-chat.sh 1.2 KB runs code
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.
- 5d ago First seen · 198 lines · 26 tokens per session scan A ea96797b1107
imessage is a skill published in the GitHub repository dvdsgl/claude-imessage (54 stars, last pushed 9mo ago), licensed MIT. It adds 26 tokens to every session and 1,561 once invoked, about $0.0001 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 skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.