Borrowing it
Nothing to install: this file belongs to carterlasalle/mac_messages_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/carterlasalle/mac_messages_mcp/main/.claude/skills/mac-messages/SKILL.mdgit clone --depth 1 https://github.com/carterlasalle/mac_messages_mcpWrote 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/carterlasalle/mac_messages_mcp/mac-messages)<a href="https://agentmods.dev/skills/carterlasalle/mac_messages_mcp/mac-messages"><img src="https://agentmods.dev/badge/skills/carterlasalle/mac_messages_mcp/mac-messages/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/carterlasalle/mac_messages_mcp/mac-messages"><img src="https://agentmods.dev/badge/skills/carterlasalle/mac_messages_mcp/mac-messages.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00090 | $0.03076 |
| Opus 5.5 | $0.00036 | $0.01230 |
| Sonnet 5.5 | $0.00018 | $0.00615 |
| Haiku 4.5 | $0.00009 | $0.00308 |
Grade A, and why
mac-messages 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 1mo 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mac Messages MCP
Call the mac-messages MCP server to read and search the local Messages
database, list conversations, resolve Contacts entries, fetch or search
attachments, create a contact, schedule a message, and send one outgoing
message through Messages.app.
Preconditions
The server runs on macOS only and reads ~/Library/Messages/chat.db plus the
Contacts/AddressBook databases.
- The host app or terminal needs Full Disk Access.
- Sending needs Automation permission for Messages.app, a signed-in Messages account, and Messages.app able to reach the recipient.
- Creating a contact needs Automation permission for Contacts.app.
- Permission failures surface as tool text such as
Operation not permittedorunable to open database file; they are not exceptions you can retry past.
On the first message-related task in a session, confirm the server can read its data before assuming a lookup result of "no messages" is real:
tool_check_db_access— Messages database.tool_check_addressbook— Contacts database.
Tool map
| Goal | Tool |
|---|---|
| Recent messages, filtered by contact, chat, date range, or unread | tool_get_recent_messages |
| Message text matching a phrase, scoped to a contact or chat | tool_fuzzy_search_messages |
| Every conversation with kind, counts, and last activity | tool_list_conversations |
| Block until a newer message arrives | tool_wait_for_new_messages |
| Contact name to send-ready number(s) | tool_find_contact |
| Send-ready group chat names and IDs | tool_get_chats |
| Attachment metadata by date, contact, or MIME type | tool_search_attachments |
| Text inside attachment contents | tool_search_attachment_contents |
| One attachment by ID | tool_get_attachment |
| Whether a recipient is reachable over iMessage | tool_check_imessage_availability |
| Diagnostics: Messages DB, AddressBook, contact count | tool_check_db_access, tool_check_addressbook, tool_check_contacts |
| Send one message now | tool_send_message |
| Queue a message for later | tool_schedule_message, tool_list_scheduled_messages, tool_cancel_scheduled_message |
| Create one Contacts entry | tool_create_contact |
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.
- 1mo ago First seen · 241 lines · 90 tokens per session scan A 82154ba09469
mac-messages is a skill published in the GitHub repository carterlasalle/mac_messages_mcp (343 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 3,076 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-07.
mac-messages compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mac-messagescarterlasalle/mac_messages_mcp | Skill | 343 | yesterday | MIT | A | 90 | Claude Code |
| imessage-inboxbenelser/imessage-tools | Skill | 3 | 14d ago | MIT | A | 9 | Claude Code |
| peon-ping-togglePeonPing/peon-ping | Skill | 5.1k | 18d ago | MIT | A | 58 | Claude Code |
| peon-ping-logPeonPing/peon-ping | Skill | 5.1k | 18d ago | MIT | A | 64 | Claude Code |
| planning-with-filesmxyhi/ok-skills | Skill | 509 | yesterday | Apache-2.0 | A | 117 | Claude Code |
| getting-starteddavekilleen/Dex | Skill | 512 | 8d ago | MIT | A | 70 | Claude Code, Codex |
| resume-builderdavekilleen/Dex | Skill | 512 | 8d ago | MIT | A | 12 | Claude Code, Codex |