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 skills add wende/macbeth --skill messagesgit clone --depth 1 https://github.com/wende/macbethWrote 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/wende/macbeth/messages)<a href="https://agentmods.dev/skills/wende/macbeth/messages"><img src="https://agentmods.dev/badge/skills/wende/macbeth/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/wende/macbeth/messages"><img src="https://agentmods.dev/badge/skills/wende/macbeth/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 | $0.00014 | $0.01761 |
| Opus 5.5 | $0.00006 | $0.00704 |
| Sonnet 5.5 | $0.00003 | $0.00352 |
| Haiku 4.5 | $0.00001 | $0.00176 |
Grade A, and why
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Messages.app Automation
Connect
connect_app({ name: "Messages" })
Layout
Messages has a two-pane layout: conversation list (left) and transcript (right).
- Window title reflects the currently open conversation's contact name.
- The window identifier is always
SceneWindow.
Key Elements
Toolbar
| Query | Label | Action |
|---|---|---|
[{role:"window"}, {role:"toolbar"}, {role:"button"}] |
Compose | Start new conversation |
[{role:"window"}, {role:"toolbar"}, {role:"menu_button", index:0}] |
filter | Filter: Messages / Spam / Recently Deleted |
[{role:"window"}, {role:"toolbar"}, {role:"menu_button", index:1}] |
Start FaceTime | Call menu |
Search
[{"role":"window"}, {"role":"group", "identifier":"CKConversationListCollectionView"}, {"role":"text_field"}]
Label: "Search". Use fill to type a search query.
Conversation List
Container:
[{"role":"window"}, {"role":"group", "identifier":"ConversationList"}]
Each conversation is a text element. Iterate with index:
[{"role":"window"}, {"role":"group", "identifier":"ConversationList"}, {"role":"text", "index": N}]
- Pinned contacts come first (indices 0, 1, 2, ...). Label format:
"Name, Pinned" - Regular conversations follow. Label format:
"Name, Preview text, Date"
The label field contains all info — contact name, last message preview, and timestamp are comma-separated.
To open a conversation, the user must click it manually — see Gotchas below.
Conversation Title
[{"role":"window"}, {"role":"button", "identifier":"ConversationTitle"}]
Shows the currently open contact's name in label. Click to view contact details.
Message Transcript
Container:
[{"role":"window"}, {"role":"group", "identifier":"TranscriptCollectionView"}]
Two types of children:
Date/time separators — text elements. Iterate with index:
[..., {"role":"text", "index": N}]
Label examples: "Nov 6, 2022 at 16:30", "Sun, Mar 1 at 00:50"
What ships with it
1 file 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.
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 · 185 lines · 14 tokens per session scan A 0e00e56d5d68
messages is a skill published in the GitHub repository wende/macbeth (4 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 1,761 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-delegation
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
manage-lounge-history
Review, correct or delete a signed-in user's logged visits and reviews. Requires OAuth with the write scope.
track-lounge-visits
Log a lounge visit, write or edit a review, and manage a wishlist on behalf of a signed-in user. Requires OAuth with the write scope.
lounge-wishlist-and-passport
Show a signed-in user's profile, lounge passport stats and wishlist, and add or remove wishlist lounges. Requires OAuth.
shortcuts-cli
DEPRECATED — macOS Shortcuts capability has been absorbed into the Switchboard plugin. Use the switchboard-usage skill instead (runshortcut, viewshortcut, shortcutsusage MCP tools, plus the switchboard shortcuts CLI). Do not trigger this skill; if a request mentions running, listing, or viewing macOS Shortcuts, defer…
openclaw-telegram-bot
Telegram bot toolkit MCP server with 5 tools for AI agents. Use when: (1) 'send a message to Telegram' or 'notify me on Telegram', (2) 'send an alert' or 'notify on error', (3) 'get latest Telegram messages' or 'check for commands', (4) 'set bot commands menu', (5) 'send daily report to Telegram'. TelegramBridge…