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/wende/macbeth/messagesnpx skills add wende/macbeth --skill messagesgit clone --depth 1 https://github.com/wende/macbethWhat 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 | $0.00014 | $0.01761 |
| Opus 5 | $0.00007 | $0.00881 |
| Sonnet 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 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.
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.
- 2d ago First seen · 185 lines · 14 tokens per session scan A 0e00e56d5d68
messages is a skill published in the GitHub repository wende/macbeth (3 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 1,761 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 2026-08-31.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
smart-search
基于 opencli 命令的智能搜索路由器。当用户想要使用 OpenCLI、CLI 或 API 搜索、查询、查找或研究信息时，尤其是涉及指定网站、社交媒体、技术资料、新闻、购物、旅游、求职、金融或中文内容时，务必使用此 skill.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…