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 bulutarkan/mac-mcp --skill 1.0.0git clone --depth 1 https://github.com/bulutarkan/mac-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/bulutarkan/mac-mcp/1.0.0)<a href="https://agentmods.dev/skills/bulutarkan/mac-mcp/1.0.0"><img src="https://agentmods.dev/badge/skills/bulutarkan/mac-mcp/1.0.0/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/bulutarkan/mac-mcp/1.0.0"><img src="https://agentmods.dev/badge/skills/bulutarkan/mac-mcp/1.0.0.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 | $0.00034 | $0.00466 |
| Opus 5.5 | $0.00014 | $0.00186 |
| Sonnet 5.5 | $0.00007 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
browser-forms 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 3d 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
Browser forms, comments and long pages
Mac MCP has one-action shortcuts for the browser work agents repeat most. Use them instead of observing and acting one field or one step at a time.
Fill a form: one browser_act action
browser_observethe tab once. When it sees form fields it returnsfill_template, a ready{type:'fill', values:{...}}action with every field label.- Put the values in and send it as one
browser_act:{type:'fill', values:{'Full name': 'Ada', 'Country': 'Turkey', 'I accept the terms': true}}- Text boxes are typed; native and custom dropdowns pick the option; checkboxes and radios take true or false and are left alone when already right.
- Fields go in order. A field that appears after an earlier choice (country, then state) is awaited.
- A field that is not found is listed in
failed_fields; the others are already filled. Fill only the missing ones next time.
- Do not press Submit unless the task asks for it.
Post a comment or reply: one action
{type:'post', text:'...'} for the page's comment box, or
{type:'post', text:'...', within:'a phrase only that comment has'} for a reply. It opens the
reply box with that comment's own Reply button, types, presses the box's submit button and
confirms the text is on the page.
posted: truemeans it is published.POST_NOT_CONFIRMED(posted: null) means the button was pressed but the text did not show up: check the page before posting again; never post twice blindly.
Read a long page or thread
browser_observe reads what is on screen. To read a whole thread, send one
browser_act with {type:'scan'}: it scrolls and collects the items in one call.
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.
- 3d ago First seen · 38 lines · 34 tokens per session scan A ae1e3bced4bd
browser-forms is a skill published in the GitHub repository bulutarkan/mac-mcp (83 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 466 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 2026-10-13.
Other skills, from other repositories
clawdcursor
FALLBACK ONLY — do not invoke unless you have already ruled out (1) a native API (Gmail API, GitHub API, Slack API …), (2) a CLI (git, gh, aws, npm, curl …), (3) direct file editing, and (4) existing browser automation (Playwright, Puppeteer). Only when all four are unavailable or have already failed should you use…
reverse-search-video-frame
Reverse-search a captured video point and verify candidate identity against source appearance, readable text and page context before reporting a match.
macbeth
How to drive macOS apps with Macbeth MCP tools — discovery, locators, actions, menus, screenshots/OCR, handles, and fallbacks.
safari
Navigate, search, click links, read content, and manage tabs in Safari.
electron
Automate Electron apps (Slack, VS Code, Discord, etc.) whose UI is Chromium web content exposed through the Accessibility API.
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 14 tools: SearXNG + Exa AI search, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search, and service health. Trigger…