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/madappgang/magus/core-apinpx skills add MadAppGang/magus --skill core-apigit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/core-api)<a href="https://agentmods.dev/skills/madappgang/magus/core-api"><img src="https://agentmods.dev/badge/skills/madappgang/magus/core-api.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 | $0.00034 | $0.07346 |
| Opus 5 | $0.00017 | $0.03673 |
| Sonnet 5 | $0.00007 | $0.01469 |
| Haiku 4.5 | $0.00003 | $0.00735 |
Grade A, and why
core-api 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 4d 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 — 735 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Use Core API
Reference for the MCP tools exposed by the Browser Use plugin: the upstream Browser Use set plus ten Magus-specific additions. All are accessed via mcp__browser-use__<tool_name>. The authoritative list is whatever the server registers at runtime, so check there rather than counting this table.
1. Quick Reference Table
| Tool | Purpose | Requires session_id? |
|---|---|---|
browser_navigate |
Navigate to URL (creates session) | No (creates it) |
browser_click |
Click element by DOM index | Yes |
browser_type |
Type text into an input element | Yes |
browser_get_state |
Get full DOM element map with indices | Yes |
browser_extract_content |
LLM-powered semantic content extraction | Yes |
browser_get_html |
Raw HTML (full page or CSS selector) | Yes |
browser_screenshot |
Capture viewport or full-page screenshot | Yes |
browser_scroll |
Scroll the page up, down, left, right | Yes |
browser_go_back |
Navigate back in browser history | Yes |
browser_list_tabs |
List all open tabs in a session | Yes |
browser_switch_tab |
Switch to a tab by tab_id | Yes |
browser_close_tab |
Close a specific tab | Yes |
browser_list_sessions |
List all active browser sessions | No |
browser_close_session |
Close session and release browser resources | Yes |
retry_with_browser_use_agent |
Autonomous LLM agent for complex tasks | No (creates session) |
browser_export_session |
Export cookies + localStorage to JSON file | Yes |
browser_import_session |
Restore session from exported JSON file | No (creates session) |
browser_run_script |
Run a standalone Python script as a subprocess (own browser) | No |
browser_evaluate |
Run JS in the live page and return its result (CDP) | No (uses current) |
browser_press_key |
Press a key/shortcut (e.g. Meta+a, Enter, Escape) |
No (uses current) |
browser_keyboard |
Batch keys + insert literal text via CDP | No (uses current) |
browser_focus |
Focus any element by CSS selector (incl. hidden inputs) | No (uses current) |
browser_doctor |
Preflight: Python / deps / Chromium / API keys | No |
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.
- 4d ago First seen · 735 lines · 34 tokens per session scan A 21bee9204c19
core-api is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 7,346 once invoked, about $0.0002 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
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.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.