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 Plocr/Reasonix-computer-use --skill web-navigatorgit clone --depth 1 https://github.com/Plocr/Reasonix-computer-useWrote 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/plocr/reasonix-computer-use/web-navigator)<a href="https://agentmods.dev/skills/plocr/reasonix-computer-use/web-navigator"><img src="https://agentmods.dev/badge/skills/plocr/reasonix-computer-use/web-navigator/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/plocr/reasonix-computer-use/web-navigator"><img src="https://agentmods.dev/badge/skills/plocr/reasonix-computer-use/web-navigator.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 | $0.00030 | $0.00382 |
| Opus 5.5 | $0.00012 | $0.00153 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
web-navigator 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.
What it actually says
Web Navigator — 浏览器自动化
你是 Reasonix Web 自动化 Operator。Web 场景统一通过 web_navigator 工具路由。
工具
| 工具 | 作用 |
|---|---|
web_navigator(operation="navigate") |
路由 URL 导航到 Playwright MCP 或 mcp-chrome |
web_navigator(operation="snapshot") |
获取页面 Accessibility Tree 快照 |
web_navigator(operation="action") |
路由浏览器操作（click、fill、type、press_key、hover） |
路由策略
| 场景 | 后端 | 说明 |
|---|---|---|
| 公开网站 | Playwright MCP（默认） | 隔离浏览器实例，基于 Accessibility Tree，纯净自动化 |
| 企业内网 | mcp-chrome（可选） | 复用用户浏览器登录态，use_chrome=true |
执行流程
- 导航 —
web_navigator(operation="navigate", url="...")获取路由建议。 - 快照 —
web_navigator(operation="snapshot")→ 实际调用mcp__playwright__take_snapshot。 - 操作 —
web_navigator(operation="action", action_type="click", uid="...")→ 实际调用mcp__playwright__click。
坐标
Web 场景使用 Accessibility Tree 的 uid（元素引用），不使用像素坐标。
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 · 34 lines · 30 tokens per session scan A 28c4a12424b4
web-navigator is a skill published in the GitHub repository Plocr/Reasonix-computer-use (43 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 382 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 2026-08-30.
Other skills, from other repositories
macos-harness
Read and operate the apps on this Mac from the shell. Use it when a task needs an app's UI and no API, CLI or purpose-built tool can do it.
nova-grounding
AX-first reading and grounded activation workflow for Nova desktop automation on macOS and Windows. Use for reading UI, clicking controls, OCR fallback, screenshots, and coordinate input without guessing.
computer-use-macos
Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
computer-use
Linux/X11 desktop control — inspect, click, type into visible windows via AT-SPI + xdotool. Returns @eN refs from the focused window's accessibility tree.
fill-form
Fill out web forms with human-like anti-detection typing. Applications, registration, checkout, surveys, contact forms. Use when: "fill out form", "complete application", "register on", "submit form", "fill in details", "checkout", "sign up on".
learn-platform
Discover how to automate a new app or website. Explore UI elements, scrape docs, build selector references. Use when: "learn how to automate", "explore the UI of", "map the interface", "discover selectors", "build reference for", "what can you do in this app", "how does this app work", "explore app".