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/johnkozaris/web-interact-plugin/modenpx skills add johnkozaris/web-interact-plugin --skill modegit clone --depth 1 https://github.com/johnkozaris/web-interact-pluginWhat 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 | $0.00046 | $0.00358 |
| Opus 5 | $0.00023 | $0.00179 |
| Sonnet 5 | $0.00009 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
mode 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.
What it actually says
mode
Switch the browser engine used by web-interact.
Usage
# Show current mode
web-interact mode
# Switch to default (Playwright — standard automation)
web-interact mode default
# Switch to assistant (Patchright — removes automation flags)
web-interact mode assistant
Modes
| Mode | Engine | Automation banner | Humanize | Best for |
|---|---|---|---|---|
default |
Playwright | Visible | Off (use --humanize to enable) |
Your own apps, testing, development |
assistant |
Patchright | Hidden | Auto-enabled | Sites with bot detection, login flows |
Assistant mode auto-enables --humanize: natural random delays between clicks (200-600ms),
keystrokes (80-200ms per char), field focus (500-1200ms), and form actions. Timing is biased
toward the fast end of human ranges. You can also use --humanize with default mode on any command.
What happens on switch
- Running daemon and browsers are stopped
~/.web-interact/is cleaned (full reset)- Mode is saved to
~/.web-interact/mode - Next command auto-reinstalls the correct engine
The switch takes a few seconds. No manual setup needed after.
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 · 46 lines · 46 tokens per session scan A 9b7da6fda6c1
mode is a skill published in the GitHub repository johnkozaris/web-interact-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 358 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
fanqie-publisher
Publish prepared novel chapters from local Markdown files to the Fanqie Novel writer web backend via browser automation. Use when the user wants to upload chapters, continue publishing unpublished chapters, save or reuse login state, or schedule Fanqie chapter releases from a local directory.
chrome-control
Use when debugging web applications, diagnosing page errors, inspecting console output, or capturing screenshots via Chrome DevTools Protocol (CDP).
firefox-control
Use when you need to automate Firefox via WebDriver BiDi — tab listing, JS evaluation, screenshots, DOM helpers. TEST TOOL — Firefox sets navigator.webdriver=true.
xiaohongshu-ops
把 Hermes Agent 变成你的小红书运营助手 — 首页分析、账号诊断、选题灵感、内容创作、自动发布、评论回复、爆款复刻、知识库沉淀。全链路 SOP 覆盖，基于浏览器自动化（CDP）。.
platform-data-explorer
通用平台探索 Skill。使用 DataSaver Chrome MCP 工具对目标平台（URL/页面/模块）进行系统性探索，发现该平台可以做哪些用户操作类和数据提取类 Skill，输出 Skill 提案清单供用户确认，确认后按类型分流创建：API取数类调用 api-skill-builder，浏览器操作类调用 chrome-workflow-build。.
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.