browser-login

browser-login is a skill for Claude Code, Codex from 0xNyk/oneclaw. It costs 0 tokens per session (879 once invoked), scanned C, original, MIT.

A browser-based procedure for signing into websites by inspecting each page and choosing the next action. It handles different login screens while keeping passwords and one-time codes out of chat and storage.

In plain words
What is it for?
Use it when an agent must open a website, complete email or password forms, handle login steps, and stop for extra verification when needed.
Why use it?
It removes the need for a separate login script for every website and reduces the risk of exposing credentials.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/0xnyk/oneclaw/browser-login
Any agent
npx skills add 0xNyk/oneclaw --skill browser-login
Clone the repo
git clone --depth 1 https://github.com/0xNyk/oneclaw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for browser-login

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xnyk/oneclaw/browser-login.svg)](https://agentmods.dev/skills/0xnyk/oneclaw/browser-login)
Your own site
<a href="https://agentmods.dev/skills/0xnyk/oneclaw/browser-login"><img src="https://agentmods.dev/badge/skills/0xnyk/oneclaw/browser-login.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00879
Opus 5 $0.00000 $0.00439
Sonnet 5 $0.00000 $0.00176
Haiku 4.5 $0.00000 $0.00088

Measured 6d ago against content hash 04a67aa24057, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

browser-login scanned grade C with 1 finding 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 6d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

- Always collect secrets using `secret_prompt`, then pass only the returned `secret://...` handle to `browser` actions.
src/skills/builtins/browser-login/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Login (Login Machine Loop)

Goal: log into an arbitrary website without provider-specific scripts by looping:

  1. observe current page
  2. classify what screen it is
  3. act using stable refs/semantic selectors
  4. repeat until logged in

Non-Negotiables (Security)

  • Never ask the user to paste passwords/OTP into chat.
  • Always collect secrets using secret_prompt, then pass only the returned secret://... handle to browser actions.
  • Do not store credentials in memory or write them to disk.
  • Prefer browser snapshot refs (@e1, @e2) and semantic browser find over brittle CSS selectors.

Setup

  1. browser tool must be enabled and the target domain must be in browser.allowed_domains.
  2. Start by opening the login URL (or the product URL that redirects to login).

Core Loop

Repeat up to ~20 iterations:

  1. Observe:

    • Call browser snapshot with interactive_only=true, compact=true.
    • If the snapshot is insufficient (missing context), take browser screenshot.
  2. Classify the screen (pick one):

    • credential_form: there are input fields and a primary submit.
    • email_first: email/username only with a next/continue.
    • password_only: password only (email is remembered).
    • choice_screen: account/workspace picker or auth method selector.
    • blocked_modal: cookie banner / modal blocking clicks.
    • mfa_otp: asks for a code (TOTP/SMS/email).
    • magic_link: instructs user to check email for a link.
    • captcha: challenge detected (cannot solve reliably inside this loop).
    • logged_in: you can see app content / avatar / logout / dashboard.
    • loading: spinners, disabled UI; wait and resnapshot.
  3. Act (handlers):

blocked_modal

  • Find the dismiss/accept button (often "Accept", "Agree", "Close", "X").
  • Use browser click by ref or browser find by text/role, then resnapshot.

credential_form / email_first / password_only

  • Identify required fields (email/username, password).
  • For each required secret:
    • Use secret_prompt:
      • kind="text" for email/username
      • kind="password" for password
    • Fill using browser fill where value is the returned secret://... handle.
  • Submit:
    • Click the primary submit button (ref or browser find by role/text).
  • If there is a second step (email -> password), resnapshot and repeat.

Read the full file on GitHub · 95 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 95 lines · 0 tokens per session scan C 04a67aa24057

Subscribe to this mod's changes

browser-login is a skill published in the GitHub repository 0xNyk/oneclaw (3 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 879 tokens. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

kaivyy/kabot · 17 tokens

codebase-classification

Classify codebases before modification to choose appropriate development approach.

gptme/gptme · 16 tokens

python-repl

Interactive Python REPL automation with common helpers and best practices.

gptme/gptme · 15 tokens

web-access

复杂 web 任务的方法论与跨 session 站点经验库。Use when:抓取反爬或需登录态的平台(小红书、微信公众号、微博、推特、知乎等)、 目标站点结构未知需要边看边探索、多来源交叉核实信息、分析页面里的图片/视频内容、并行调研多个独立来源、 或 websearch/webfetch 拿不到目标内容需要升级到真实浏览器时。 简单的已知 URL 抓取或单步页面操作(无登录/反爬因素)不需要加载本 skill——直接用 webfetch / browser 工具即可。.

open-octo/octo-agent · 139 tokens

knowledge-browser-automation

Covers 原生 Playwright Browser Tool、Chromium 进程池、Session Context、页面与 ARIA snapshot/ref 权威、同源安全、诊断/截图和 Web Browser 面板投影。 Navigate when: 修改 BrowserNavigate/Snapshot/Interact/Wait/Inspect/Page、浏览器安装、跨源阻断、页面并发、截图制品、Agent 浏览器可视化或资源回收。 Excludes: 被动 WebSearch/WebFetch(见 ../integration-and-workflow-tool-adapters/)、通用工具权限顺序(见…

echoVic/blade-code · 162 tokens

web-scrape

Extract structured data from web pages using CSS selectors. Use when the user asks to scrape a website, extract text or links from a page, parse HTML content, get data from a table, read article content, collect image URLs, or pull structured information from any web page. Keywords: scrape, extract, parse, crawl, get…

bug-ops/zeph · 82 tokens