frontend-explorer

frontend-explorer is a skill for Claude Code, Codex from martin1847/evolab. It costs 121 tokens per session (2,283 once invoked), scanned A, original, MIT.

An exploratory browser test that uses a real browser and a first-time-user perspective to find where people get stuck or do not understand a web product. Each finding includes the text seen on screen and screenshot evidence, ordered by how much it blocks progress.

In plain words
What is it for?
Use it for a UX pass, a new-user walkthrough, or exploratory testing of a running web application.
Why use it?
It reveals usability problems that scripted checks may miss because it does not start with predefined acceptance criteria. It focuses on confusion and obstacles rather than performance or code quality.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it for a UX pass, a new-user walkthrough, or exploratory testing of a running web application.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martin1847/evolab/frontend-explorer
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.

Any agent
npx skills add martin1847/evolab --skill frontend-explorer
Clone the repo
git clone --depth 1 https://github.com/martin1847/evolab

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 frontend-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/martin1847/evolab/frontend-explorer/github.svg)](https://agentmods.dev/skills/martin1847/evolab/frontend-explorer)
Your own site
<a href="https://agentmods.dev/skills/martin1847/evolab/frontend-explorer"><img src="https://agentmods.dev/badge/skills/martin1847/evolab/frontend-explorer/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.

agentmods 80×15 button for frontend-explorer

Your own site · 80×15
<a href="https://agentmods.dev/skills/martin1847/evolab/frontend-explorer"><img src="https://agentmods.dev/badge/skills/martin1847/evolab/frontend-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00121 $0.02283
Opus 5 $0.00060 $0.01141
Sonnet 5 $0.00024 $0.00457
Haiku 4.5 $0.00012 $0.00228

Measured yesterday against content hash 262f94555af2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

frontend-explorer 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (references/hold-spec.template.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/frontend-explorer/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

frontend-explorer — 探索型前端测试

脚本化测试回答「我已经想到的那件事还好使吗」。这里回答另一个问题:一个从没见过这个产品的人 打开它——在哪停住,在哪盯着屏幕不明白? 这两种失败形态就是全部产出;其余一切只为让这份产出诚实。

本 skill 对你的项目一无所知:应用在哪跑、怎么拿登录态、屏幕上的词什么意思,全部来自一份配置 (references/config.example.yaml)。想改本 skill 的文件去适配项目 = 那个事实该进配置。

前置条件

  1. 一份配置:复制 references/config.example.yaml 填好;含本机路径就别进版本库。做任何事之前先读它。
  2. 应用在跑且可达base_url 可访问、其 host 在 allowed_origins 里。没在跑就按配置 auth.setup 起, 不要自己发明启动方式。
  3. 浏览器驱动 = playwright-cli@playwright/cli,0.x 命令面会漂,项目钉版本):探索者经 Bash 调它, 每个 persona 一个命名会话 -s=<persona.session>,与项目自己的会话及彼此隔离。-s= 只隔离浏览器,不隔离账号: 本版一份 session_file = 一个账号 = 两 persona 串行(第一轮打通的账号第二轮无路可走);并行不在承诺面。不用 Playwright MCP、 不用别的驱动、不调外部 LLM API。工具选型与登录态原则与 cto-orchestration references/frontend-verify.md 同向(可选阅读,非依赖)。

流程(五步)

1 — 准备会话。 配置有 auth.setup.command 就跑它:它负责把应用带起来、签一个新用户、写出 auth.session_file(含入口 URL 与 storageState 路径),并停在前台。脚本里起它要让它独占一个进程组setsid 起、记下 那个 pgid),结束时给该组发 INT(kill -INT -- -<pgid>);只给 wrapper PID 发不起作用——bash 等前台子进程结束才跑 trap。

2 — 派发前先冒烟。 对每个 persona 的会话起浏览器、载入登录态、亲眼确认:

playwright-cli -s=<会话> open <entry_url>
playwright-cli -s=<会话> state-load <storageState 文件>
playwright-cli -s=<会话> goto <entry_url>
playwright-cli -s=<会话> find "<signed_in_marker.visible_text>"

看到标记文本才算登录态生效。没亲眼看到会话有效就派探索者 = 它报的每条 finding 都是「没登录」的伪影。 派第二个 persona 前再证一件事:它要走的失败 / 返工路径在这个栈上能触发(例:一次故意不合格的提交会被打回)—— fake 判定永不打回的栈,rework 步结构上探不到,steps_not_reached 那一行就是整轮的结论,别浪费一轮。 登录态只经文件路径进浏览器state-load)。禁止 cookie-set / cookie-get / cookie-list / localstorage-* / sessionstorage-*,禁止在 eval 正文里碰 cookie / token / localStorage——值上了命令行 或 stdout 就进了 transcript——一次性 session token 正是这样泄漏的。state-save 只许落 gitignored 的输出目录。

3 — 派发探索者。 配置里每个 persona 派一个独立子代理,brief 按 references/dispatch.md 组装, 自包含——子代理看不到本对话。席位形态:宿主的带 Bash 的子代理(如 Claude Code 的 Agent 工具,通用类型), 显式指定经济型模型(如 model: sonnet——这是耐心观察不是重推理,别让它默认继承你的高级模型);cwd 设为输出目录、 或独立 worktree 兜只读。探索者只读:驱动浏览器、只往 output.dir 写文件;不读不改不跑项目代码,不离开 allowed_origins

Read the full file on GitHub · 118 lines

Files

What ships with it

6 files 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. yesterday First seen · 118 lines · 121 tokens per session scan A 262f94555af2

Subscribe to this mod's changes

frontend-explorer is a skill published in the GitHub repository martin1847/evolab (6 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,283 once invoked, about $0.0006 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 2026-09-11.

Related

Other skills, from other repositories

webapp-testing

Verify a local web app in a real browser with page, element, click, form, console and screenshot evidence. Use after a build or UI change; do not implement features or publish deployments with this skill.

Prompthon-IO/agent-systems-handbook · 46 tokens

e2e-testing-standards

End-to-end testing with Playwright - browser automation, visual regression, test data management.

LiorCohen/sdd · 26 tokens

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.

affaan-m/ECC · 53 tokens

e2e-testing-patterns

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

wshobson/agents · 51 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

browser4-cli

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, test web applications, or extract information from web pages.

platonai/Browser4 · 52 tokens