What is browser-interaction?

A guide for automating browser tasks such as clicking, entering text, taking screenshots, and testing web flows.

Use it to navigate websites, fill forms, click controls, capture screenshots, and debug or test user journeys.

It gives browser interactions a repeatable pattern: inspect the current page, act on the right element, and verify the result.

browser-interaction — Skill for Claude Code by vladolaru

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 vladolaru/claude-code-plugins --skill browser-interaction

Clone the repo

git clone --depth 1 https://github.com/vladolaru/claude-code-plugins

Made for: Claude Code.

Or install pirategoat-tools, the plugin that ships this one along with the rest of its 22 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/browser-interaction/github.svg)](https://agentmods.dev/skills/vladolaru/claude-code-plugins/browser-interaction)

Your own site

<a href="https://agentmods.dev/skills/vladolaru/claude-code-plugins/browser-interaction"><img src="https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/browser-interaction/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vladolaru/claude-code-plugins/browser-interaction"><img src="https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/browser-interaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,783 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Tool Misuse · line 269
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.02783
Opus 5.5	$0.00014	$0.01113
Sonnet 5.5	$0.00007	$0.00557
Haiku 4.5	$0.00003	$0.00278

Measured 2mo ago against content hash 2e2ae3141617, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-interaction 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 2mo 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.

plugins/pirategoat-tools/skills/browser-interaction/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Interaction

Browser automation via MCP tools (chrome-devtools or playwright).

Prerequisites

Load browser MCP tools before any interaction:

ToolSearch query: "+chrome-devtools list pages snapshot navigate screenshot"

If chrome-devtools unavailable, fall back to playwright:

ToolSearch query: "+playwright browser snapshot navigate"

Tool Mapping

Action	Chrome DevTools	Playwright
List pages	`list_pages`	`browser_tabs`
Navigate	`navigate_page`	`browser_navigate`
Click	`click`	`browser_click`
Fill	`fill`	`browser_type`
Screenshot	`take_screenshot`	`browser_take_screenshot`
Snapshot	`take_snapshot`	`browser_snapshot`
Wait	`wait_for`	`browser_wait_for`

RULE 0: Fresh Snapshot Before Interaction

Every browser interaction follows this loop:

Navigate → Fresh Snapshot → Interact (using uid) → Verify
         ↑                                        │
         └────────────────────────────────────────┘

Element refs (uid="1_5") regenerate per snapshot. Old refs match DIFFERENT elements after navigation.

# WRONG: uid reused after navigation
take_snapshot()            # uid="1_42" → Save button
navigate_page(url="/foo")
click(uid="1_42")          # uid "1_42" may now match an unrelated element

# RIGHT: fresh snapshot after every navigation
navigate_page(url="/foo")
take_snapshot()            # fresh uids
click(uid=<new>)

Navigate:

mcp__chrome-devtools__navigate_page(type: "url", url: "http://localhost:8080/wp-admin/", timeout: 30000)

Snapshot → Interact:

mcp__chrome-devtools__take_snapshot()
mcp__chrome-devtools__click(uid: "1_42", includeSnapshot: true)
mcp__chrome-devtools__fill(uid: "1_15", value: "[email protected]")

Verify (see RULE 1 for screenshot selection):

mcp__chrome-devtools__take_screenshot(uid: "3_272")

RULE 1: Token-Efficient Interaction

Choose the cheapest tool for your goal:

Read the full file on GitHub · 275 lines

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.

2mo ago First seen · 275 lines · 35 tokens per session scan A 2e2ae3141617

Subscribe to this mod's changes

browser-interaction is a skill published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 2,783 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 2026-09-03.

Browser automation E2E testing Testing

browser-interaction next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
browser-interactionvladolaru/claude-code-plugins	Skill	8	5d ago	MIT	A	35	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	today	MIT	A	68	Claude Code, Codex
create-verification-skillget-bb/bb	Skill	5.3k	today	MIT	A	57	Claude Code, Codex
browser-qahashgraph-online/awesome-codex-plugins	Skill	1.6k	yesterday	Apache-2.0	A	58	Claude Code, Codex
webapp-testinganthropics/skills	Skill	192k	4d ago	none	A	35	Claude Code
test-electron-appPostHog/posthog-foss	Skill	730	today	MIT	A	112	Claude Code
smoke-testSkyvern-AI/skyvern	Skill	23k	today	AGPL-3.0	A	50	Claude Code, Codex