browser-research-prose

browser-research-prose is a skill for Claude Code, Codex from modiqo/skillspec. It costs 28 tokens per session (469 once invoked), scanned A, original, Apache-2.0.

A browser-research skill for inspecting websites through a browser. It can observe rendered pages and collect evidence from what the page currently shows.

In plain words
What is it for?
Use it to open pages, click through interfaces, inspect content, take snapshots, and extract or verify information from websites.
Why use it?
It avoids relying on search snippets or downloaded page source when the important details depend on the visible page, navigation, or logged-in state.

Skill for Claude CodeCodex

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/modiqo/skillspec/prose_only
Any agent
npx skills add modiqo/skillspec --skill prose_only
Clone the repo
git clone --depth 1 https://github.com/modiqo/skillspec

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-research-prose

README.md
[![agentmods](https://agentmods.dev/badge/skills/modiqo/skillspec/prose_only.svg)](https://agentmods.dev/skills/modiqo/skillspec/prose_only)
Your own site
<a href="https://agentmods.dev/skills/modiqo/skillspec/prose_only"><img src="https://agentmods.dev/badge/skills/modiqo/skillspec/prose_only.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00028 $0.00469
Opus 5 $0.00014 $0.00234
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 5d ago against content hash 007be7ea7823, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browser-research-prose scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Do not use curl, static HTML fetches, or search snippets as substitutes for
docs/examples/why-skillspec-demo/prose_only/SKILL.md · 48 lines

What it actually says

Browser Research

Use this skill when the user asks you to browse a website, open a page, click through an interface, inspect page content, take a snapshot, extract evidence from a page, or verify what a page currently shows.

For browser tasks, use browser automation. Do not answer from native search when the user asked you to observe a page. Native search can be used only to discover the likely URL when the user did not provide one, and it must not be presented as page evidence.

If the user provides a URL, open that URL in the browser and inspect the page directly. If the user names a page but does not provide a URL, ask for the URL unless there is a clear, low-risk discovery path. If discovery is needed, search only long enough to identify the target URL, then switch to browser automation and verify the page itself.

Do not use curl, static HTML fetches, or search snippets as substitutes for browser evidence when the task depends on rendered page state, navigation, logged-in state, screenshots, dynamic content, or visible UI.

Before taking action, make sure a browser session is available and that network access is allowed. If a login, credential, or private workspace is needed, stop and ask before proceeding.

When the work is done, report what page was opened, what evidence was observed, which route was used, and any limitations. If there was URL discovery before browser inspection, say so clearly.

Good behavior examples:

  • "browse https://example.com and take a snapshot" means open that URL in the browser and report browser evidence.
  • "inspect the latest docs page but I do not have the URL" means discover the likely URL first, then verify the page in the browser.
  • "summarize search results about this company" is not a browser-inspection task unless the user asks to open or inspect a page.

This skill relies on the agent following the prose carefully. There is no separate validation command, scenario test, dependency preflight, or trace contract in this prose-only version.

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. 5d ago First seen · 48 lines · 28 tokens per session scan A 007be7ea7823

Subscribe to this mod's changes

browser-research-prose is a skill published in the GitHub repository modiqo/skillspec (739 stars, last pushed 27d ago), licensed Apache-2.0. It adds 28 tokens to every session and 469 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

v8-jit

V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…

vercel/next.js · 88 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens