browser-research-agent

browser-research-agent is a skill for Claude Code, Codex from memi-design/design-skills. It costs 32 tokens per session (244 once invoked), scanned A, original, MIT.

A deprecated browser-based research workflow for collecting evidence, citations, and source-freshness information. It is retained for compatibility, while newer work should use the web-research skill.

In plain words
What is it for?
Use it only for existing workflows that require browser-backed research evidence, source URLs, access dates, screenshots, or a list of unverified claims.
Why use it?
It provides a structured way to record where claims came from and whether they still need verification. However, its own instructions identify it as an older compatibility option.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: mentions Codex; built for hermes-agent.

Good fit Use it only for existing workflows that require browser-backed research evidence, source URLs, access dates, screenshots, or a list of unverified claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/memi-design/design-skills/browser-research-agent
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 memi-design/design-skills --skill browser-research-agent
Clone the repo
git clone --depth 1 https://github.com/memi-design/design-skills

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/memi-design/design-skills/browser-research-agent/github.svg)](https://agentmods.dev/skills/memi-design/design-skills/browser-research-agent)
Your own site
<a href="https://agentmods.dev/skills/memi-design/design-skills/browser-research-agent"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/browser-research-agent/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 browser-research-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/memi-design/design-skills/browser-research-agent"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/browser-research-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 244 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 $0.00032 $0.00244
Opus 5 $0.00016 $0.00122
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00024

Measured 12d ago against content hash 28cd926a98d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

browser-research-agent 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 12d 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.

skills/browser-research-agent/SKILL.md · 30 lines

What it actually says

Browser Research Agent

Deprecated compatibility slug. Use web-research for new work. This payload remains self-contained for clients that installed the historical name.

Run browser-backed research agents that capture evidence, citations, and source freshness.

When to Use

Use this Note when a Memoire or Studio run needs browser research, web evidence, citation capture, source comparison.

Workflow

  1. Start with primary sources, then use secondary sources only to find more primary evidence.
  2. Record source URL, access date, claim, confidence, and whether the fact is time-sensitive.
  3. Use screenshots for visual UI claims and direct API responses for machine-readable facts.
  4. Separate quotes from paraphrases and keep quoted excerpts short.
  5. Finish with an evidence table and a list of claims that still need verification.

Sources

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. 12d ago First seen · 30 lines · 32 tokens per session scan A 28cd926a98d2

Subscribe to this mod's changes

browser-research-agent is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 244 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.

Related

Other skills, from other repositories

canon-favicons

Use when implementing favicons, touch icons, web app icons, or browser tab icons — the full set of sizes and formats needed for modern browsers, iOS home screen, Android, and PWA manifests. Trigger when the user mentions favicon, icon, apple-touch-icon, manifest icons, or browser tab icon.

Dragoon0x/canon · 68 tokens

browser-qa

A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.

hashgraph-online/awesome-codex-plugins · 58 tokens

verify

Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).

meursyphus/ssgoi · 26 tokens

memstack-development-webapp-testing

Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.

cwinvestments/memstack · 75 tokens

macos-harness

Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…

browser-use/macos-harness · 71 tokens

fetch-url-as-markdown

Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for…

CodeAlive-AI/ai-driven-development · 90 tokens