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.
npx agentmods add skills/ssube/conclave/web-browsenpx skills add ssube/conclave --skill web-browsegit clone --depth 1 https://github.com/ssube/conclaveWrote 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.
[](https://agentmods.dev/skills/ssube/conclave/web-browse)<a href="https://agentmods.dev/skills/ssube/conclave/web-browse"><img src="https://agentmods.dev/badge/skills/ssube/conclave/web-browse.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.01173 |
| Opus 5 | $0.00025 | $0.00587 |
| Sonnet 5 | $0.00010 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
web-browse 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Browse Skill
Load URLs in a headless browser and extract visual, textual, or structural content.
Actions
Screenshot — Visual capture
python3 {baseDir}/browse.py screenshot <url> [options]
Options:
--output <path>— Save screenshot to file (default:/tmp/screenshot-<timestamp>.png)--width <px>— Viewport width (default: 1280)--height <px>— Viewport height (default: 800)--full-page— Capture full scrollable page, not just viewport--wait <ms>— Wait time after page load before capture (default: 2000)--selector <css>— Screenshot only a specific element
Text — Content extraction
python3 {baseDir}/browse.py text <url> [options]
Options:
--output <path>— Save text to file (default: stdout)--selector <css>— Extract text from specific element only--wait <ms>— Wait time after page load (default: 2000)--links— Include href URLs in output--max-length <chars>— Truncate output (default: 50000)
Inspect — Element discovery
Discover all interactive elements on a page — buttons, links, inputs, forms. Useful for debugging Playwright automation or understanding a page's structure.
python3 {baseDir}/browse.py inspect <url> [options]
Options:
--wait <ms>— Wait time after page load (default: 2000)--width <px>— Viewport width (default: 1280)--console— Capture and display browser console output--screenshot <path>— Also save a full-page screenshot--json— Output element data as JSON (for programmatic use)
Execute — Run JavaScript
Execute a JavaScript expression on a loaded page and return the result.
python3 {baseDir}/browse.py execute <url> "<script>" [options]
Options:
--wait <ms>— Wait time after page load (default: 2000)
Examples
# Screenshot a web page
python3 {baseDir}/browse.py screenshot "https://example.com" --output /tmp/example.png
# Full-page screenshot
python3 {baseDir}/browse.py screenshot "https://example.com" --full-page --output /tmp/site.png
# Extract text from a page
python3 {baseDir}/browse.py text "https://example.com/article" --max-length 10000
# Extract text with links
python3 {baseDir}/browse.py text "https://github.com/example/repo" --links
# Discover all interactive elements on a page
python3 {baseDir}/browse.py inspect "https://example.com/form"
# Inspect with console capture and screenshot
python3 {baseDir}/browse.py inspect "https://example.com" --console --screenshot /tmp/inspect.png
# Inspect and get JSON output for scripting
python3 {baseDir}/browse.py inspect "https://example.com/form" --json
# Execute JavaScript to extract specific data
python3 {baseDir}/browse.py execute "https://example.com" "document.querySelectorAll('img').length"
# Get page metadata via JS
python3 {baseDir}/browse.py execute "https://example.com" \
"JSON.stringify({title: document.title, links: document.querySelectorAll('a').length})"
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.
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.
- 4d ago First seen · 139 lines · 50 tokens per session scan A de08ccf3e2d2
web-browse is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,173 once invoked, about $0.0003 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.
Other skills, from other repositories
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
playwright
Browser automation, web scraping, E2E testing, and visual regression with Playwright. Covers 30+ patterns: login flows, form testing, responsive design checks, broken link validation, API mocking, data extraction, PDF generation, accessibility audits (axe-core), performance budgets (Lighthouse), visual diffing…
tlamatini-daily-chat-test
Run the daily automated Tlamatini chat regression — drive a visible Chrome via Playwright, log into agentpage.html, ask up to 1000 curated safe questions one-by-one (Multi-Turn ON, ACPX/Ask-Execs/Exec-Report/Internet OFF), wait for and qualify each answer (heuristic + LLM judge on failures), then write a dated report…
browser-qa
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
project-daily-chat-test-skill
The tlamatini-daily-chat-test Claude Code skill — Playwright/real-Chrome harness that asks 1000 curated questions to the Tlamatini chat daily and qualifies the answers.
sc:webapp-testing
Test a web app end-to-end with Playwright: drive real flows, assert on visible state, catch console/network errors, and do visual + RTL/Hebrew checks. Covers writing resilient selectors (roles/text over CSS), waiting on conditions (never sleeps), screenshot diffing, and a quick smoke pass before shipping. Activate…