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 skills add strikersam/autonomous-ai-agency --skill dev-browsergit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/dev-browser)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/dev-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/dev-browser/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.
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/dev-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/dev-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 96 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00075 | $0.01492 |
| Opus 5.5 | $0.00030 | $0.00597 |
| Sonnet 5.5 | $0.00015 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
dev-browser 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 1mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dev-browser — Browser Automation via Sandboxed JS
Installation
npm install -g dev-browser
dev-browser install # Downloads Playwright + Chromium
Add to .claude/settings.json to pre-approve all commands:
{"permissions": {"allow": ["Bash(dev-browser *)"]}}
Primary invocation styles
# Inline heredoc (most common)
dev-browser <<'EOF'
const page = await browser.getPage("main");
await page.goto("https://example.com");
console.log(await page.title());
EOF
# Run a .js file
dev-browser run script.js
# Named browser instance (persists across runs)
dev-browser --browser my-project < script.js
# Connect to existing Chrome (local debugging port)
dev-browser --connect http://localhost:9222 <<'EOF'
const page = await browser.getPage("main");
await page.goto("https://example.com");
EOF
# Auto-discover Chrome with remote debugging enabled
dev-browser --connect <<'EOF'
const page = await browser.getPage("main");
console.log(await page.title());
EOF
CLI flags
| Flag | Default | Description |
|---|---|---|
--browser NAME |
"default" |
Named daemon-managed browser instance |
--connect [URL] |
— | Connect to running Chrome (no URL = auto-discover) |
--headless |
— | Launch without visible window |
--ignore-https-errors |
— | Ignore self-signed TLS certificate errors |
--timeout SECONDS |
30 |
Max script execution time |
Subcommands
dev-browser run FILE # Run a JS file
dev-browser install # Install Playwright browsers (Chromium)
dev-browser browsers # List all managed browser instances
dev-browser status # Show daemon status
dev-browser stop # Stop daemon and all browsers
Sandbox environment
Scripts run in QuickJS WASM, NOT Node.js. These are NOT available:
require()/import()— no module loadingprocess— no process accessfs/path/os— no direct filesystem accessfetch/WebSocket— no direct network access__dirname/__filename— no path globals
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.
- 1mo ago First seen · 207 lines · 75 tokens per session scan A a9b7027b6c48
dev-browser is a skill published in the GitHub repository strikersam/autonomous-ai-agency (11 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,492 once invoked, about $0.0003 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.
Other skills, from other repositories
verify
How to run and drive this app to verify UI/server changes at runtime.
sidekick-audit
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
sidekick-test
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
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.
test-production
Runs bin/test-production.ps1 to acceptance-test a production (or prerelease) release of browser4-cli. Use when asked to run production tests, acceptance-test a release, or verify the published CLI.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.