agentleFS
Sign inStart free
ivanrvpereiraivanrvpereira/.agents/skills/auto/dev-browser/SKILL.md

dev-browser

Skill19 starsChanged 4 days agoApache-2.0View on GitHub

Drive a real Chrome with the dev-browser CLI. Use when the user asks to open or click through a site, fill a form, log in, take a screenshot, or test a web app in a browser.

  • Installs packages

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the pinned 1.0 release candidate for this Puppeteer API.

    line 16
  2. Very specific:

    Run dev-browser --help (full guide.

    line 19
  3. Very specific:

    Every distinct --browser <NAME> spawns a separate Chromium instance.

    line 37
  4. Very specific:

    If a running instance fits the task (check its named pages), reuse its name with --browser <NAME>.

    line 43
  5. Very specific:

    Prefer attaching to an already-open Chrome: when one is running with remote debugging enabled: use dev-browser --connect (auto-discovers).

    line 44

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

dev-browser

CLI for controlling a real Chrome with short Puppeteer scripts. One warm daemon; named pages persist between runs.

npm install -g dev-browser@1.0.0-rc.4
dev-browser --version
dev-browser install          # only if the first run says "No Chrome found"

Use the pinned 1.0 release candidate for this Puppeteer API. The unqualified npm package currently installs 0.2.9, which uses Playwright. Scripts run with the daemon's permissions. The script runtime is not a security sandbox.

Run dev-browser --help (full guide; dev-browser help <topic> for one section) before non-trivial work. Quick start:

dev-browser <<'EOF'
const page = await browser.getPage("main");        // named page persists across runs
await page.goto("https://example.com");            // default waitUntil: domcontentloaded
await page.snapshot({ interactive: true })         // ARIA tree with refs; last expression is printed
EOF
dev-browser -e 'const p = await browser.getPage("main"); await p.click("ref/e6"); await p.waitForLoad(); p.url()'

Gotchas: end lines with semicolons (a line starting with ( continues the previous one); return an object as ({ a, b }); page.click never waits (use waitForSelector first); page names are per browser (--headless and headed are separate Chromes and profiles); refs reset on navigation — re-snapshot; file paths resolve against your cwd (uploadFile, screenshot/pdf path); do not run parallel dev-browser calls against the same named page.

Reuse browser instances — do not open new ones

Every distinct --browser <NAME> spawns a separate Chromium instance. To avoid window sprawl:

  1. Before the first script of a session, check what already exists:
    dev-browser browsers
    If a running instance fits the task (check its named pages), reuse its name with --browser <NAME>.
  2. Prefer attaching to an already-open Chrome when one is running with remote debugging enabled: use dev-browser --connect (auto-discovers). Only fall back to daemon-launched browsers when no debuggable Chrome is available.
  3. Never invent a new --browser name unless the user explicitly asks for an isolated session/profile. Otherwise stick to the default instance (omit the flag) or an existing name from dev-browser browsers.
  4. Check project instructions (AGENTS.md) for a project-specific browser name before choosing one — some projects pin a named instance that holds required login sessions.
  5. Reuse named pages (browser.getPage("main")) instead of creating new pages for every script.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free