gemini-worker

gemini-worker is a skill for Claude Code, Codex from Syysean/web-ai-skills. It costs 63 tokens per session (1,475 once invoked), scanned A, original, MIT.

A skill for sending prompts to Google Gemini through a browser and returning its response. It supports tasks such as questions, summaries, translations, rewrites, extraction, comparisons, brainstorming, and analysis.

In plain words
What is it for?
Starting the local browser, opening Gemini, submitting a prompt, waiting for the response, and returning the result with its task type and status.
Why use it?
It lets an AI agent delegate a prompt to Gemini and receive a structured result without requiring a Gemini login.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Starting the local browser, opening Gemini, submitting a prompt, waiting for the response, and returning the result with its task type and status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/syysean/web-ai-skills/gemini-worker
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 Syysean/web-ai-skills --skill gemini-worker
Clone the repo
git clone --depth 1 https://github.com/Syysean/web-ai-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 gemini-worker

README.md
[![agentmods](https://agentmods.dev/badge/skills/syysean/web-ai-skills/gemini-worker/github.svg)](https://agentmods.dev/skills/syysean/web-ai-skills/gemini-worker)
Your own site
<a href="https://agentmods.dev/skills/syysean/web-ai-skills/gemini-worker"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/gemini-worker/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 gemini-worker

Your own site · 80×15
<a href="https://agentmods.dev/skills/syysean/web-ai-skills/gemini-worker"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/gemini-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,475 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 $0.00063 $0.01475
Opus 5 $0.00032 $0.00737
Sonnet 5 $0.00013 $0.00295
Haiku 4.5 $0.00006 $0.00147

Measured 11d ago against content hash 56ce92075e3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gemini-worker 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 11d 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.

gemini-worker/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Worker

Send a prompt to Gemini via browser and return the response.

Environment

  • Browser: Chrome on localhost:9222 (managed by local-browser-tools)
  • Login: Not required — Gemini guest mode is confirmed working
  • Tools: browser-start.js, browser-nav.js, browser-eval.js, browser-screenshot.js

Input

prompt: string        # The text to send to Gemini
task_type: string     # qa | summary | translation | rewrite | extraction | comparison | brainstorming | analysis

Output

Always output this JSON block first:

{
  "site": "gemini",
  "task_type": "<task_type>",
  "status": "success | partial | error",
  "answer": "<extracted response text>",
  "retry_count": 0,
  "elapsed_ms": 0,
  "error_reason": null
}

Then follow with a short human-readable summary (2–3 sentences max).


Workflow

Step 1 — Start browser

node ~/.pi/agent/skills/local-browser-tools/browser-start.js

Expected: ✓ Chrome already running on :9222 or ✓ Chrome started on :9222

If fails: return error status, stop.


Step 2 — Navigate to Gemini

node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://gemini.google.com/app

After navigation, take a screenshot and verify:

  • Input box is visible
  • Page is NOT a login wall (a "Sign in" button in the top-right corner is normal and acceptable — guest mode works)

If a full-page login form appears with no input box: return error status, stop.


Step 3 — Locate input box

Try selectors in this order until one works:

  1. [aria-label="Enter a prompt for Gemini"]
  2. [contenteditable="true"][role="textbox"]
  3. div.ql-editor

Use browser-eval.js to check:

!!document.querySelector('[aria-label="Enter a prompt for Gemini"]')

If no selector works after 3 attempts: trigger retry.


Step 4 — Insert prompt

(function() {
  const input = document.querySelector('[aria-label="Enter a prompt for Gemini"]')
    || document.querySelector('[contenteditable="true"][role="textbox"]')
    || document.querySelector('div.ql-editor');
  if (!input) return "NOT_FOUND";
  input.focus();
  input.textContent = "";
  input.textContent = PROMPT_TEXT;
  input.dispatchEvent(new Event("input", { bubbles: true }));
  return input.textContent;
})()

Read the full file on GitHub · 215 lines

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. 11d ago First seen · 215 lines · 63 tokens per session scan A 56ce92075e3b

Subscribe to this mod's changes

gemini-worker is a skill published in the GitHub repository Syysean/web-ai-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 1,475 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.