gemini-deep-research

gemini-deep-research is a skill for Claude Code from terrylica/cc-skills. It costs 35 tokens per session (1,726 once invoked), scanned A, original, MIT.

A browser-driven way to run Google's Gemini Deep Research, which produces long research reports with cited sources. It uses a logged-in Chrome session and Playwright to control the browser.

In plain words
What is it for?
Use it to investigate a topic and obtain a cited Markdown report. It requires Chrome's remote debugging mode, a Gemini Advanced login, and Playwright.
Why use it?
It removes the need to manually run and collect a long-form research task in Gemini. It also gathers the result and its source citations into a report.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the cc-skills plugin — 183 skills, 1 hook, 2 plugins shipped together

Good fit Use it to investigate a topic and obtain a cited Markdown report. It requires Chrome's remote debugging mode, a Gemini Advanced login, and Playwright.

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

Made for: Claude Code.

Or install cc-skills, the plugin that ships this one along with the rest of its 183 skills, 1 hook, 2 plugins.

Its marketplace also offers this one on its own, as the plugin gemini-deep-research/plugin install gemini-deep-research after adding the marketplace above.

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-deep-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/research.svg)](https://agentmods.dev/skills/terrylica/cc-skills/research)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/research"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,726 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 14 findings, up to high

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 →

  • high Tool Misuse · line 59
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Rogue Agent · line 187
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Rogue Agent · line 7
    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.
  • medium MCP Rug Pull · line 23
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 42
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 45
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 48
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 54
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 59
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 58
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 59
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 70
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 166
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 108
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00035 $0.01726
Opus 5 $0.00017 $0.00863
Sonnet 5 $0.00007 $0.00345
Haiku 4.5 $0.00003 $0.00173

Measured 3d ago against content hash 42d03df4eaa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gemini-deep-research 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 3d 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.

plugins/gemini-deep-research/skills/research/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Deep Research

Run long-form research queries through Google's Gemini Deep Research via browser automation (Playwright CDP). Produces 40k+ char markdown reports with source citations.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Prerequisites

  1. Chrome with debug port: Must be running with --remote-debugging-port=9222
  2. Gemini Advanced subscription: Logged into gemini.google.com in the debug Chrome
  3. playwright-core: bun add -g playwright-core (or project-local)
  4. Runtime: Use npx tsx (not bun run) — Bun's CDP connectOverCDP times out; Node.js connects in <1s

Launch Chrome (if not running)

/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
  --remote-debugging-port=9222 \
  --user-data-dir="/tmp/gemini-research-profile" \
  "https://gemini.google.com/app" &

Then log in manually with a Gemini Advanced account.

Usage

CLI (direct)

# Health check — verify Chrome CDP + Gemini login
npx tsx {{skill_dir}}/scripts/research.ts --health

# Basic research (runs preflight automatically)
npx tsx {{skill_dir}}/scripts/research.ts "your research query"

# Save to specific file
npx tsx {{skill_dir}}/scripts/research.ts \
  --output /tmp/report.md \
  --timeout 45 \
  "comprehensive analysis of quantum computing error correction 2025-2026"

# Auto-save to directory (creates {date}-{slug}.md)
npx tsx {{skill_dir}}/scripts/research.ts \
  --output-dir ~/.claude/automation/gemini-deep-research/output \
  "your query"

# Without auto-confirming plan (lets you review first)
npx tsx {{skill_dir}}/scripts/research.ts --no-confirm "query"

Programmatic (import)

import { GeminiDeepResearchClient } from "{{skill_dir}}/scripts/client.js";

const client = new GeminiDeepResearchClient({
  cdpUrl: "http://127.0.0.1:9222",
  maxResearchTimeMs: 30 * 60 * 1000,
  autoConfirm: true,
  onProgress: (msg) => console.log(msg),
});

await client.init();
const result = await client.research("your query");
// result.report — full markdown report (40k+ chars)
// result.plan — research plan text
// result.completed — boolean
// result.durationMs — execution time
// result.shareLink — Gemini share URL (if Firecrawl enabled)
await client.close();

Read the full file on GitHub · 190 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. 3d ago First seen · 190 lines · 35 tokens per session scan A 42d03df4eaa7

Subscribe to this mod's changes

gemini-deep-research is a skill published in the GitHub repository terrylica/cc-skills (62 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,726 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 2026-09-05.

Related

Other skills, from other repositories

gs-skillify

Codify a successful gstack scrape/browser flow into a permanent browser-skill on disk (scrape-specific). CARL TRIGGERS: make this a skill, skillify, turn into a skill, save this workflow, capture this pattern. SOURCE: garrytan/gstack/skillify, integrated as gs-skillify on 2026-05-29.

YousefNabil-SOC/claude-apex · 81 tokens

Instagram Access

Permanent capability skill for authenticated Instagram data extraction using instaloader and a reusable session cookie file.

YousefNabil-SOC/claude-apex · 21 tokens

gcp-setup

Automates Google Cloud Console setup via browser. Use when the user wants to set up a GCP project, enable APIs, create service accounts, configure IAM, set up billing, configure OAuth, set up firewall rules, or deploy to Cloud Run/App Engine/GKE. Also use when the user says "set up GCP", "configure Google Cloud"…

N-O-P-E/nope-marketplace · 161 tokens

search-console

Audit Google Search Console via browser. Use when the user says "check Search Console", "what's wrong with my domain", "why aren't my pages indexed", "SEO audit", "sitemap issues", or wants to investigate indexing problems, Core Web Vitals, structured data errors, or merchant listing issues. Opens GSC in Chrome, reads…

N-O-P-E/nope-marketplace · 83 tokens

cloudflare-connect

Adds a subdomain to a Cloudflare-managed zone and wires it to a hosting platform (Railway, Vercel) via browser automation. Use when the user wants to point a subdomain at a Railway service, Vercel project, or other hosting platform. Also use when the user says "add a subdomain", "connect domain to Railway/Vercel"…

N-O-P-E/nope-marketplace · 169 tokens

playwright-visual-testing

Browser automation, visual testing, and screenshot validation using Playwright MCP server for accelerated web development. Master visual regression testing, automated UI testing, and cross-browser validation.

manutej/luxor-claude-marketplace · 39 tokens