A command that sends one deep-research question to several online AI services, such as ChatGPT, Gemini, and Grok, through a logged-in browser. It collects the resulting reports and combines them into a consensus.

Use it to distribute a research prompt, gather multiple AI answers, preserve the source reports, and synthesize their findings.

It reduces dependence on one AI service and makes disagreements or shared conclusions across research reports easier to review. The original reports are also archived for reference.

dr-fanout — Skill for Claude Code by tonydzi/second-brain-starter-kit

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 tonydzi/second-brain-starter-kit --skill dr-fanout

Clone the repo

git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 248 skills, 3 agents, 1 plugin.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/dr-fanout/github.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/dr-fanout)

Your own site

<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/dr-fanout"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/dr-fanout/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/dr-fanout"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/dr-fanout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 11,807 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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: 4 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 YARA Match · line 17
YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
high Data Exfiltration · line 81
Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
medium Excessive Agency · line 34
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 153
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.

Model	Per session	Once invoked
Fable 5.1	$0.00083	$0.11807
Opus 5.5	$0.00033	$0.04723
Sonnet 5.5	$0.00017	$0.02361
Haiku 4.5	$0.00008	$0.01181

Measured 2d ago against content hash a1f0bba2ebb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dr-fanout scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (glm_probe.js, paste_verify.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **🔑 PROMPT TRANSPORT = `window.name`, not inline in javascript_tool.** A 12 KB prompt inlined for three vendors = ~37 KB of context plus an escaping risk. The working path, 0 tokens: `navigate` the tab to a local fil

skills/dr-fanout/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/dr-fanout — fan a Deep Research prompt out to 3+ LLMs and collect a consensus

The final stage of the Alpha Protocol, automated. Channels: ChatGPT (chatgpt.com) · Gemini (gemini.google.com) · Grok (grok.com). The mechanism = the Claude-in-Chrome MCP (the operator's live logged-in Chrome). Canon: [[alpha-protocol-recall-plus-dr]], decision-multi-llm-vendor-independence (heterogeneous consensus), [[chrome-autonomy-self-drive]], [[browser-work-on-peers-not-hub]] (strictly local).

⭐ What is already decided (the foundation, don't re-research) — updated 2026-07-16

The browser layer = Firefox-first (Decision Memo 02-Decisions/decision-2026-07-16-browser-automation-layer.md, DR26-07-16-HUB-01, confidence high). Chrome 127+ encrypts cookies (ABE) and since April 2026 binds sessions to the hardware (DBSC) → external cookie extraction is impossible without malware techniques. Firefox cookies are open (plaintext SQLite, DBSC not implemented) → a dedicated per-service Firefox profile + Playwright launch_persistent_context; a Chrome CDP attach is only a fallback for strictly-Chromium sites. The hub stack is already up: firefox_cookies.py (~/.claude/scripts/_shared/), profiles in <AUTOMATION_BROWSERS_ROOT>\Firefox\.
The live Chrome MCP (Claude-in-Chrome) remains the deliberate anti-ban path for actions that must look like "a human in a real session" (fb-post/x-post go that way). For dr-fanout the choice of execution path (live Chrome MCP vs headless Firefox+Playwright) is being clarified by an ongoing DR (see item 4).
A CLI workaround does NOT give you subscription Deep Research (verified 07-15): the Codex CLI / Gemini CLI only do web search; real consumer-subscription Deep Research cannot be triggered programmatically (Google's DR agent = a separate paid API). ⇒ the browser front end is the only road to subscription DR, so we make it anti-fragile instead of running away from it.
ToS risk, sharpest at Grok: the xAI AUP explicitly forbids automated/non-human access (risk of suspension/termination). There are no documented bans for automating YOUR OWN account, but the text is explicit → run the Grok channel at human pace; the decision to "keep / slow down / replace with claude.ai" belongs to the owner.
Grok — we simply keep using it (the owner's decision, 2026-07-16). The xAI AUP formally forbids automation, but enforcement hunts mass scraping (a $15k/1M-requests penalty), and our pace is naturally tiny (a few DRs per day at most) → we are not the target. The value of a third independent voice > the managed risk. Do NOT build limiters/throttling ([[ak47-simplicity]]) — Grok stays in the normal rotation; if the vendor itself pushes back (a captcha/challenge) — report it and skip that channel, no drama.

The execution path is HYBRID, per vendor (the owner's decision, 2026-07-16, "both ways"). Not one method for everyone:

Vendor	Path	Why
Grok	live Chrome MCP, human pace	ToS-sensitive → act like a human in a real session (maximum anti-ban, same as fb-post [[chrome-autonomy-self-drive]]); a headless bot here = maximum risk
ChatGPT	a dedicated headless Firefox profile (unattended) OR the live Chrome MCP	milder ToS; report extraction = backend JSON (works in both); for an unattended schedule → Firefox
Gemini	a dedicated headless Firefox profile (unattended)	two-phase (plan → Start research), tolerant of automation; candidate #1 for a fully unattended run
The principle: the harsher a vendor's ToS / ban sensitivity → the closer to "a live human in a session" (Chrome MCP); the more tolerant it is + the more unattended operation matters → the closer to a dedicated Firefox profile (Playwright persistent, the HUB-01 foundation).

✅ The orchestration is CONFIRMED by an external DR (DR26-07-14-FLEE-01, a ChatGPT+Grok synthesis 2026-07-16, digest in 03-Insights/insight-DR-DR26-07-14-FLEE-01-*). Both vendors independently: the core = a durable state machine + a job ledger, NOT "a long-lived autonomous browser agent"; a local ledger FSM is sufficient for a single-owner hub. Both independently advise NOT to build unattended Grok automation (the xAI AUP + enforcement is real: >52k bans in 2026, Reuters 07-15) → our matrix in item 6 already honours that (Grok only via live Chrome MCP, never in a daemon). Start the unattended schedule with 2 vendors: ChatGPT + Gemini.
Keep the vendor logic THIN and the orchestration SHARED. UI-specific repos die fast (chatgpt-automation-mcp archived 2026-04-27, browserbase/gemini-browser archived 2026-05-20). Everything vendor-specific = swappable "adapters" at the bottom; the state machine/ledger above them does not change.
⚠️ OPEN — the official path for Gemini: the Deep Research Agent / Interactions API (background=True + polling, collaborative_planning) — production-ready, and it removes the most fragile and slowest browser channel. BUT ⚠️ ADDED COMPLEXITY + unclear billing: is it included in the Ultra subscription or is it separate money (the ChatGPT report says "NOT the same free-with-subscription")? Check the billing BEFORE building ([[prefer-included-limits-before-paid-api]]) — if it is paid, don't set it up without the owner's "+".

Read the full file on GitHub · 172 lines

Files

What ships with it

2 files 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.

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.

2d ago Changed a1f0bba2ebb2
15d ago Changed · -1 lines ce5b1125cc88
20d ago Changed · -373 lines · -58 tokens per session b7e1a3f50f21
21d ago Changed 46fa9d16041c
29d ago Changed · +371 lines · +58 tokens per session af4bbcf5cb52
1mo ago Changed · +1 lines · -15 tokens per session fe60d503eb4e
1mo ago First seen · 174 lines · 98 tokens per session scan A da98688dbe7e

Subscribe to this mod's changes

dr-fanout is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 11,807 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation Claude Code Research ai-agents knowledge-management obsidian personal-knowledge-management second-brain

defuddle

Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…

AgriciDaniel/claude-obsidian · 61 tokens

last30days-plus

The last30days research skill with your own subscriptions added as extra research lanes, driven inside Agent Chrome. Grok (Private Chat) for X/Twitter, Perplexity Deep research (Incognito) for the web and news, and Meta's Muse for Facebook groups and Instagram (experimental). Runs the upstream last30days skill…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 152 tokens

muse-browser

EXPERIMENTAL. Research Facebook and Instagram (trends, Reels, creators, and conversations in Facebook groups you belong to) by asking Meta's own AI agent Muse (muse.ai) inside Agent Chrome, in a fresh side chat with a read-only instruction. Muse searches Facebook, Instagram and Threads posts your account can see and…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 159 tokens

perplexity-browser

Research with your own Perplexity subscription inside Agent Chrome instead of the paid Perplexity API. Quick cited web answers (Search) or Perplexity Deep research reports with dozens of sources, always in Incognito and with a neutral preface so your personalization and memory don't shape the answer. Use when asked to…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 140 tokens

facebook-personal-browser

Read your own signed-in personal Facebook inside Agent Chrome, strictly read-only. Open and read a specific post and its comments (fb-read), look inside a group you belong to, or check your own notifications or posts. Use when asked to "open this Facebook post", "read the comments on", "check my Facebook…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 151 tokens

grok-browser

Research what people are saying on X (Twitter) through Grok on grok.com inside Agent Chrome, always in Grok Private Chat so nothing lands in your Grok history, memory or model training. Grok searches X live (with engagement filters like minfaves) and returns posts with handles, dates and status URLs; the driver checks…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 149 tokens

dr-fanout