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 nicobailon/surf-cli --skill deep-x-researchgit clone --depth 1 https://github.com/nicobailon/surf-cliWrote 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/nicobailon/surf-cli/deep-x-research)<a href="https://agentmods.dev/skills/nicobailon/surf-cli/deep-x-research"><img src="https://agentmods.dev/badge/skills/nicobailon/surf-cli/deep-x-research/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/nicobailon/surf-cli/deep-x-research"><img src="https://agentmods.dev/badge/skills/nicobailon/surf-cli/deep-x-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.01309 |
| Opus 5.5 | $0.00030 | $0.00524 |
| Sonnet 5.5 | $0.00015 | $0.00262 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
deep-x-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 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep X Research
Research a topic across X by putting Grok to work from multiple angles — it runs keyword and semantic X searches and watches videos natively — then deliver categorized findings where every claim is traceable to a post URL.
Requires: surf installed and connected (surf doctor), Chrome logged into x.com. Command reference: the surf skill or surf --help.
Quota: X caps Grok requests (typically 15 per 20 hours on a standard plan). Every surf grok call spends one. Budget the session before the first query and make each query do multi-angle work — never spend a request on what a quota-free step can answer.
Steps
1. Decompose the topic and budget the queries
Break the topic into angles: showcases/examples, techniques & tutorials, tools, notable creators, community discussion — adapt to the topic. Plan a Grok budget of 4-8 queries covering every angle (combine related angles into one query rather than spending two). Done when each angle is assigned to a budgeted query.
2. Grok sweep
Run the budgeted queries sequentially. Engineer each so Grok does the fan-out internally and returns traceable sources:
# Broad pass — force multi-angle search and URLs
surf grok "Do deep research on TOPIC on X. Search both latest and top posts, keyword and semantic. Return the most relevant posts with full post URLs (x.com/user/status/ID) and a one-line description of each."
# Focused passes — one per remaining angle group
surf grok "TOPIC on X: tutorials, techniques, and the tools people use. Include post URLs for every example."
# Deepest pass — spend DeepSearch on the highest-value angle
surf grok "TOPIC: notable creators, how the trend is evolving, and the standout posts of the last 6 months. Post URLs required." --deep-search
Record every post Grok cites: author, one-line gist, full https://x.com/USER/status/ID URL. If a response gives claims without URLs, the next query in the budget re-asks for sources — never leave an angle sourceless. Done when every planned angle has been queried and the final response adds no new relevant posts, or the budget is spent.
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 · 107 lines · 76 tokens per session scan A 568ae39f6925
deep-x-research is a skill published in the GitHub repository nicobailon/surf-cli (641 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,309 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 2026-08-30.
Other skills, from other repositories
core
Core chrome-use usage guide. Read this before running any chrome-use commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple…
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
canvas
Drive canvas / WebGL / game UIs that paint to a with no DOM or accessibility node — game boards, voice-room mic seats, map tiles, 3D viewers, design canvases (Figma/mockitt), HUDs. Use when snapshot/find/eval querySelector return no ref for something clearly on screen, when the label shows in get text but has no @ref…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using chrome-use via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
sessions
Run multiple isolated browser sessions in parallel (each --session = own cookies/tabs/refs), recover a stranded tab by CDP targetId across sessions, --reuse-tab, and reset stuck daemons (daemon status/restart). Use for multi-user flows, parallel scraping, or when a session's tab/handle got stuck.
network
Mock responses, rewrite outgoing requests, block URLs, and record HAR with chrome-use network route (CDP Fetch, no proxy). Use when a task needs to stub an API response, override request headers/body, rewrite a URL to staging, block analytics, or capture/inspect network traffic.