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 agentmods add skills/w-winter/dot314/deep-x-researchnpx skills add w-winter/dot314 --skill deep-x-researchgit clone --depth 1 https://github.com/w-winter/dot314Wrote 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/w-winter/dot314/deep-x-research)<a href="https://agentmods.dev/skills/w-winter/dot314/deep-x-research"><img src="https://agentmods.dev/badge/skills/w-winter/dot314/deep-x-research.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01317 |
| Opus 5 | $0.00038 | $0.00659 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00132 |
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 6d 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.
This is a copy
97% identical to deep-x-research — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 108 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.
- 6d ago First seen · 108 lines · 76 tokens per session scan A 8859dd9e7032
deep-x-research is a skill published in the GitHub repository w-winter/dot314 (130 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,317 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to deep-x-research, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
pi-commandcode-release
Use when preparing, validating, publishing, or documenting a pi-commandcode-provider release/deployment, including version bumps, changelog entries, npm publish, GitHub releases, tags, and release follow-up comments.
refresh-model-catalog
Use when adding or removing Command Code models, refreshing the model catalog snapshot (image, reasoning, effort, output-limit metadata), updating display pricing, or refreshing test fixtures in pi-commandcode-provider.
bot-instructions
Load to render, check, or adopt a repo's GitHub review-bot instruction files from the shared doctrine and its effective manifest.
harness-ci
Load to wire, tune, or debug a repo's harness-only skip.
my-skill
When to load this skill. Agents read this line to decide whether to load it, so be specific.
orch
PRIMARY AGENT ONLY. Load to orchestrate a Linear or GitHub work item from preparation through merge.