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 varrdinc/varrd --skill varrd-researchgit clone --depth 1 https://github.com/varrdinc/varrdWrote 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/varrdinc/varrd/varrd-research)<a href="https://agentmods.dev/skills/varrdinc/varrd/varrd-research"><img src="https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-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/varrdinc/varrd/varrd-research"><img src="https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-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 | $0.00060 | $0.01664 |
| Opus 5 | $0.00030 | $0.00832 |
| Sonnet 5 | $0.00012 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
varrd-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 9d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VARRD Research — The Main Event
This is the core of VARRD. Everything else — scanning, searching, checking balances — those are environmental functions that support what happens here. This tool is how you talk to VARRD's AI to do real quantitative research.
Through this single interface, VARRD's AI can load market data, build indicators, chart patterns, run rigorous statistical tests, optimize stop-loss and take-profit levels, compute the best way to trade an edge, generate ideas through its expert council, and deliver exact dollar trade setups. It has 15 internal tools and knows how to use them.
Command
varrd research "<your trading idea>"
The Typical Flow
A research session follows a natural progression:
1. You bring an idea. This can be a specific hypothesis ("When RSI drops below 25 on ES, is there a bounce?"), a broad question ("What happens to crude when weekly inventory draws exceed expectations?"), or a request for idea generation ("Use the ELROND council on NQ" — 8 specialist investigators each trained on different systematic trading frameworks).
2. VARRD charts the pattern. It loads real market data, builds the indicators, evaluates the formula, and shows you exactly where the pattern fired on a real price chart with signal count. You review it — does this look right? Are the signals where you'd expect them?
3. You validate or tweak. If the chart looks good, you approve it for testing. If something's off, you refine the formula — adjust thresholds, add filters, change the market or timeframe. Iterate until you're satisfied with what you're about to test.
4. VARRD recommends and runs the test. Based on your setup, VARRD recommends the best testing approach. There are several types:
| Test Type | What It Does | When It's Used |
|---|---|---|
| Single Event Study | Forward return analysis on one market at multiple time horizons | Default for one market — "does price go up or down after this signal?" |
| Parallel Event Study | Same pattern tested independently on 2-5 markets, per-market results | "Does this work on ES, NQ, and CL?" |
| Batch Event Study | Same pattern pooled across 6+ markets into one aggregate result | Broad screen — "does this work across all metals?" |
| Backtest Strategy | Full simulation with stop-loss, take-profit, equity curve, drawdown, in-sample and sacred one-shot out-of-sample validation | When you want to simulate actually trading it as a system |
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.
- 9d ago First seen · 118 lines · 60 tokens per session scan A a9e3554a3470
varrd-research is a skill published in the GitHub repository varrdinc/varrd (24 stars, last pushed 9d ago), licensed MIT. It adds 60 tokens to every session and 1,664 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 2026-08-30.
Other skills, from other repositories
devwiki
Use when the user asks about JoyinCode development workflow, how to use AI coding in this project, or mentions any pipeline step (markitdown Word-to-MD conversion, grill-with-docs requirement analysis, opsx proposal workflow).
jcdb
A read-only database lookup skill that checks real tables, columns, definitions, and selected data before SQL or code is written. Its documentation is in Chinese.
specx
An enterprise software-development workflow that takes a request through clarification, specification, design, task planning, execution, and archiving.
grill-with-docs
Full design grilling session. I interview you relentlessly about every aspect of your plan until we reach shared understanding. At the end, I generate CONTEXT.md and ADR files from what we discussed.
opsx
A command for managing proposals in the OPSX workflow. It supports starting, applying, archiving, and initialising proposals.
demo
A project-analysis skill for the cloudQuant/backtrader repository, with steps for reviewing its structure, related processes, and visible results.