varrd-research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited varrd-research (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
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.
varrd research "<your trading idea>"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 |
There's also portfolio backtesting for combining multiple strategies into a book, but that follows the same mechanics as strategy backtesting.
5. You see the results and decide what's next.
The cycle continues: idea → chart → validate → test → interpret → next idea. Each round gets you closer to a real edge or confirms there isn't one.
While you research, VARRD enforces institutional-grade statistical guardrails automatically:
These are the same controls that institutional quant firms enforce internally. They run identically whether you're testing interactively or running autonomous overnight research. You don't configure them. You can't skip them. That's the point.
| Verdict | Meaning |
|---|---|
| STRONG EDGE | Significant vs both zero and market baseline — real returns that also beat what the market does on its own |
| MARGINAL | Significant vs zero only — there's a real signal, but it doesn't clearly beat the market's natural drift |
| PINNED | Significant vs market only — returns are flat but meaningfully different from market behavior (useful for hedging or relative value) |
| NO EDGE | Neither test passed — no tradeable signal found |
varrd research "When RSI drops below 25 on ES, is there a bounce?"
varrd research "Use the ELROND council on NQ"
varrd research "When wheat drops 3 consecutive days after monthly highs, is there a snap-back?"
varrd research "Load TLT and CL. When bonds sell off for a week, does crude follow?"
varrd research "What happens to gold when the VIX spikes above 30?"Each turn prints response text and any widgets (charts, test results, trade setups). Key context fields:
has_edge: True — edge found, get the trade setup, donehas_edge: False — no edge, valid complete resulthas_edge: None — still in progress, keep goingnext_actions — what to say next (the CLI follows these automatically)edge_verdict — STRONG EDGE, MARGINAL, PINNED, or NO EDGE--max-turns 20 for complex research that needs more steps~20-30 cents per complete workflow (idea through validated trade setup). ELROND council calls cost ~40-60 cents. Multi-market (3+ markets) can reach ~$1.
from varrd import VARRD
v = VARRD()
r = v.research("When RSI drops below 25 on ES, is there a bounce?")
r = v.research("test it", session_id=r.session_id)
r = v.research("show me the trade setup", session_id=r.session_id)For richer integration with streaming progress and automatic instructions, use the MCP server at https://app.varrd.com/mcp.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.