varrd-hypothesis

varrd-hypothesis is a skill for Claude Code, Codex from varrdinc/varrd. It costs 37 tokens per session (548 once invoked), scanned A, original, MIT.

A lookup for one saved trading strategy, showing its formula, test results, and revision history. A strategy is a set of rules used to decide when to trade.

In plain words
What is it for?
Use it to inspect a strategy’s market, long or short direction, win rate, risk-adjusted returns, profit factor, historical trades, results over different time periods, and formula versions.
Why use it?
It gathers the details of a strategy in one place, so you do not have to search through separate tests or revisions. It also shows that its trade levels may be out of date.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to inspect a strategy’s market, long or short direction, win rate, risk-adjusted returns, profit factor, historical trades, results over different time periods, and formula versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/varrdinc/varrd/varrd-hypothesis
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 varrdinc/varrd --skill varrd-hypothesis
Clone the repo
git clone --depth 1 https://github.com/varrdinc/varrd

Made for: Claude Code, Codex.

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.

agentmods badge for varrd-hypothesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-hypothesis.svg)](https://agentmods.dev/skills/varrdinc/varrd/varrd-hypothesis)
Your own site
<a href="https://agentmods.dev/skills/varrdinc/varrd/varrd-hypothesis"><img src="https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-hypothesis.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00548
Opus 5 $0.00018 $0.00274
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00004 $0.00055

Measured 7d ago against content hash 2b93ce230d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

varrd-hypothesis 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 7d 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.

skills/varrd-hypothesis/SKILL.md · 71 lines

What it actually says

VARRD Hypothesis — Strategy Details

Use this skill when a user wants to see full details on a specific strategy from their library.

Command

varrd hypothesis <hypothesis_id>

How It Works

Returns complete details for a saved strategy: formula, setup code, statistical metrics, version history, and horizon results.

Example

varrd hypothesis hyp_abc123

Reading the Output

Field Description
Name Strategy name (e.g. "RSI Oversold ES Daily")
Formula The boolean pattern expression
Market Primary market tested on
Direction LONG or SHORT
Edge verdict STRONG EDGE, MARGINAL, or NO EDGE
Win rate Historical win percentage
Sharpe ratio Risk-adjusted return metric
Profit factor Gross profits / gross losses
Total trades Number of historical signals
Horizon results Per-horizon stats (1, 3, 5, 10, 20 bars)
Versions Formula revision history

Important: Trade Levels May Be Stale

Trade levels from varrd hypothesis are from when the strategy was last tested. They may be outdated. For fresh current prices:

  • Use varrd scan — if the strategy is firing, you get fresh levels
  • Use varrd research "Load hypothesis <id>" then "show me the trade setup" — forces fresh calculation

Tips

  • Get hypothesis IDs from varrd scan or varrd search results
  • This command is free — no credits consumed
  • Use this to understand a strategy before acting on scan signals

Cost

Free. No credits consumed.

Python SDK Equivalent

from varrd import VARRD
v = VARRD()
hyp = v.get_hypothesis("hyp_abc123")
print(f"{hyp.name}: {hyp.win_rate:.0%} WR, {hyp.sharpe:.2f} Sharpe")
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.

  1. 7d ago First seen · 71 lines · 37 tokens per session scan A 2b93ce230d44

Subscribe to this mod's changes

varrd-hypothesis is a skill published in the GitHub repository varrdinc/varrd (24 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 548 once invoked, about $0.0002 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.