varrd-search

varrd-search is a skill for Claude Code, Codex from varrdinc/varrd. It costs 29 tokens per session (494 once invoked), scanned A, original, MIT.

Una búsqueda para encontrar estrategias de trading guardadas usando palabras clave o preguntas en lenguaje natural. Una estrategia de trading es un conjunto de reglas para decidir cuándo comprar o vender en un mercado.

In plain words
What is it for?
Sirve para buscar estrategias por conceptos como RSI, impulso, reversión a la media o materias primas, y limitar los resultados a un mercado o a una cantidad determinada.
Why use it?
Evita revisar manualmente toda una biblioteca de estrategias y ayuda a localizar las que coinciden con un tema, mercado o patrón concreto.

Skill for Claude CodeCodex

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

Good fit Sirve para buscar estrategias por conceptos como RSI, impulso, reversión a la media o materias primas, y limitar los resultados a un mercado o a una cantidad determinada.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/varrdinc/varrd/varrd-search
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-search
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-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-search.svg)](https://agentmods.dev/skills/varrdinc/varrd/varrd-search)
Your own site
<a href="https://agentmods.dev/skills/varrdinc/varrd/varrd-search"><img src="https://agentmods.dev/badge/skills/varrdinc/varrd/varrd-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 494 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 $0.00029 $0.00494
Opus 5 $0.00015 $0.00247
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 8d ago against content hash 4b1aca8ca31a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

varrd-search 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 8d 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-search/SKILL.md · 72 lines

What it actually says

VARRD Search — Find Saved Strategies

Use this skill when a user wants to find strategies in their library by topic, keyword, or market.

Command

varrd search "<query>"
varrd search "RSI oversold" --market ES
varrd search "momentum strategies" --limit 5

How It Works

Searches all saved strategies using keyword and semantic matching. Returns matches ranked by relevance with key stats (win rate, Sharpe, edge status).

Options

Flag Description
--market ES Filter results to a specific market
--limit N Max results to return (default 10)

Examples

varrd search "momentum strategies"
varrd search "RSI oversold"
varrd search "corn seasonal"
varrd search "mean reversion" --market ES
varrd search "volatility" --limit 20

Reading the Output

Each result includes:

  • Strategy name and hypothesis ID
  • Formula — the pattern expression
  • Market and direction
  • Edge status — whether a validated edge was found
  • Win rate and Sharpe ratio
  • Similarity score — how closely it matches your query

Tips

  • Use natural language: "strategies that work on crude oil" works just as well as "CL"
  • Use the hypothesis ID from results with varrd hypothesis <id> for full details
  • Search is free — no credits consumed

Cost

Free. No credits consumed.

Python SDK Equivalent

from varrd import VARRD
v = VARRD()
results = v.search("momentum on grains", limit=5)
for r in results.results:
    print(f"{r.name} ({r.market}) — edge: {r.has_edge}, WR: {r.win_rate}")
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. 8d ago First seen · 72 lines · 29 tokens per session scan A 4b1aca8ca31a

Subscribe to this mod's changes

varrd-search is a skill published in the GitHub repository varrdinc/varrd (24 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 494 once invoked, about $0.0001 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.