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-hypothesisgit 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-hypothesis)<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>- 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 | $0.00037 | $0.00548 |
| Opus 5 | $0.00018 | $0.00274 |
| Sonnet 5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
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.
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 scanorvarrd searchresults - 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")
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.
- 7d ago First seen · 71 lines · 37 tokens per session scan A 2b93ce230d44
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.
Other skills, from other repositories
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.
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).
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.