nansen-perp-screener

nansen-perp-screener is a skill for Claude Code from nansen-ai/nansen-cli. It costs 35 tokens per session (779 once invoked), scanned A, original, MIT.

A market-scanning tool for Hyperliquid perpetual contracts, which are crypto derivatives without an expiry date. It shows market activity, trader rankings, and trades by tracked smart-money accounts.

In plain words
What is it for?
Use it to rank contracts by volume or open interest, inspect trader performance, and find smart-money perpetual trades. Results can be filtered by trader type or Nansen label.
Why use it?
It gathers contract activity, open positions, funding, prices, and trader results into one scan instead of requiring separate lookups.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

not rated 135repo +1 today A scan Socket: passSnyk: warnSkillSpector: pass 35 tokens original MIT

Good fit Use it to rank contracts by volume or open interest, inspect trader performance, and find smart-money perpetual trades. Results can be filtered by trader type or Nansen label.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nansen-ai/nansen-cli/nansen-perp-screener
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 nansen-ai/nansen-cli --skill nansen-perp-screener
Clone the repo
git clone --depth 1 https://github.com/nansen-ai/nansen-cli

Made for: Claude Code.

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 nansen-perp-screener

README.md
[![agentmods](https://agentmods.dev/badge/skills/nansen-ai/nansen-cli/nansen-perp-screener/github.svg)](https://agentmods.dev/skills/nansen-ai/nansen-cli/nansen-perp-screener)
Your own site
<a href="https://agentmods.dev/skills/nansen-ai/nansen-cli/nansen-perp-screener"><img src="https://agentmods.dev/badge/skills/nansen-ai/nansen-cli/nansen-perp-screener/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.

agentmods 80×15 button for nansen-perp-screener

Your own site · 80×15
<a href="https://agentmods.dev/skills/nansen-ai/nansen-cli/nansen-perp-screener"><img src="https://agentmods.dev/badge/skills/nansen-ai/nansen-cli/nansen-perp-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 779 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
  • Socket pass 17 Mar 2026
  • Snyk warn 17 Mar 2026
  • 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 $0.00035 $0.00779
Opus 5 $0.00017 $0.00390
Sonnet 5 $0.00007 $0.00156
Haiku 4.5 $0.00003 $0.00078

Measured 10d ago against content hash 3a52e05377e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nansen-perp-screener 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 10d 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/nansen-perp-screener/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perp Market Scan

Answers: "What's the state of the Hyperliquid perp market right now?"

nansen research perp screener --sort volume:desc --limit 20
# → token_symbol, volume, buy/sell_volume, buy_sell_pressure, open_interest, funding, mark_price

nansen research perp leaderboard --days 7 --limit 20
# → trader_address, trader_address_label, total_pnl, roi, account_value

nansen research smart-money perp-trades --limit 20
# → token_symbol, side, action (Open/Close), value_usd, price_usd, trader_address_label

New Filters (ECINT-6680)

--trader-type

Filter by trader type. Accepted values: all (default), sm, whale, public_figure, high_winrate_hl_perps_trader.

# Show only whale traders
nansen research perp screener --trader-type whale --limit 10

# Show only smart money traders
nansen research perp screener --trader-type sm --limit 20

# Show high win-rate HL perps traders
nansen research perp screener --trader-type high_winrate_hl_perps_trader --limit 20

--sm-label-filter

Comma-separated Nansen SM labels to filter by. Only applies when --trader-type is all or sm.

# Filter to a specific SM label
nansen research perp screener --trader-type sm --sm-label-filter "30D Smart Trader"

# Multiple labels
nansen research perp screener --sm-label-filter "30D Smart Trader,Smart LP"

--trader-label-filter

Comma-separated HL perps trader labels to filter by. Only applies when --trader-type is all or sm.

# Filter to HL Perps Whale label
nansen research perp screener --trader-label-filter "HL Perps Whale"

--sectors-filter

Comma-separated category:subcategory pairs to filter coins by sector.

# Filter to AI and DeFi crypto sectors
nansen research perp screener --sectors-filter "Crypto:AI,Crypto:DeFi" --trader-type whale

# Combine with trader type and limit
nansen research perp screener --sectors-filter "Crypto:AI,Crypto:DeFi" --trader-type whale --limit 10 --sort volume:desc

Read the full file on GitHub · 92 lines

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. 10d ago First seen · 92 lines · 35 tokens per session scan A 3a52e05377e7

Subscribe to this mod's changes

nansen-perp-screener is a skill published in the GitHub repository nansen-ai/nansen-cli (135 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 779 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.