best3

best3 is a skill for Claude Code from Degenapetrader/EVClaw. It costs 43 tokens per session (449 once invoked), scanned A, original, MIT.

A command that selects up to three current perpetual-futures trading setups on Hyperliquid, a cryptocurrency derivatives exchange. It creates manual plans with entries and commands for later execution.

In plain words
What is it for?
Use it to rank candidates, calculate support-, resistance-, or volatility-based entries, save trade plans, and produce commands for chasing or placing limit orders.
Why use it?
It turns an existing list of trading candidates into consistent, ready-to-review plans without relying on a language model to rank them.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Good fit Use it to rank candidates, calculate support-, resistance-, or volatility-based entries, save…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/degenapetrader/evclaw/best3
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 Degenapetrader/EVClaw --skill best3
Clone the repo
git clone --depth 1 https://github.com/Degenapetrader/EVClaw

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 best3

README.md
[![agentmods](https://agentmods.dev/badge/skills/degenapetrader/evclaw/best3.svg)](https://agentmods.dev/skills/degenapetrader/evclaw/best3)
Your own site
<a href="https://agentmods.dev/skills/degenapetrader/evclaw/best3"><img src="https://agentmods.dev/badge/skills/degenapetrader/evclaw/best3.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 449 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.
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 $0.00043 $0.00449
Opus 5 $0.00022 $0.00225
Sonnet 5 $0.00009 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 7d ago against content hash 20d8c7e82821, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

best3 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_best3.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

openclaw_skills/best3/SKILL.md · 51 lines

What it actually says

/best3 (deterministic)

Goal: when the user types /best3, pick the best up to 3 current Hyperliquid perp opportunities using our existing candidate snapshot and produce manual plans (no LLM).

How it works

Run:

EVCLAW_ROOT="${EVCLAW_ROOT:-$HOME/.openclaw/skills/EVClaw}" \
python3 "$EVCLAW_ROOT/openclaw_skills/best3/scripts/generate_best3.py"

Optional:

  • --n 3 (default 3)
  • --db /path/to/ai_trader.db
  • --runtime /path/to/evclaw/state

The script will:

  • Load latest evclaw_candidates_*.json
  • Rank candidates by blended_conviction (fallbacks to conviction)
  • Allocate plan IDs in manual_trade_plans
  • Build deterministic setups with:
    • LIVE HL mid + BBO
    • RESTING entry = SR support/resistance when available; fallback to 1×ATR from mid when SR missing/too far
    • Post-only safe limit nudging
  • Write /tmp/manual_trade_plan_<ID>.json
  • Store READY rows in manual_trade_plans for /execute <ID> chase|limit

Output rules

  • One-shot, normie-friendly.
  • No internal jargon.
  • Display live price (HL mid) for each pick.
  • Always include true one-click copy for Telegram: EACH execute command gets its own single-line code block.

Example:

/execute <ID> chase
/execute <ID> limit
  • Do NOT add labels/bullets/extra text inside those code blocks.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 51 lines · 43 tokens per session scan A 20d8c7e82821

Subscribe to this mod's changes

best3 is a skill published in the GitHub repository Degenapetrader/EVClaw (40 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 449 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.