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 Superior-Trade/superior-skills --skill basis-arbgit clone --depth 1 https://github.com/Superior-Trade/superior-skillsWrote 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/superior-trade/superior-skills/basis-arb)<a href="https://agentmods.dev/skills/superior-trade/superior-skills/basis-arb"><img src="https://agentmods.dev/badge/skills/superior-trade/superior-skills/basis-arb/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.
<a href="https://agentmods.dev/skills/superior-trade/superior-skills/basis-arb"><img src="https://agentmods.dev/badge/skills/superior-trade/superior-skills/basis-arb.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00087 | $0.02817 |
| Opus 5 | $0.00044 | $0.01409 |
| Sonnet 5 | $0.00017 | $0.00563 |
| Haiku 4.5 | $0.00009 | $0.00282 |
Grade A, and why
basis-arb 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategy: Basis Flipping — Directional (Long-Perp Leg)
Honest framing — read this first
True basis arbitrage is a two-leg trade:
- Long perp + short spot (when perp trades at a discount to spot, basis < 0)
- Short perp + long spot (when perp trades at a premium, basis > 0)
You earn the basis as the legs converge. Freqtrade is a single-leg engine — it can't run paired hedged trades on the same ticker. The strategy below captures the directional signal that "basis flipping negative + funding negative = bullish positioning shift" and goes long the perp accordingly. It's a momentum read on positioning, not a hedged arb.
If you want the actual hedged version, run an external system (or a custom Hyperliquid-only multi-leg runtime). Don't deploy this template thinking it's market-neutral.
Backtest reference
| Window | BTC/USDC:USDC 1h, 2026-01-01 → 2026-05-01 |
|---|---|
| Trades | 0 (no spot leg available in the engine) |
| Backtest ID | 01kr42hegps9w20njsty2cqb41 |
The Superior Trade backtest engine doesn't currently expose Hyperliquid spot OHLCV alongside perp pairs via Freqtrade's informative_pairs mechanism, so the spot_close column is never populated and the entry filter never fires. The strategy code is structurally sound — it runs cleanly to completion with 0 trades — but this template can't be validated end-to-end on the current backtest engine. Two paths:
- Validate live, paper-traded — run as a dry-run deployment for a week and compare the entries against an external basis tracker (CoinGlass
basisHistoryor a simple notebook). - Substitute external basis feed — replace the
informative_pairsspot fetch with a CoinGlass/api/futures/basis/historycall from a side-channel cache. Out of scope for this template; would be a Phase 2 backend change.
The strategy is shipped as a directional blueprint, not a live-validated runtime. Treat it as a teachable template for how to wire spot-perp basis into a Freqtrade strategy, rather than an off-the-shelf deployment.
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.
- 11d ago First seen · 219 lines · 87 tokens per session scan A 911c6fff66dd
basis-arb is a skill published in the GitHub repository Superior-Trade/superior-skills (209 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,817 once invoked, about $0.0004 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
crypto-derivatives
Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks analysis.
defi-yield
DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.
onchain-analysis
On-chain data analysis — active addresses / whale tracking / TVL / DEX liquidity, interpretation and signal generation using on-chain valuation metrics such as MVRV / NVT / SOPR.
stablecoin-flow
Stablecoin supply and flow analysis — USDT/USDC mint-burn signals, exchange stablecoin reserves, on-chain stablecoin velocity, and capital rotation indicators for crypto market timing.
token-unlock-treasury
Token unlock schedule analysis and project treasury tracking — vesting cliffs, linear unlocks, team/investor/ecosystem token releases, treasury diversification, and sell pressure forecasting.
ccxt
CCXT unified crypto exchange library (100+ exchanges). Free public market data. Fallback when OKX is unavailable.