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 leecyno1/boutique-skills --skill alphagbm-bps-backtestgit clone --depth 1 https://github.com/leecyno1/boutique-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/leecyno1/boutique-skills/alphagbm-bps-backtest)<a href="https://agentmods.dev/skills/leecyno1/boutique-skills/alphagbm-bps-backtest"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/alphagbm-bps-backtest/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/leecyno1/boutique-skills/alphagbm-bps-backtest"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/alphagbm-bps-backtest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00168 | $0.01682 |
| Opus 5 | $0.00084 | $0.00841 |
| Sonnet 5 | $0.00034 | $0.00336 |
| Haiku 4.5 | $0.00017 | $0.00168 |
Grade A, and why
alphagbm-bps-backtest 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.
This is a copy
100% identical to alphagbm-bps-backtest — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlphaGBM BPS Backtest
Backtests the Bull Put Spread (short put + long put at lower strike) as a mechanical strategy over 2018–present on any ticker, with two passes per call:
- With Signal — only enters when the per-ticker FearScore is ≥ your threshold
- No Signal (Control) — enters unconditionally every Monday
The side-by-side comparison shows whether the signal is doing work, or whether you're paying 1 credit for noise.
Parameters
All optional except ticker:
| Param | Default | Range | Meaning |
|---|---|---|---|
ticker |
required | US / HK / CN | Underlying |
dte_target |
14 | 7–45 | Days to expiry on entry |
short_delta |
0.25 | 0.15–0.35 | Absolute delta of the short put leg |
spread_width |
5.0 | 2–10 | Dollar width of the spread |
take_profit_pct |
0.50 | 0.20–0.80 | Close when realized % of max profit hits this |
fear_threshold |
60 | 40–80 | FearScore ≥ X is entry signal |
start_date |
2018-01-01 | YYYY-MM-DD | Backtest start |
end_date |
2026-04-20 | YYYY-MM-DD | Backtest end |
include_control |
true | bool | Run no-signal control pass alongside |
What's Returned
Per pass (with_signal and no_signal):
total_trades,win_rate_pct,annual_return_pct,sharpe,max_drawdown_pct,roc_pct,avg_holding_days,avg_pnl_per_trade,total_pnl,final_capitalexit_reasons— count bytake_profit / stop_loss / expiry_otm / expiry_itm / close_earlytrades[]— full ledger (entry/exit date, strikes, credit, pnl, reason)equity_curve[]— per-day cumulative capitalpnl_histogram— bucket counts for the P&L distribution
Plus:
summary— one-paragraph zh/en takeaway comparing signal vs control, with ⚠️ flags when drawdown or win rate look problematic
Methodology Notes
- IV is proxied by 20-day historical volatility (HV20) for BS pricing. Historical option-chain IV is unaffordable to source at scale; HV20 is a reasonable proxy but will under-estimate IV around events. Live results typically outperform backtest because of this.
- FearScore is reconstructed from the same 6 indicators the live version uses, but computed from cheap historical price + volume data only.
- Entries filtered by
max_positions(3) andmin_entry_spacing_days(3) and arisk_per_tradecap (0.5% of capital).
What ships with it
17 files 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.
- LICENSE 1.0 KB
- mock-data/AAPL.json 6.7 KB
- mock-data/buffett-analysis/example-ko.json 1.9 KB
- mock-data/fear-score/example-calm.json 661 B
- mock-data/fear-score/example-signal-triggered.json 663 B
- mock-data/hedge-advisor/example-gain-protection.json 1.5 KB
- mock-data/marks-cycle/example-neutral.json 366 B
- mock-data/META.json 8.8 KB
- mock-data/NVDA.json 8.4 KB
- mock-data/SPY.json 7.5 KB
- mock-data/take-profit/example-leveraged-etf.json 1.1 KB
- mock-data/tepper-signal/example-armed.json 589 B
- mock-data/tepper-signal/example-cold.json 488 B
- mock-data/TSLA.json 9.4 KB
- mock-data/vix-status/example-extreme-fear.json 528 B
- mock-data/vix-status/example-sweet-spot.json 506 B
- SOURCE.txt 451 B
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.
- 10d ago First seen · 142 lines · 168 tokens per session scan A 9a5be0b99044
alphagbm-bps-backtest is a skill published in the GitHub repository leecyno1/boutique-skills (5 stars, last pushed 20d ago), licensed MIT. It adds 168 tokens to every session and 1,682 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to alphagbm-bps-backtest, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.