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 dvgamerr-app/gokub-mcp --skill low-riskgit clone --depth 1 https://github.com/dvgamerr-app/gokub-mcpWrote 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/dvgamerr-app/gokub-mcp/low-risk)<a href="https://agentmods.dev/skills/dvgamerr-app/gokub-mcp/low-risk"><img src="https://agentmods.dev/badge/skills/dvgamerr-app/gokub-mcp/low-risk/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/dvgamerr-app/gokub-mcp/low-risk"><img src="https://agentmods.dev/badge/skills/dvgamerr-app/gokub-mcp/low-risk.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 | $0.00064 | $0.00827 |
| Opus 5 | $0.00032 | $0.00413 |
| Sonnet 5 | $0.00013 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
low-risk 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Low-Risk Trading Rules (Bitkub)
Applies on top of playbook. These rules override the playbook where they conflict.
When they are silent, the playbook rules apply unchanged.
Why BTC-only
BTC and ETH have correlation 0.7–0.9. Holding both does not diversify — ETH just amplifies the drawdown. In a 50% BTC crash, ETH typically falls 30–40% more. On Bitkub (no short, no hedge), capital preservation = stay in BTC or cash.
Portfolio allocation (hard rules)
| Bucket | Allocation | Purpose |
|---|---|---|
| Cash reserve | ≥ 60% of equity | Dry powder; never touch for a single trade |
| Active capital | ≤ 40% of equity | Only this pool is risked |
| Risk per trade | ≤ 1% of equity | Half the playbook's 2% |
Example: 100,000 THB equity → 60,000 cash → 40,000 active → risk ≤ 1,000 THB per trade.
Check get_wallet_balance before every session. If cash < 60%, do not open new positions.
Symbol filter
- Trade only
btc_thb. No ETH, no altcoins. - Rationale: BTC has the best liquidity on Bitkub, lowest spread, least manipulation.
Entry checklist (stricter than playbook)
All five must be true before entering. Evaluate on the 4H candle for entry signal and 1D candle for regime confirmation.
| # | Check | Tool |
|---|---|---|
| 1 | Regime = UPTREND | check_market_regime on 1D closes |
| 2 | Close > EMA200 (1D) | calculate_ema(closes, 200) |
| 3 | EMA50 > EMA200 (1D) | calculate_ema(closes, 50) |
| 4 | RSI(14) > 50 on 4H | calculate_rsi(closes_4h, 14) |
| 5 | validate_trade_setup returns can_trade=true |
gate — never skip |
If any check fails → hold cash. Cash is a position.
Take-profit & stop rules
- Minimum RR = 2:1. Same as playbook — do not lower.
- Stop = below the 4H swing low that preceded the entry signal.
- At +1R: move stop to break-even.
- At +2R: close at least 50% and trail the rest.
- Maximum loss per session: 3 losing trades → stop for the day, review journal.
What NOT to touch
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 · 76 lines · 64 tokens per session scan A bdf8918b4f6d
low-risk is a skill published in the GitHub repository dvgamerr-app/gokub-mcp (2 stars, last pushed 24d ago), licensed MIT. It adds 64 tokens to every session and 827 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and multi-market screener. Supports stocks, crypto, ETFs, indices, Turkish (BIST), and Egyptian (EGX) markets.
decker
Instructions for using Decker, an AI trading platform that provides market signals, portfolio and order information, news digests, and messaging integrations.
decker-developer
Use when a developer asks about Decker's Public API — obtaining API keys, authentication, rate limits, signal endpoints, SDK usage. Triggers: API key, dklive, X-API-Key, public API, /public/signals, REST API, developer, integrate Decker, rate limit.
decker-hyperliquid
A Decker extension for getting market data and placing trades on Hyperliquid, a decentralised crypto exchange for spot and perpetual-futures trading.
decker-polymarket
Instructions for using Decker with Polymarket, a prediction market where people trade contracts on future yes-or-no outcomes.
pine
Writes Pine Script v6 indicators and strategies for TradingView from natural-language descriptions. Use when the user asks Claude to write or build a Pine Script indicator, strategy, oscillator, or TradingView script, asks for a Pine v6 script, asks to convert v4/v5 Pine code to v6, or describes a trading…