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 Signal-Execution-Labs/forex-trading-ai-agent --skill ai-predictorgit clone --depth 1 https://github.com/Signal-Execution-Labs/forex-trading-ai-agentWrote 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/signal-execution-labs/forex-trading-ai-agent/ai-predictor)<a href="https://agentmods.dev/skills/signal-execution-labs/forex-trading-ai-agent/ai-predictor"><img src="https://agentmods.dev/badge/skills/signal-execution-labs/forex-trading-ai-agent/ai-predictor/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/signal-execution-labs/forex-trading-ai-agent/ai-predictor"><img src="https://agentmods.dev/badge/skills/signal-execution-labs/forex-trading-ai-agent/ai-predictor.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 | $0.00000 | $0.00580 |
| Opus 5 | $0.00000 | $0.00290 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
ai-predictor 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ai-predictor — 100% identical, 0 lines differ
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.
AI Market Predictor
K.I.T.'s brain for price predictions - Machine Learning that WORKS!
Features
🔮 LSTM Neural Networks
- Time Series Prediction mit Deep Learning
- Multi-Step Forecasting (1h, 4h, 24h, 7d)
- Attention Mechanisms für wichtige Patterns
📊 Feature Engineering
- Technical Indicators (RSI, MACD, Bollinger, 50+ mehr)
- Volume Profile Analysis
- Order Flow Imbalance
- Funding Rates (Perps)
- Open Interest Changes
🎯 Confidence Scoring
- Monte Carlo Dropout für Uncertainty Estimation
- Ensemble Models für robustere Predictions
- Dynamische Confidence basierend auf Volatilität
🏆 Model Performance
- Rolling Backtests
- Walk-Forward Optimization
- Real-time Model Retraining
Usage
from ai_predictor import MarketPredictor
predictor = MarketPredictor()
# Single prediction
prediction = await predictor.predict(
symbol="BTC/USDT",
timeframe="1h",
horizon=24 # hours ahead
)
print(f"Price: ${prediction.price:.2f}")
print(f"Direction: {prediction.direction}") # UP/DOWN/NEUTRAL
print(f"Confidence: {prediction.confidence:.1%}")
print(f"Range: ${prediction.low:.2f} - ${prediction.high:.2f}")
# Batch predictions
predictions = await predictor.predict_batch(
symbols=["BTC/USDT", "ETH/USDT", "SOL/USDT"],
timeframe="4h",
horizon=168 # 1 week
)
Models
| Model | Use Case | Accuracy |
|---|---|---|
| LSTM-Attention | Short-term (1-24h) | ~65% direction |
| Transformer | Medium-term (1-7d) | ~58% direction |
| XGBoost Ensemble | Volatility Prediction | MAE < 2% |
| CNN-LSTM | Pattern Recognition | ~62% breakouts |
Configuration
ai_predictor:
models:
lstm:
layers: [128, 64, 32]
dropout: 0.2
attention: true
ensemble_size: 5
features:
technical: true
orderflow: true
sentiment: true # requires sentiment-analyzer
training:
lookback: 168 # hours
retrain_interval: 24h
min_samples: 1000
Dependencies
- tensorflow>=2.15.0
- scikit-learn>=1.3.0
- ta-lib (technical analysis)
- numpy, pandas
What ships with it
3 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.
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.
- 12d ago First seen · 92 lines · 0 tokens per session scan A 47a451716722
ai-predictor is a skill published in the GitHub repository Signal-Execution-Labs/forex-trading-ai-agent (136 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 580 tokens. 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
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Use when LLM spend needs to come down, or when routing tasks across model tiers and budgets.
qveris
Paid capability marketplace for global multi-asset data; use it when free Vibe-Trading sources lack coverage, depth, or provider quality, and keep free sources as the default for routine OHLCV.
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.