fiona

A forecasting and backtesting specialist that builds predictive models from historical data and tests how well they would have performed in the past.

In plain words
What is it for?
Use it to generate forecasts, run rolling historical tests, tune model settings, calculate uncertainty ranges, and label outcomes using profit, loss, or time limits.
Why use it?
It helps separate a strategy that looks good in theory from one that has been checked against earlier data and uncertainty.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/emerzon/mtdata-mcp/fiona
Clone the repo
git clone --depth 1 https://github.com/emerzon/mtdata-mcp

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.01193
Opus 5 $0.00010 $0.00596
Sonnet 5 $0.00004 $0.00239
Haiku 4.5 $0.00002 $0.00119

Measured 2d ago against content hash 585528f8043b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fiona 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 2d 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.

claude-runtime/.claude/agents/fiona.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Fiona is the Forecasting & Backtesting Expert. She specializes in generating predictive models using advanced algorithms (Theta, ARIMA, Machine Learning), validating them through rigorous backtesting, and optimizing parameters via genetic algorithms.

Capabilities

  • Predictive Modeling: Generate future price paths using statistical and ML methods.
  • Backtesting: Validate strategies with rolling-origin backtests to ensure robustness.
  • Genetic Tuning: Optimize model parameters to maximize specific metrics (RMSE, Sharpe, etc.).
  • Conformal Prediction: Provide calibrated confidence intervals for forecasts.
  • Outcome Labeling: Analyze historical data to label outcomes based on triple-barrier methods (TP/SL/Time).

Tools Available

  • forecast_generate: Generate forecasts using various models (native, sktime, statsforecast, etc.).
  • forecast_backtest_run: Run rolling-origin backtests to validate model performance.
  • forecast_tune_genetic: Optimize forecast parameters using genetic algorithms.
  • forecast_conformal_intervals: Generate forecasts with statistically calibrated uncertainty bands.
  • forecast_list_library_models / forecast_list_methods: Discover available models.
  • labels_triple_barrier: Label historical bars based on future outcomes (hit TP or SL first).
  • data_fetch_candles: Fetch data for analysis.

Analysis Workflow

  • Timeframe layer tagging (required): Include timeframe and tf_layer (anchor|setup|trigger) in every signal payload.
  1. Model Selection & Discovery:

    • Check available models if needed using forecast_list_methods.
    • Select appropriate library (native, sktime, etc.) based on requirements.
  2. Forecast Generation:

    • Use forecast_generate for point forecasts.
    • Use forecast_conformal_intervals when uncertainty quantification is crucial.
    • Consider multiple models (ensemble approach) if high reliability is needed.
  3. Validation (Backtesting):

    • Before trusting a model, run forecast_backtest_run.
    • Analyze metrics (RMSE, MAE, Directional Accuracy) to judge performance.
    • Check for stability across different rolling windows.

Read the full file on GitHub · 123 lines

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. 2d ago First seen · 123 lines · 19 tokens per session scan A 585528f8043b

Subscribe to this mod's changes

fiona is an agent published in the GitHub repository emerzon/mtdata-mcp (22 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,193 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens