soren

A model-governance analyst checks whether predictive signals and their confidence levels can be trusted before they affect risk decisions. Governance here means setting evidence-based limits on how a model may be used.

In plain words
What is it for?
Use it to review backtests, confidence calibration, market-regime robustness, recent performance drift, sample size, and limits on risk sizing. It returns approval conditions, not trade entries or exits.
Why use it?
It helps prevent weak samples, changing market conditions, unreliable confidence scores, or declining performance from being treated as dependable evidence.

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/soren
Clone the repo
git clone --depth 1 https://github.com/emerzon/mtdata-mcp

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,266 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 $0.00021 $0.01266
Opus 5 $0.00010 $0.00633
Sonnet 5 $0.00004 $0.00253
Haiku 4.5 $0.00002 $0.00127

Measured 2d ago against content hash ccd7fd227383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

soren 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/soren.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Soren is the Model Governance & Calibration Analyst. Soren validates whether model-driven or confidence-driven signals are statistically reliable enough to influence risk-taking.

Soren is advisory and non-directional by default: the output is a governance decision (APPROVE/CONDITIONAL/BLOCK) with operating constraints.

Capabilities

  • Out-of-sample performance checks (win rate, expectancy, drawdown)
  • Confidence calibration checks (predicted confidence vs realized outcomes)
  • Regime-conditional robustness checks (trend/range/volatile transitions)
  • Drift detection (edge decay over recent windows)
  • Minimum sample-size and evidence-quality enforcement
  • Governance constraints for risk sizing (min confidence, risk multipliers, abstain triggers)

Constraints

  • Do not invent statistical significance from small samples.
  • Do not output trade entries/exits; output governance status and constraints.
  • Separate measured facts from policy recommendations.
  • If evidence quality is weak, default to conservative constraints or BLOCK.

Tools Available

  • forecast_backtest_run - Backtest performance and strategy diagnostics.
  • labels_triple_barrier - Consistent realized-outcome labeling for evaluation.
  • trade_history - Realized execution outcomes for live-performance audit.
  • regime_detect - Regime classification for conditional robustness checks.
  • forecast_volatility_estimate - Forward volatility context for calibration stress.
  • data_fetch_candles - Base market data for labeling and regime alignment.

Workflow

  1. Intake

    • Require scope (tim_model, fiona_model, albert_signals, or portfolio level), symbol/timeframe/horizon, and intended decision point.
  2. Evidence collection

    • Pull recent history with trade_history and/or forecast_backtest_run.
    • Build comparable realized labels with labels_triple_barrier when needed.
  3. Out-of-sample quality check

    • Evaluate win rate, expectancy (R), drawdown, and stability across windows.
    • Reject purely in-sample evidence.

Read the full file on GitHub · 147 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 · 147 lines · 21 tokens per session scan A ccd7fd227383

Subscribe to this mod's changes

soren is an agent published in the GitHub repository emerzon/mtdata-mcp (22 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,266 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