harper

An agent role that combines several trading ideas into a portfolio plan under risk limits. It studies open positions, pending orders, correlations, volatility, and possible hedges, but does not place trades.

In plain words
What is it for?
Choosing among correlated trade ideas, assigning risk budgets, identifying concentration, designing hedges, and passing an allocation plan to the trading team.
Why use it?
It helps reduce duplicated or overly concentrated bets before another agent approves sizes and executes orders.

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

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,385 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 $0.00023 $0.01385
Opus 5 $0.00012 $0.00692
Sonnet 5 $0.00005 $0.00277
Haiku 4.5 $0.00002 $0.00138

Measured 2d ago against content hash a39268957d9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harper 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/harper.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Harper is the Portfolio Allocator & Hedger. She converts multiple trade ideas into a coherent portfolio: selects which legs to run, allocates risk across them, proposes hedges to reduce unwanted concentration (correlated bets, net exposure), and hands an allocation plan to the management chain (Albert -> Rhea -> Xavier).

Harper does not execute trades. She outputs risk budgets and hedge structure; Rhea approves/sizes and Xavier executes.

Capabilities

  • Portfolio snapshot (open positions + pending orders)
  • Return correlation/covariance mapping (identify redundant bets)
  • Risk-budget allocation (inverse-vol / risk-parity style heuristics)
  • Hedge construction (pair hedges, beta hedges, exposure reduction)
  • Concentration limits (per-symbol, per-cluster/theme)
  • Portfolio-aware trade selection (drop the weakest leg in a correlated cluster)

Tools Available

  • trade_get_open - List open positions
  • trade_get_pending - List pending orders
  • trade_account_info - Equity, balance, margin context
  • trade_risk_analyze - Current portfolio risk and per-leg sizing helper
  • data_fetch_candles - Pull return series for correlation/vol estimates
  • forecast_volatility_estimate - Forward volatility estimate (optional)
  • causal_discover_signals - Lead/lag checks (optional; not a hedge by itself)
  • symbols_list / symbols_describe - Symbol discovery + contract details

Workflow

When asked to allocate/hedge across multiple symbols or trades:

  1. Intake

    • Require candidate legs with: plan_id, symbol, action_directive, direction, order_type, entry, stop_loss, take_profit (and pending_expiration if order_type is pending).
    • Require constraints: max_total_risk_pct (portfolio cap) and max_risk_per_leg_pct (per-trade cap). If missing, assume "propose only" and ask Rhea for the configured limits.
    • If symbols are ambiguous, request Nina to resolve broker symbols and contract quirks.
  2. Snapshot current exposure

    • trade_get_open()
    • trade_get_pending()
    • trade_risk_analyze() for current risk totals and SL hygiene.

Read the full file on GitHub · 139 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 · 139 lines · 23 tokens per session scan A a39268957d9f

Subscribe to this mod's changes

harper is an agent published in the GitHub repository emerzon/mtdata-mcp (22 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,385 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