facchini-mika

Pnl Aggregator — Development agent for Claude Code

Development community

Tier-1 Trade Evaluation.

How to install Pnl Aggregator

Installs to ~/.claude/agents/facchini-mika-autonomous-trading-pnl-aggregator.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/facchini-mika/autonomous-trading/HEAD/.claude/agents/pnl-aggregator.md -o ~/.claude/agents/facchini-mika-autonomous-trading-pnl-aggregator.md

Restart Claude Code, or start a new session, for it to be picked up.

What Pnl Aggregator does

name: pnl-aggregator description: Tier-1 Trade Evaluation. Aggregates resolved predictions into per-agent rolling PnL series. Deterministic — no tools, no network. tools: [] model: claude-haiku-4-5

Role

Cycle-scoped pnl-aggregator for the Tier-1 Trade Evaluation Team. Receives the curated `resolved_predictions` from `outcome-fetcher` (via the Lead) and folds them into per-agent rolling PnL series ready for the `agent-performance-updater`.

Inputs

`PnlAggregatorTask`:

  • cycle_id

Alternatives in Development

Full documentation available on GitHub

View Source Repository

Related Agents

Outcome Fetcher — Development agent for Claude Code

Outcome Fetcher

Tier-1 Trade Evaluation. Filters Lead-prefetched resolved predictions and advances the Tier-1 high-water mark.

Development community
Agent Performance Updater — Development agent for Claude Code

Agent Performance Updater

Tier-1 Trade Evaluation. Computes per-agent (hit_rate, sharpe, pnl, n_samples) rows for the agent_performance

Development community
Psychodrama Judge — Development agent for Claude Code

Psychodrama Judge

Use ONLY by psychodrama-protocol skill orchestrator. Aggregates R1 panel votes into a structured verdict; iden

Development community
Browser Testing — Development agent for Claude Code

Browser Testing

Browser automation and testing specialist. Uses playwright-cli (stateful Bash CLI) for deterministic scripted

Development community
Debug Memory Agent — Development agent for Claude Code

Debug Memory Agent

Records resolved bug root causes, anti-patterns, and process lessons into MEMORY.md in a structured, searchabl

Development community
Evaluation Orchestrator — Development agent for Claude Code

Evaluation Orchestrator

Use for coordinating evaluation experiments, managing experiment execution, and overseeing evaluation workflow

Development community

Related Skills

Review Forecast — AI skill for Claude Code

Review Forecast

Review a forecasting or time-series model — horizon, rolling-origin evaluation, seasonality, structural breaks

AI community
Openclaw Self Healing — AI skill for Claude Code

Openclaw Self Healing

32+ 4-tier autonomous crash recovery for Claude Code and any service — 64% auto-resolved, LLM-agnostic (Claude

AI community
SkillEvaluator — AI skill for Claude Code

SkillEvaluator

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic

AI community