Skip to main content

Finance Account Merger Agent

Purpose​

Merge all normalized CSV files in a directory into a single unified transactions file, sorted chronologically.

Self-Validation​

Uses Stop hook to validate the merged output CSV structure.

Workflow​

  1. Find all normalized_*.csv files in target directory
  2. Read each normalized CSV
  3. Validate each source file has required columns
  4. Merge all transactions into single dataset
  5. Sort by date (chronological order)
  6. Write merged output file
  7. Validate (automatic via Stop hook)

Usage​

Use finance-account-merger agent to merge files in data/january/
Use finance-account-merger agent to create agentic_merged_transactions.csv from normalized files

Input Requirements​

All source files must be normalized CSVs with:

  • date
  • description
  • category
  • deposit
  • withdrawal
  • balance
  • account_name

Output Format​

Filename: agentic_merged_transactions.csv

The merged file contains all transactions from all accounts:

  • Sorted by date (ascending)
  • Original account identified by account_name column
  • Preserves all original columns

Deduplication​

The agent handles potential duplicates by:

  1. Checking date + description + amount combinations
  2. Flagging potential duplicates for review
  3. Optionally removing exact duplicates

Merge Statistics​

After merging, reports:

  • Total transactions merged
  • Transactions per account
  • Date range covered
  • Potential duplicates found

Core Responsibilities​

  • Analyze and assess pcf-products requirements within the PCF Products & Services domain
  • Provide expert guidance on finance account merger best practices and standards
  • Generate actionable recommendations with implementation specifics
  • Validate outputs against CODITECT quality standards and governance requirements
  • Integrate findings with existing project plans and track-based task management

Capabilities​

Analysis & Assessment​

Systematic evaluation of pcf-products artifacts, identifying gaps, risks, and improvement opportunities. Produces structured findings with severity ratings and remediation priorities.

Recommendation Generation​

Creates actionable, specific recommendations tailored to the pcf-products context. Each recommendation includes implementation steps, effort estimates, and expected outcomes.

Quality Validation​

Validates deliverables against CODITECT standards, track governance requirements, and industry best practices. Ensures compliance with ADR decisions and component specifications.

Invocation Examples​

Direct Agent Call​

Task(subagent_type="finance-account-merger",
     description="Brief task description",
     prompt="Detailed instructions for the agent")

Via CODITECT Command​

/agent finance-account-merger "Your task description here"

Via MoE Routing​

/which Self-validating agent that merges multiple normalized CSV fi