jatin-gl

Recon Dispute Agent — AI skill for Claude Code

AI community

AI agentic workflow (Claude + tool-calling) that consumes reconciliation discrepancies, investigates each case with tools, classifies root cause, and proposes resolutions with a verifier loop.

How to install Recon Dispute Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open jatin-gl/recon-dispute-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Recon Dispute Agent does

AI agentic workflow (Claude + tool-calling) that consumes reconciliation discrepancies, investigates each case with tools, classifies root cause, and proposes resolutions with a verifier loop. Python + FastAPI

Alternatives in AI

Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
Omnara — by Ishaan Sehgal - A command center for AI agents that syncs Claude Code sessions across terminal, web, and mo 2.6k ★

README

recon-dispute-agent

[![CI](https://github.com/jatin-gl/recon-dispute-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/jatin-gl/recon-dispute-agent/actions/workflows/ci.yml) [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/) [![Claude](https://img.shields.io/badge/LLM-Claude%20(Anthropic)-d97757)](https://www.anthropic.com/) [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)

An **AI agent that investigates payment reconciliation discrepancies**. It takes the output of the [**payment-reconciliation-engine**](https://github.com/jatin-gl/payment-reconciliation-engine) — a list of transactions that don't line up between a PSP settlement and an internal ledger — and, for each one, runs a tool-using investigation with Claude: it pulls the PSP view, the ledger view, and the event trail, reasons to a root cause, and proposes a resolution. A second **verifier** agent then checks the conclusion against the evidence, and anything unproven is **escalated to a human**.

**The story.** The engine answers *"what doesn't reconcile?"* This agent answers *"why, and what should we do about it?"* — the judgment work a payments-ops analyst does by hand, framed as an agentic workflow with tool use, an adversarial verification pass, and a bias toward escalation over guessing.

It runs **fully offline with no API key** (a deterministic brain stands in for the model), which is how the whole thing is unit-tested end to end — then swaps to real Claude with a single flag.

What it demonstrates

A real agentic loop over custom tools — evidence gathering, a schema-valid terminal tool call to finalize, bounded steps.
A verifier / critic pass — an independent skeptical review of each proposed resolution, the standard guard against plausible-but-wrong LLM output.
Escalation under uncertainty — UNKNOWN / MANUAL_REVIEW instead of a confident g