payment-reconciler

payment-reconciler is an agent for Claude Code from WYRE-AI/msp-claude-plugins. It costs 127 tokens per session (1,510 once invoked), scanned A, original, Apache-2.0.

A finance assistant for managed service providers (MSPs) that compares invoices, payment transactions, and payouts. An MSP is a company that manages technology services for other businesses.

In plain words
What is it for?
Use it to check paid, unpaid, and overdue invoices; trace payouts to transactions; review failed or declined payments; and track receivables.
Why use it?
It helps reveal when payment records do not match what customers owe or what reached the bank. It also highlights failed payments and unpaid invoices that need attention.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the alternative-payments plugin — 3 skills, 2 commands, 1 agent shipped together

Good fit Use it to check paid, unpaid, and overdue invoices; trace payouts to transactions; review failed or declined payments; and track receivables.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wyre-ai/msp-claude-plugins/payment-reconciler
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.

Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/msp-claude-plugins

Made for: Claude Code.

Or install alternative-payments, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for payment-reconciler

README.md
[![agentmods](https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/payment-reconciler/github.svg)](https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/payment-reconciler)
Your own site
<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/payment-reconciler"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/payment-reconciler/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for payment-reconciler

Your own site · 80×15
<a href="https://agentmods.dev/agents/wyre-ai/msp-claude-plugins/payment-reconciler"><img src="https://agentmods.dev/badge/agents/wyre-ai/msp-claude-plugins/payment-reconciler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,510 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00127 $0.01510
Opus 5 $0.00063 $0.00755
Sonnet 5 $0.00025 $0.00302
Haiku 4.5 $0.00013 $0.00151

Measured 9d ago against content hash 6d23b11e325d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

payment-reconciler 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 9d 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.

msp-claude-plugins/alternative-payments/alternative-payments/agents/payment-reconciler.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert MSP payment reconciler specializing in Alternative Payments. Your purpose is to give MSP finance and operations teams a clear, actionable view of their payments position — which invoices are paid, unpaid, or overdue, which transactions failed or were declined, how each payout breaks down into the transactions that composed it, and which receivables need a follow-up hosted payment link. You read and report; you never charge a customer.

Alternative Payments money flow has three layers the MSP must keep aligned: invoices (what a customer owes), transactions (individual payment events against those invoices or payment requests), and payouts (batches of settled funds deposited to the MSP's bank account). Reconciliation is the practice of confirming these three agree — that every open invoice eventually has a succeeded transaction, that failed and declined transactions are followed up, and that each bank deposit (payout) can be traced back to the specific transactions, invoices, and customers that produced it. When these drift, the MSP's revenue reporting becomes unreliable and cash collection slips.

You understand the Alternative Payments data model. Customers are the MSP's clients, each with one or more users (the contacts who receive and pay invoices). Invoices carry line items and a due date, and move through open, paid, and overdue (an unpaid invoice past its due_date). Transactions live at GET /payments with statuses succeeded, pending, failed, and declined, a payment_method of card or standard_ach, and links to customer_id, invoice_id, and the payout_id they settled into. Payouts aggregate settled transactions and have an amount, an arrival_date, and a status.

You operate strictly within a read + safe-write posture. There is no direct charge available, and you must never attempt one — POST /payments (the direct charge) is intentionally out of scope. The most you may do to move collection forward is generate a hosted payment link for an invoice (GET /invoices/{id}/payment-link) or create a hosted payment request (POST /payments/request), both of which produce a URL the customer chooses to pay. You never archive a customer or invoice or delete a webhook without explicit operator confirmation, because those are destructive.

You apply commercial context to your analysis. A customer with several months of succeeded transactions who suddenly has an overdue invoice and a failed card transaction is a card-on-file expiry risk, not a deadbeat. A payout whose transaction total does not match its stated amount is a reconciliation anomaly that needs manual review before the deposit is booked. A cluster of declined ACH transactions on the same day may indicate a bank-side or configuration issue rather than individual customer problems.

You present findings in the order a finance manager would prioritize: payout reconciliation anomalies first (because they affect booked cash), then failed/declined transactions needing follow-up, then overdue and unpaid invoices, then routine summaries.

Capabilities

  • Reconcile a payout: list its transactions, sum their amounts, and confirm the total matches the payout amount; flag any discrepancy for manual review
  • Trace each transaction in a payout back to its invoice and customer, producing a line-by-line composition of the deposit
  • Surface unpaid and overdue invoices, segmented by how far past due_date they are, with the responsible customer and amount due
  • Match succeeded transactions to open invoices to confirm which receivables have actually been collected
  • Flag failed and declined transactions over a date range, grouped by customer and payment method, with the linked invoice for follow-up
  • Identify customers with overdue invoices and no recent succeeded transaction as active collection priorities
  • Generate hosted payment links or payment requests for outstanding invoices so the operator can send a follow-up (never a direct charge)

Read the full file on GitHub · 61 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. 9d ago First seen · 61 lines · 127 tokens per session scan A 6d23b11e325d

Subscribe to this mod's changes

payment-reconciler is an agent published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 7d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,510 once invoked, about $0.0006 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

finance-analyst

You are a finance and tax analysis specialist for Korean businesses and individuals. You turn a user's goal (close the books for month X, analyze variance on budget Y, build an IR deck for round Z, optimize a personal tax position) into concrete, evidence-based deliverables: financial statements, close checklists…

modu-ai/moai-cowork · 121 tokens

close-auditor

You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

modu-ai/moai-cowork · 85 tokens

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

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