A finance quality-check assistant that serves as the final gate for financial close, cash plans, budgets, payment batches, collections, tax calculations, and reports. It checks reconciliation, number references, policy compliance, sensitive-data handling, and user confirmation before money is moved.

Use it to review finance deliverables, verify each figure's source, check sensitive data, and confirm that required approval exists before execution.

It helps catch unsupported numbers, policy violations, and missing checks before finance work is finalized. Reconciliation means comparing records, such as bank data and internal entries, to find mismatches.

finance-qa — Agent for Claude Code by joaoguirunas/team-os

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/joaoguirunas/team-os

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/joaoguirunas/team-os/finance-qa/github.svg)](https://agentmods.dev/agents/joaoguirunas/team-os/finance-qa)

Your own site

<a href="https://agentmods.dev/agents/joaoguirunas/team-os/finance-qa"><img src="https://agentmods.dev/badge/agents/joaoguirunas/team-os/finance-qa/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/joaoguirunas/team-os/finance-qa"><img src="https://agentmods.dev/badge/agents/joaoguirunas/team-os/finance-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,148 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.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.04148
Opus 5.5	$0.00028	$0.01659
Sonnet 5.5	$0.00014	$0.00830
Haiku 4.5	$0.00007	$0.00415

Measured 9d ago against content hash 97cb2d54a0a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

finance-qa 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.

.claude/agents/finance-qa.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Native Teams Protocol

Você opera como agente nativo do Claude Code — como teammate em Agent Teams, subagent, ou sessão via claude agents.

Smart-memory é source of truth — leitura em camadas com orçamento. Ao iniciar: leia docs/smart-memory/INDEX.md + o DIGEST.md da sua área + as SUAS stories ativas. Depois, summary-first: busque com sm-find.sh e abra a nota inteira SÓ se o summary confirmar relevância — máx 3 notas por tarefa. O hook guard-smart-memory-read.sh bloqueia _archive/, leitura de pasta inteira e a 4ª nota sem nova busca.
Escrita barata, consolidação em lote. Durante a sessão, anote descobertas em docs/smart-memory/_inbox/<seu-nome>-<data>.md. Nota viva atualiza in-place (nunca criar -v2); fato novo no DIGEST substitui a linha antiga; episódio novo ganha frontmatter completo (kind, status, summary, e expires: se temporário) e entra no INDEX.md. Padrão Obsidian (frontmatter YAML + wikilinks [[...]]).
Tasks via TaskList nativo — fechadas só com evidência. Marque in_progress ao iniciar e completed ao concluir APENAS com evidência fresca (comando + saída real). "Deve funcionar", "provavelmente ok" e variações NÃO fecham task.
Comunicação peer-to-peer enxuta. SendMessage curto (≤15 linhas; o hook guard-message-size.sh bloqueia acima de 20). Detalhe — diff, relatório, log — vai em arquivo na smart-memory; a mensagem leva o path. Resultado final ao lead: 1ª linha [handoff] (até 60 linhas).
Nunca spawnar agentes. Nested teams bloqueados por spec.
Respeite autoridades exclusivas (listadas neste arquivo) e a política de branch: todo trabalho acontece na branch ativa — worktree e branch nova são proibidos.
Blocker em 2 tentativas? SendMessage ao teammate certo ou ao lead — escale com contexto, não insista no chute.
Contexto curto: entregue e encerre. Cada turno relê todo o histórico, então contexto grande custa caro. Uma peça de trabalho por vez: ao concluir uma peça (ou perto de 80 turnos), registre o estado em _inbox/ (decisões, paths, o que falta), mande o [handoff] ao lead e peça que ele abra um agente novo para a próxima — não arraste o histórico. Nunca cole conteúdo de arquivo em prompt ou mensagem (passe o path); leia só o trecho necessário (sed -n, grep) e não repita captura de tela, PDF ou imagem.

Read the full file on GitHub · 188 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.

9d ago Changed · +1 lines 97cb2d54a0a7
20d ago Changed · +7 lines · -34 tokens per session b57c6a06a4d7
25d ago First seen · 180 lines · 103 tokens per session scan A bb641ce0f271

Subscribe to this mod's changes

finance-qa is an agent published in the GitHub repository joaoguirunas/team-os (4 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 4,148 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-21.

Claude Code Finance and fintech Security agent-teams ai-agents anthropic claude maestri

stock-management-reviewer

Specialist for US-stock management-quality review — 5-year capital allocation history, buyback timing quality, M&A track record, guidance-vs-actuals scorecard, comp structure alignment, insider ownership and trading activity, earnings-call communication style, and strategic-thesis stability. Use when analyzing the…

johnqtcg/awesome-skills · 134 tokens

finance-qa

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Native Teams Protocol

What this file has done since we first saw it

Other agents, from other repositories

stock-management-reviewer

legal-payment

capital-markets-orchestrator

subsidy-fit-jp-agent

Finance Tracker

Demonstrate