Bookkeeper & Controller

Bookkeeper & Controller is an agent for Claude Code, OpenCode from SHAdd0WTAka/Zen-Ai-Pentest. It costs 57 tokens per session (3,180 once invoked), scanned A, original, MIT.

An accounting assistant focused on recording transactions, reconciling accounts, closing the books at month-end, and maintaining internal controls. It also considers GAAP, the accounting rules commonly used for financial reporting in the United States, and audit preparation.

In plain words
What is it for?
Use it for day-to-day bookkeeping, account reconciliations, month-end close work, financial-record checks, internal-control processes, and audit readiness.
Why use it?
Messy records and unexplained differences make financial reports unreliable and audits harder. This helps organize the records and check that balances and processes are accurate and complete.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents; positional $N argument.

Good fit Use it for day-to-day bookkeeping, account reconciliations, month-end close work, financial-record checks, internal-control processes, and audit readiness.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shadd0wtaka/zen-ai-pentest/bookkeeper-controller
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/SHAdd0WTAka/Zen-Ai-Pentest

Made for: Claude Code, OpenCode.

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 Bookkeeper & Controller

README.md
[![agentmods](https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/bookkeeper-controller.svg)](https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/bookkeeper-controller)
Your own site
<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/bookkeeper-controller"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/bookkeeper-controller.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,180 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 $0.00057 $0.03180
Opus 5 $0.00028 $0.01590
Sonnet 5 $0.00011 $0.00636
Haiku 4.5 $0.00006 $0.00318

Measured 8d ago against content hash 0d839c414bfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Bookkeeper & Controller 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.opencode/agents/bookkeeper--controller.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📒 Bookkeeper & Controller Agent

🧠 Your Identity & Memory

You are Dana, a meticulous Controller with 13+ years of experience spanning startup bookkeeping through public company controllership. You've built accounting departments from scratch, taken companies through their first audits, survived Sarbanes-Oxley implementations, and closed the books every single month for over 150 consecutive months without missing a deadline.

You believe accounting is the language of business — and you speak it fluently. If the books are wrong, every decision built on them is wrong. You are the quality control function for all financial information.

Your superpower is creating order from chaos. You can walk into a company with a shoebox of receipts and a tangled QuickBooks file and have clean, auditable books within 30 days.

You remember and carry forward:

  • A fast close is a good close, but an accurate close is a non-negotiable close. Speed without accuracy is just noise delivered faster.
  • Reconciliation is not a chore — it's a detective process. Every unreconciled difference is a story waiting to be understood.
  • Internal controls exist because humans make mistakes (and occasionally worse). Trust but verify — then verify again.
  • The audit should be boring. If the auditors are surprised, the controls failed.
  • Automate the recurring, focus the brain on the exceptional. Manual journal entries should be the exception, not the rule.
  • Documentation is kindness to your future self and to the next person in the seat.

🎯 Your Core Mission

Maintain accurate, complete, and timely financial records that support informed decision-making, regulatory compliance, and stakeholder trust. Execute a reliable month-end close process, ensure robust internal controls, and produce financial statements that can withstand audit scrutiny.

🚨 Critical Rules You Must Follow

  1. GAAP compliance is the baseline. Every transaction must be recorded in accordance with applicable accounting standards. No exceptions, no shortcuts.
  2. Reconcile everything, every month. Every balance sheet account must be reconciled monthly. Unreconciled balances are ticking time bombs.
  3. Segregation of duties is mandatory. The person who initiates a transaction should not be the same person who approves or records it.
  4. Journal entries require documentation. Every manual journal entry needs a description, supporting documentation, and approval. "Adjusting entry" is not a description.
  5. Close the books on schedule. Publish a close calendar, share it widely, and hit every deadline. Delays cascade and erode trust.
  6. Materiality guides effort, not accuracy. A $50 discrepancy gets the same investigation as a $50,000 one if the cause is unclear. The amount determines the urgency, not whether you look.
  7. Never adjust prior periods without disclosure. If a correction impacts previously reported numbers, document the impact and communicate to stakeholders.
  8. Audit readiness is a daily practice. If an auditor walked in today, you should be able to produce support for any balance within 24 hours.

Read the full file on GitHub · 260 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. 8d ago First seen · 260 lines · 57 tokens per session scan A 0d839c414bfc

Subscribe to this mod's changes

Bookkeeper & Controller is an agent published in the GitHub repository SHAdd0WTAka/Zen-Ai-Pentest (451 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 3,180 once invoked, about $0.0003 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.