What is bookkeeper-starter CLAUDE.md?

Project instructions for Bookkeeper, a bookkeeping system that keeps separate double-entry records in Google Sheets and stores PDF documents in Google Drive for multiple clients.

Managing client ledgers, importing bank and payment statements, processing expenses, reviewing exceptions, closing monthly accounts, onboarding clients, and creating invoices.

They help an agent work within each client's records, follow important rules, and require human approval at key points. This reduces the risk of mixing clients or changing financial data incorrectly.

How audrey-560/bookkeeper-starter configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to audrey-560/bookkeeper-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/audrey-560/bookkeeper-starter/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/audrey-560/bookkeeper-starter

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/instructions/audrey-560/bookkeeper-starter/claude-md/github.svg)](https://agentmods.dev/instructions/audrey-560/bookkeeper-starter/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/audrey-560/bookkeeper-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/audrey-560/bookkeeper-starter/claude-md/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/instructions/audrey-560/bookkeeper-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/audrey-560/bookkeeper-starter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,067 This file is loaded in full into every session.

When invoked 1,067 The same file — it is already loaded in full.

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	$0.01067	$0.01067
Opus 5.5	$0.00427	$0.00427
Sonnet 5.5	$0.00213	$0.00213
Haiku 4.5	$0.00107	$0.00107

Measured 2mo ago against content hash 318d216f1d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bookkeeper-starter CLAUDE.md 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 2mo 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.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bookkeeper — AI Bookkeeping OS (multi-client)

A productized bookkeeping system: per-client Google Sheets double-entry ledgers + Drive PDF archives, operated by deterministic tools behind human approval gates. Every command takes --client <slug>; with no flag it acts on DEFAULT_CLIENT (sandbox-demo, the bundled example tenant). New here? Start with README.md. Docs: docs/PRODUCT.md (what/who), docs/ARCHITECTURE.md (how), docs/CONTROLS.md (trust model), docs/LIMITATIONS.md (honest boundaries).

Layout

Path	What
`clients/<slug>/`	Tenant: `profile.json` (entity, money map, tax, invoicing), `.env` (secrets, 600), `customers.json`, `inbox/` (statement drop), `state/` (import ledger, posted index, learned rules, exceptions, close states, audit log)
`tools/`	Deterministic Python. All take `--client` (default `sandbox-demo`) via `client_context.py`
`tools/importers/`	Statement adapters: rbc_csv, wise_csv, stripe_csv, generic_csv (+ stubs)
`workflows/`	SOPs: monthly_close, import_statements, process_expenses, exception_review, corrections, onboarding, generate_invoice
`jurisdictions/`	Tax packs: ca-on (production), us-federal + generic-vat (stubs)
`institutions/`	Registry + per-bank download instruction cards
`docs/`	Product documentation
`tests/`	`contract_test.sh` (run after ANY change), personas, fake sheets client

Key invariants (do not break)

One Journal writer: every JE goes through post_je() — COA check, Dr=Cr, period lock, dedupe key, audit log. Never append to Journal any other way.
Additive-only sheet schema: Invoices A–R frozen; new columns only to the right. Journal Q = Dedupe Key, Expenses Q = Txn ID.
Contract surface (the skills depend on it): mark_invoice_paid.py flags, clients/<slug>/customers.json via ctx.customers_path, sheets_client.py path. Run ./tests/contract_test.sh after any change.
No silent guessing: uncertainty → exceptions_queue, never the books.
Confirm every cloud write: dry-run → user OK → --commit.
Locked periods are immutable: corrections per workflows/corrections.md.
Judgment lives in workflows/packs/profiles — never hardcoded in tools.

Read the full file on GitHub · 75 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.

2mo ago First seen · 75 lines · 1,067 tokens per session scan A 318d216f1d16

Subscribe to this mod's changes

bookkeeper-starter CLAUDE.md is an instructions file published in the GitHub repository audrey-560/bookkeeper-starter (14 stars, last pushed 3mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0043 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 2026-08-30.

Documents Finance and fintech PDF Spreadsheets

bookkeeper-starter CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bookkeeper-starter CLAUDE.mdaudrey-560/bookkeeper-starter	Instructions file	14	3mo ago	MIT	A	1,067	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bookkeeper-starter: Instructions file for Claude Code