bookkeeper-starter: Skill for Claude Code

.claude/skills/invoice/SKILL.md

invoice is a skill for Claude Code from audrey-560/bookkeeper-starter. It costs 70 tokens per session (1,104 once invoked), scanned A, original, MIT.

A workflow for creating a client invoice as a PDF, uploading it to Drive, recording it in Google Sheets, and adding the related bookkeeping entry. An invoice is a request for payment for goods or services.

In plain words
What is it for?
It is for resolving a customer from the client registry, generating and issuing an invoice, logging it, and recording the journal entry.
Why use it?
It connects invoice creation with storage, tracking, and bookkeeping, reducing repeated data entry. It asks for confirmation before making cloud changes.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: positional $N argument.

This is audrey-560/bookkeeper-starter's own configuration. It tells Claude Code how to work on bookkeeper-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bookkeeper-starter configures →

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/skills/invoice/SKILL.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.

agentmods badge for invoice

README.md
[![agentmods](https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/invoice/github.svg)](https://agentmods.dev/skills/audrey-560/bookkeeper-starter/invoice)
Your own site
<a href="https://agentmods.dev/skills/audrey-560/bookkeeper-starter/invoice"><img src="https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/invoice/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 invoice

Your own site · 80×15
<a href="https://agentmods.dev/skills/audrey-560/bookkeeper-starter/invoice"><img src="https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/invoice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,104 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 $0.00070 $0.01104
Opus 5 $0.00035 $0.00552
Sonnet 5 $0.00014 $0.00221
Haiku 4.5 $0.00007 $0.00110

Measured 9d ago against content hash 3afb9f9c056e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

invoice 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/skills/invoice/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoice

Runs the full bookkeeper invoice workflow with a customer-registry layer on top so an existing client's billing details are auto-filled. User-invoked only — every run writes to Google Sheets and Drive and posts a journal entry, so pause for confirmation before each cloud write.

The tool commands and their exact flags live in the source-of-truth workflow: workflows/generate_invoice.md. This skill adds customer resolution + confirmation gates around those 6 steps. Do not re-derive the flags — read that workflow.

Step 0 — Enter the project

cd /path/to/bookkeeper

All paths below are relative to this directory. Tenant: the books belong to a bookkeeper client under clients/ — default sandbox-demo. If the user says the invoice is for a different client's books (--for <slug> or by context), append --client <slug> to EVERY tool command below; the registry is then that client's clients/<slug>/customers.json. Business identity, remittance details, tax rule, and invoice numbering all come from that client's profile automatically.

Step 1 — Resolve the customer

The argument $1 is the client name (may be partial, e.g. /invoice Acme). If no argument, ask who the invoice is for.

  1. Read tools/customers.json.
  2. Case-insensitively match $1 against client_name / keys (substring match is fine).
    • One match → show the stored client_name, client_address, currency, is_canadian_client, default_payment_terms. Ask the user to confirm or edit. If the address is blank, collect it now.
    • Multiple matches → list them, ask which one.
    • No match → new client. Collect client_name, client_address, currency (CAD/USD), and is_canadian_client (drives HST). Remember this is new — you'll offer to save it in Step 5.

Never silently overwrite a stored address — if the user changes it, confirm before saving.

Step 2 — Collect the invoice line items

Ask for the remaining inputs (see the input table in workflows/generate_invoice.md): services (description + amount per line), invoice_date (default today, America/Toronto), payment_terms (default the client's stored terms), optional due_date / notes. Currency and HST flag come from Step 1.

Read the full file on GitHub · 89 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 · 89 lines · 0 tokens per session scan A 3afb9f9c056e

Subscribe to this mod's changes

invoice is a skill published in the GitHub repository audrey-560/bookkeeper-starter (13 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,104 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.

Related

Other skills, from other repositories

cwicr-report-generator

Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 29 tokens

procesar-mis-estados-de-cuenta

Proceso un lote de estados de cuenta bancarios y de tarjeta de crédito en PDF o CSV de principio a fin: extraigo cada transacción (subagentes Haiku en paralelo), normalizo los nombres de las contrapartes, categorizo contra tu plan de cuentas bloqueado (subagentes Sonnet en paralelo), detecto transferencias entre…

gethouston/houston · 151 tokens

jangbu-import

A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.

kimlawtech/korean-jangbu-for · 97 tokens

receipts-to-expenses

Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.

skrun-dev/skrun · 54 tokens

investment-due-diligence-report

A tool for preparing investment due-diligence reports from sources such as spreadsheets, PDFs, and written materials. Due diligence is the research used to assess a potential investment.

xiaoyuge886/aigc · 120 tokens

prior-provider-worker-migration

Set up a company's workers in Check from any prior payroll provider's worker report. Accepts CSV, XLS, XLSX, or PDF reports and auto-detects the format — whether it's a tabular spreadsheet, a multi-line cell layout, or a PDF employee details report. Parses workplaces and worker data (employees and/or contractors)…

check-technologies/mcp-server-check · 194 tokens