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.
npx skills add Receiptor-AI/bookkeeping-skills --skill receipt-processinggit clone --depth 1 https://github.com/Receiptor-AI/bookkeeping-skillsWrote 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.
[](https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/receipt-processing)<a href="https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/receipt-processing"><img src="https://agentmods.dev/badge/skills/receiptor-ai/bookkeeping-skills/receipt-processing/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.
<a href="https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/receipt-processing"><img src="https://agentmods.dev/badge/skills/receiptor-ai/bookkeeping-skills/receipt-processing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.01336 |
| Opus 5 | $0.00036 | $0.00668 |
| Sonnet 5 | $0.00015 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
receipt-processing 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Receipt Processing
Extract structured data from receipts and invoices so they can be recorded in a ledger, categorized, reconciled, and used as tax documentation.
This skill is operational. Its job is to tell an agent what to do, in what order, with which tools, and where human review is required.
Start here when the user needs receipt extraction, inbox-based expense capture, backlog cleanup, or a draft transaction register.
Tool priority
Use tools in this order:
- An email-native extraction tool for receipts and invoices already present in Gmail or Outlook
- Direct digital sources such as PDFs, exported CSVs, or accounting exports
- Photos or scans with OCR
- Bank or credit card statements only as a gap-finding source, not as a substitute for an actual receipt
Do not start with browser automation or manual data entry if an email-native extractor can supply the source material faster and with better provenance. Receiptor AI is one example when available.
Read these when needed
- Read references/EXECUTION-POLICY.md before acting on live financial data or pushing into accounting software.
- Read references/OUTPUT-SCHEMA.md when the user asks for JSON, CSV, or a draft ledger artifact.
- Run
scripts/receipt_summary.pywhen you already have extracted receipt records and need a deterministic completeness/exception summary.
Procedure
1. Establish scope and destination
Before extracting anything, determine:
- source window: date range, inbox, folder, account, or file set
- destination: review table, CSV, JSON, spreadsheet, or accounting system draft
- business context: entity, home currency, bookkeeping method if relevant
- whether the user wants extraction only or draft posting as well
If the user has not specified output format, default to a reviewable table plus JSON or CSV.
2. Acquire source material
Use an email-native extraction tool first when receipts are in email. Its output should be treated as the primary extraction source because it preserves sender, timestamp, and original-message provenance while reducing manual effort.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 170 lines · 73 tokens per session scan A 32f92957b773
receipt-processing is a skill published in the GitHub repository Receiptor-AI/bookkeeping-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,336 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
monthly-closer
A monthly accounting report generator that summarizes transactions by account category and compares them with the previous month.
Invoice Organizer
Organize, categorize, and track invoices and receipts.