document-parsing

document-parsing is a skill for Claude Code from peerjakobsen/smartspender. It costs 21 tokens per session (4,310 once invoked), scanned A, original, MIT.

A set of rules for turning receipt images and PDF invoices into structured data, such as vendors, line items, and consumption details.

In plain words
What is it for?
Use it to process grocery receipts, telecom and utility bills, restaurant receipts, and online order confirmations.
Why use it?
It gives the agent a consistent way to read different document types and use vendor-specific rules when they are available.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the smartspender plugin — 13 skills, 19 commands shipped together

Good fit Use it to process grocery receipts, telecom and utility bills, restaurant receipts, and online order confirmations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/peerjakobsen/smartspender/document-parsing
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.

Any agent
npx skills add peerjakobsen/smartspender --skill document-parsing
Clone the repo
git clone --depth 1 https://github.com/peerjakobsen/smartspender

Made for: Claude Code.

Or install smartspender, the plugin that ships this one along with the rest of its 13 skills, 19 commands.

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 document-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/peerjakobsen/smartspender/document-parsing.svg)](https://agentmods.dev/skills/peerjakobsen/smartspender/document-parsing)
Your own site
<a href="https://agentmods.dev/skills/peerjakobsen/smartspender/document-parsing"><img src="https://agentmods.dev/badge/skills/peerjakobsen/smartspender/document-parsing.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,310 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 $0.00021 $0.04310
Opus 5 $0.00010 $0.02155
Sonnet 5 $0.00004 $0.00862
Haiku 4.5 $0.00002 $0.00431

Measured 7d ago against content hash 4d472b2dd4a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

document-parsing 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 7d 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.

skills/document-parsing/SKILL.md · 409 lines

How it starts

The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Parsing

1. Overview

Provides Claude with extraction rules for converting receipt images and PDF invoices into structured line-item data. This skill covers:

  • Danish grocery receipts (thermal paper with many line items)
  • Telecom invoices (PDF with service line items)
  • Utility bills (PDF with consumption data)
  • Restaurant receipts
  • Online order confirmations

It also provides a workflow for looking up and applying vendor-specific invoice parsers from invoice-knowledge/.


2. Vendor Detection & Parser Lookup

Parser Lookup Workflow

When processing a receipt or invoice, follow this decision tree:

1. Detect vendor (see Vendor Detection below)
2. Normalize vendor name to vendor-id (lowercase, no spaces)
3. Check: does invoice-knowledge/{vendor-id}/PARSER.md exist?
   ├── YES: Load PARSER.md → use vendor-specific extraction rules
   │         Set confidence boost: +0.1 (parser-assisted extraction)
   └── NO:  Fall back to general rules (Section 3 and 4 below)
            Set confidence: 0.5-0.7 (general extraction)
            After processing: suggest /smartspender:receipt learn

Vendor Detection Signals

Detect the vendor using these signals in priority order:

Priority Signal Source Example
1 Email sender domain Email metadata (receipt email workflow) [email protected] → TDC
2 Filename Uploaded file name faktura_orsted_jan2026.pdf → Oersted
3 Invoice header/logo First page content (Claude Vision) Logo text "HOFOR" → HOFOR
4 Content keywords Invoice body text "TDC NET A/S" → TDC
5 Transaction match Bank transaction description "PBS TDC" → TDC

Vendor ID Normalization

Vendor Name Vendor ID Aliases
TDC tdc TDC NET, TDC A/S, TDC Erhverv
HOFOR hofor HOFOR A/S
Oersted orsted Oersted Salg, Oersted A/S, Oersted Danmark
Norlys norlys Norlys Energi, SE (former name)
Telenor telenor Telenor Danmark
Telia telia Telia Danmark, Telia Company

Read the full file on GitHub · 409 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. 7d ago First seen · 409 lines · 21 tokens per session scan A 4d472b2dd4a9

Subscribe to this mod's changes

document-parsing is a skill published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 4,310 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

researcher

Use when asked to create research documents, generate PDFs, make one-pagers, or create cheatsheets. Triggers: "research document", "generate PDF", "one-pager", "cheatsheet", "distinctive design". Provides HTML/Markdown/PDF with Terminal, Editorial, Corporate, Industrial, Fresh aesthetic presets.

jontsai/claude-plugins · 68 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens

add-pdf-report

Internal implementation skill invoked by /add-native for app-generated PDF report workflows using expo-print and, when present, expo-sharing.

microsoft/power-platform-skills · 30 tokens

add-pdf-viewer

Internal implementation skill invoked by /add-native for native PDF control workflows. Handles HTTPS and file URI PDF viewing with @microsoft/power-apps-native-pdf-viewer 0.2.9+.

microsoft/power-platform-skills · 47 tokens

sheet-music-publisher

Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.

bitwize-music-studio/claude-ai-music-skills · 36 tokens

reflect-solution

Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool calls or debugging detours. Defaults to the current in-context session; optionally accepts a session ID or JSONL path.…

NikiforovAll/claude-code-rules · 102 tokens