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 iterationlayer/skills --skill extract-violations-and-generate-summarygit clone --depth 1 https://github.com/iterationlayer/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/iterationlayer/skills/extract-violations-and-generate-summary)<a href="https://agentmods.dev/skills/iterationlayer/skills/extract-violations-and-generate-summary"><img src="https://agentmods.dev/badge/skills/iterationlayer/skills/extract-violations-and-generate-summary/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/iterationlayer/skills/extract-violations-and-generate-summary"><img src="https://agentmods.dev/badge/skills/iterationlayer/skills/extract-violations-and-generate-summary.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 | $0.00029 | $0.04662 |
| Opus 5 | $0.00015 | $0.02331 |
| Sonnet 5 | $0.00006 | $0.00932 |
| Haiku 4.5 | $0.00003 | $0.00466 |
Grade A, and why
extract-violations-and-generate-summary scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
EXTRACTION=$(curl -s -X POST https://api.iterationlayer.com/document-extraction/v1/extract \ How it starts
The opening of the file, as written. The whole thing — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extract Violations and Generate a Fine Summary
Fleet management agencies use this pipeline to process stacks of traffic fine notices — extracting violation details and generating a consolidated spreadsheet for client review, accounting, and driver accountability.
APIs Used
Document Extraction (1 credit per page), Sheet Generation (1 credits/request)
Prerequisites
You need an Iteration Layer API key. Get one at platform.iterationlayer.com during the 7-day trial.
For full integration guidance (SDKs, auth, MCP, error handling), see the Iteration Layer Integration Guide.
Implementation
# Step 1: Extract violation data from a fine notice
EXTRACTION=$(curl -s -X POST https://api.iterationlayer.com/document-extraction/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"files": [
{
"type": "url",
"name": "fine-notice-TRF-2026-4471.pdf",
"url": "https://example.com/fines/fine-notice-TRF-2026-4471.pdf"
}
],
"schema": {
"fields": [
{
"name": "violation_number",
"type": "TEXT",
"description": "Violation or ticket reference number"
},
{
"name": "violation_date",
"type": "DATE",
"description": "Date the violation occurred"
},
{
"name": "vehicle_plate",
"type": "TEXT",
"description": "License plate number"
},
{
"name": "driver_name",
"type": "TEXT",
"description": "Name of the driver if listed"
},
{
"name": "violation_type",
"type": "TEXT",
"description": "Type of violation, e.g. speeding, red light"
},
{
"name": "location",
"type": "TEXT",
"description": "Location where the violation occurred"
},
{
"name": "fine_amount",
"type": "CURRENCY_AMOUNT",
"description": "Fine amount"
},
{
"name": "due_date",
"type": "DATE",
"description": "Payment due date"
},
{
"name": "points",
"type": "INTEGER",
"description": "Penalty points assigned"
}
]
}
}')
# Step 2: Generate a summary spreadsheet
curl -X POST https://api.iterationlayer.com/sheet-generation/v1/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"format": "xlsx",
"sheets": [
{
"name": "Violation Summary",
"columns": [
{
"name": "Violation #",
"width": 20
},
{
"name": "Date",
"width": 14
},
{
"name": "Plate",
"width": 14
},
{
"name": "Driver",
"width": 22
},
{
"name": "Type",
"width": 18
},
{
"name": "Location",
"width": 30
},
{
"name": "Fine",
"width": 14
},
{
"name": "Due Date",
"width": 14
},
{
"name": "Points",
"width": 10
}
],
"rows": [
[
{
"value": "TRF-2026-4471"
},
{
"value": "2026-03-12",
"format": "date"
},
{
"value": "FL-8823-KM"
},
{
"value": "Marco Vitali"
},
{
"value": "Speeding (22 km/h over)"
},
{
"value": "A1 Motorway, km 142.3, Lazio"
},
{
"value": 185.00,
"format": "currency",
"currency_code": "EUR"
},
{
"value": "2026-04-11",
"format": "date"
},
{
"value": 3,
"format": "number"
}
]
]
}
]
}'
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.
- 6d ago First seen · 576 lines · 29 tokens per session scan A dfe37b1ad0ac
extract-violations-and-generate-summary is a skill published in the GitHub repository iterationlayer/skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 4,662 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
liteparse
Parse documents into LLM-ready content entirely on the local machine — PDF / DOCX / XLSX / PPTX / images → Markdown, structured JSON (with bounding boxes), or page screenshots, via the lit CLI. No cloud, no LLM, works offline. Use whenever the user attaches or points to a document that must be read before reasoning…
document-skills
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
work-markitdown
A document conversion tool that turns files such as Word documents, PDFs, PowerPoint presentations, spreadsheets, images, HTML, and CSV files into Markdown. Markdown is plain text with simple symbols for headings, lists, and other structure.
markitdown
A local document-conversion guide built around MarkItDown, a tool that turns files such as DOCX, PDF, PPTX, XLSX, images, HTML, and CSV into Markdown text.
dev-document
Document generation (PDF, DOCX, XLSX, PPTX). Trigger when the user wants to create a document, generate a report, export to PDF/Word/Excel/PowerPoint, or produce an office file.
markitdown
Convert files, URLs, and documents to Markdown using the markitdown MCP server. Activate when the user asks to convert, extract, or read content from PDFs, Word docs, PowerPoints, spreadsheets, images, audio files, or any URL.