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 DaizeDong/buy-me-a-car --skill carfax-pdf-reviewgit clone --depth 1 https://github.com/DaizeDong/buy-me-a-carWrote 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/daizedong/buy-me-a-car/carfax-pdf-review)<a href="https://agentmods.dev/skills/daizedong/buy-me-a-car/carfax-pdf-review"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/carfax-pdf-review/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/daizedong/buy-me-a-car/carfax-pdf-review"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/carfax-pdf-review.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 | $0.00114 | $0.01984 |
| Opus 5 | $0.00057 | $0.00992 |
| Sonnet 5 | $0.00023 | $0.00397 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
carfax-pdf-review 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carfax & PDF Review
Caveat: this skill is one author's playbook + 5-scenario stress test. Verify state fees / CPO terms / EV credits / dealer practices against current sources before quoting numbers to a dealer or making financial decisions. Not tax, legal, or financial advice. last_verified: 2026-05-18 (Phase 2C sub-skill split from orchestrator)
Structured extraction from three common dealer-attached PDFs: CARFAX vehicle history, dealership service records, and OTD/financing proposals. Output is a typed red-flag report the buyer can act on.
When To Use
- Dealer email attaches a CARFAX PDF and buyer wants accident/owner/title verification
- Dealer attaches service records PDF and buyer wants completeness check
- Dealer attaches OTD proposal / financing worksheet and buyer wants F&I add-ons surfaced
- Buyer wants to verify dealer's verbal claims against the written PDF
When NOT To Use
- No PDF attached - skill cannot proceed; tell user to request the file from dealer
- PDF is text-extracted poorly (scanned image with no OCR) - flag to user, do not invent content
- Generic listing screenshot, not a PDF - hand off to inventory research in
../orchestrator
Critical Gotchas Up Front
- V1: CARFAX 1-Owner is necessary but NOT sufficient. A 1-owner car can still have unreported body damage or missing scheduled service. Always cross-check service records.
- V2: Read the PDF yourself with the Read tool. Never trust dealer's verbal summary. ("Just a fender bender" has masked $8k structural repairs.)
- D7: Dealer proposal PDFs sometimes render as image-only or with hidden text layers that Claude cannot see. If extraction fails, ask buyer to (a) open the PDF locally and paste the line items inline, OR (b) ask dealer to paste the OTD breakdown into email body as plain text.
Full gotcha list: ../orchestrator/references/pdf_review_checklist.md.
3-Section Workflow
Section 1 - CARFAX Analysis
- VIN match: confirm VIN on PDF matches VIN in dealer listing and buyer's notes. Mismatch = stop and re-confirm.
- Owner count: 1-owner is gold; 2-owner is fine if both held >2 years; 3+ owners in <5 years is a flip-warning.
- Accident detail extraction (use template below): impact zones, repair shop name, structural damage flag, airbag deployment flag, estimated ADAS recalibration cost (see ADAS table below).
- Service record completeness: count service entries vs vehicle age; flag gaps >18 months.
- Title brand: Salvage / Junk / Rebuilt / Lemon / Flood = walk away immediately.
- Odometer audit: last reported reading should match dealer's listed mileage within 500 mi.
- Open recalls: list each recall ID; demand written confirmation that all are resolved before purchase.
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.
- 12d ago First seen · 155 lines · 114 tokens per session scan A 6c1d261d9a14
carfax-pdf-review is a skill published in the GitHub repository DaizeDong/buy-me-a-car (5 stars, last pushed 8d ago), licensed MIT. It adds 114 tokens to every session and 1,984 once invoked, about $0.0006 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
pdf-report
Generate a branded, audience-structured marketing report — executive summary, campaign report, channel deep-dive, competitor report, or monthly/quarterly review — assembled via pdf-generator.py with brand colors, logo, and fonts, and previewed for adjustments before finalizing. Pulls data from campaign-tracker.py…
album-report
Turn an album or a selection into a PDF report: metadata per photo, frames per video, and Claude's own description of what is in each one. Use when the user says "PDF of the album", "album report", "export to PDF", "make a document with these photos", "catalog the album", "identify what is in each video and put it in…
ebook-drive
ค้นหาหนังสือหรือเอกสาร PDF จากแหล่งที่ถูกกฎหมายบนอินเทอร์เน็ต แล้วบันทึกเข้าโฟลเดอร์ Google Drive ของผู้ใช้ โดยอัตโนมัติผ่าน Google Apps Script — ผู้ใช้ไม่ต้องดาวน์โหลดหรืออัปโหลดไฟล์เองแม้แต่ขั้นตอนเดียว ใช้เมื่อผู้ใช้พิมพ์ชื่อหนังสือ/เอกสารพร้อมขอให้หาให้, แนบรูปปกหนังสือแล้วขอให้หา, หรือพูดถึงการเก็บ ebook/PDF…
ebook
ค้นหาและดาวน์โหลดไฟล์ PDF จากแหล่งที่ถูกกฎหมายบนอินเทอร์เน็ต ใช้เมื่อผู้ใช้ต้องการดาวน์โหลดไฟล์ PDF เช่น "หาและดาวน์โหลด Clean Code", "โหลด PDF นี้ให้หน่อย" หรือแค่วาง URL ลิงก์ PDF มาเลย เรียกใช้ผ่าน /ebook เท่านั้น — ไม่ auto-trigger จากบทสนทนา รองรับการตั้งค่า path บันทึกไฟล์และเปลี่ยน path ได้.
media-ocr-ai
Modern AI OCR with open-source + commercial-safe models: PaddleOCR (Apache 2.0, Baidu, 80+ languages, layout analysis, tables), EasyOCR (Apache 2.0, JaidedAI, 80+ languages, easiest install), Tesseract 5 (Apache 2.0, mature LSTM backend, 100+ languages), TrOCR (MIT, Microsoft transformer, the only one that really…
demand-draft
Draft a Letter Before Action or Letter of Claim from a completed intake, gated on a privilege / without-prejudice / waiver / admission checklist, with a .docx output, post-send checklist, and an offer to create a matter. Use when the user says "draft the demand", "write the [type] letter", or has a finished demand…