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 masked8knights/carsales-mcp --skill car-inspectiongit clone --depth 1 https://github.com/masked8knights/carsales-mcpWrote 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/masked8knights/carsales-mcp/car-inspection)<a href="https://agentmods.dev/skills/masked8knights/carsales-mcp/car-inspection"><img src="https://agentmods.dev/badge/skills/masked8knights/carsales-mcp/car-inspection/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/masked8knights/carsales-mcp/car-inspection"><img src="https://agentmods.dev/badge/skills/masked8knights/carsales-mcp/car-inspection.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 | $0.00108 | $0.00956 |
| Opus 5 | $0.00054 | $0.00478 |
| Sonnet 5 | $0.00022 | $0.00191 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
car-inspection 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Car Inspection (verify a listing)
You are helping a buyer assess a used vehicle from its listing photos and metadata.
The carsales-mcp server can return the listing's photos as image blocks
(get_listing_details / fetch with includeImages: true, and the deep-research
search/fetch tools). Use those images and the structured listing data
(price, year, odometer, badge, deal score) to form a judgement.
When to use
- User pastes a listing URL / listing id and asks "is this good?", "any issues?", "worth it?", "looks dodgy?", "check for damage".
- After a
search_cars/search_all_carsgood-deal hit, to do due diligence before recommending it.
Steps
- Fetch the listing with photos:
get_listing_details({ listingId or url, includeImages: true })(orfetchfor deep-research ids). Also callsearch_facebook_cars/search_all_carsto compare the asking price against similar cars. - Look at EVERY photo the model was given (exterior front/back/sides, interior, engine bay, dash/odometer, VIN plate, tyres, underbody if shown).
- Cross-check the listing metadata: does the odometer photo match the stated odometer? Does the VIN/Rego in the photo match the listing? Are there modifications not mentioned?
Inspection checklist (adapted from Vehicle Damage Assessor standards)
Report each that you can assess from the photos:
- Identity & docs: VIN plate readable and consistent; rego sticker present; no obvious cloned/wrong VIN; plates match listing.
- Structure / body: panel gaps even; no misaligned panels; no fresh paint overspray; no filler/bondo; no sagging; boot/doors close squarely.
- Rust / corrosion: wheel arches, sills, floor, suspension mounts, subframe, exhaust — note surface vs structural.
- Paint / accident signs: colour mismatch between panels; overspray on trims/rubbers; witness marks; mismatched panels suggesting prior crash.
- Glass & lights: cracks/chips in windscreen; mismatched headlight assemblies; condensation inside lights.
- Tyres & wheels: uneven wear (alignment/suspension issue); low tread; mismatched tyres; kerbed/cracked alloys.
- Interior: rips/stains; water stains (flood damage); warning lights on the dash; worn pedals inconsistent with odometer; aftermarket wiring.
- Engine bay: leaks; corroded terminals; missing/bodged components; non-factory modifications; signs of fire/flood.
- Safety systems: airbag warning lights; aftermarket/removed airbags.
- Modifications: lifts, tunes, exhausts — note effect on warranty/insurance and potential abuse (e.g. tuned hot hatches).
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 · 66 lines · 108 tokens per session scan A bd327528b48a
car-inspection is a skill published in the GitHub repository masked8knights/carsales-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 108 tokens to every session and 956 once invoked, about $0.0005 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
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.