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 state-fee-lookupgit 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/state-fee-lookup)<a href="https://agentmods.dev/skills/daizedong/buy-me-a-car/state-fee-lookup"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/state-fee-lookup/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/state-fee-lookup"><img src="https://agentmods.dev/badge/skills/daizedong/buy-me-a-car/state-fee-lookup.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 | $0.00090 | $0.02004 |
| Opus 5.5 | $0.00036 | $0.00802 |
| Sonnet 5.5 | $0.00018 | $0.00401 |
| Haiku 4.5 | $0.00009 | $0.00200 |
Grade A, and why
state-fee-lookup 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Fee Lookup
The public dataset covers 50 states and DC as a research index. Coverage does not mean all fields are verified or every tax mechanism is implemented. Do not answer from a legacy numeric value whose field_provenance.status is unverified.
Lookup procedure
- Resolve the vehicle's registration state and applicable transaction jurisdiction. Identify purchase versus lease, dealer versus private seller, vehicle/powertrain class, date, trade eligibility, exemptions and rebates.
- Read the exact field in
data/state_fees.jsontogether with its provenance. For a reviewed field, verify that the saved value matches the cited source value, the source is official, the review date is not stale/future, and the transaction is within the recorded effective scope. - If the field is unverified, follow the official agency/statute link and verify that field. Record the actual date of review, the applicable effective period if known, and the narrow transaction scope. Never copy an old record's verification date into a new review.
- For doc fees, distinguish a maximum from a disclosure rule, a finance-contract safe harbor, a filing fee or a typical dealer charge. Null plus unverified provenance means unknown. It does not mean unlimited.
- For registration, quote the actual class/weight/term/locality/plate/powertrain formula or obtain the transaction-specific fee. The calculator requires explicit title and registration values.
- Use the state calculator only when its profile supports the transaction and all required field evidence passes. Otherwise request an itemized dealer/DMV calculation.
check_freshness.py is a gate by default. --report-only allows a report containing unverified fields; malformed and empty data still fail. --calculator checks the enabled profiles' required tax fields. --state XX narrows the report. A passing profile check does not verify all other fields in that state.
Reviewed field table
This table is generated from the JSON by render_state_data.py --write-references. --check detects drift across all three tax reference surfaces. Reviewed dates and applicability live with each field in JSON. Unverified legacy rates/fees are deliberately not printed here.
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.
- 1mo ago Changed · -95 lines · -13 tokens per session 229df1d86c2a
- 1mo ago First seen · 189 lines · 103 tokens per session scan A d92f28a53837
state-fee-lookup is a skill published in the GitHub repository DaizeDong/buy-me-a-car (11 stars, last pushed 11d ago), licensed MIT. It adds 90 tokens to every session and 2,004 once invoked, about $0.0004 per session on Opus 5.5. 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
internal-controls-and-audit
Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…
capital-structure-and-covenants
Decides how the business is financed and what that financing then requires of it — debt versus equity, weighted average cost of capital as a hurdle rate, how much leverage cash flow can carry, and the financial, affirmative and negative covenants, definitions, test dates and cure rights that come attached. Use this to…
revenue-recognition
Determines when and how revenue is recognized — performance obligations, contract terms that change the answer, and the deal structures that create accounting problems. Use this to work out how a contract should be recognized, review a non-standard deal before it is signed, understand deferred revenue, or spot terms…
tax
Structures the tax questions a growing business faces — corporate income, sales and use, payroll, nexus, and the obligations created by hiring or selling somewhere new. Use this to work out what a new state or country obligates you to, prepare for a tax filing or audit, understand sales tax on your product, or check…
kyc-kancelaria-pl
Dla kancelarii przyjmującej klienta-spółkę. Składa teczkę KYC/AML: pobiera odpis aktualny KRS i status z białej listy VAT (wysyła tylko numer KRS albo NIP), przesiewa klienta, organ, prokurentów, wspólników, beneficjentów i osoby działające przez listy sankcyjne ONZ, UE i MSWiA - porównanie LOKALNE, nazwiska nie…
mortgage-compliance
You are operating under strict mortgage regulatory compliance rules. Every response you generate that touches on lending, rates, fees, qualifications, or loan terms MUST comply with the following regulations. Violations of these rules expose Lendtrain powered by Atlantic Home Mortgage and its borrowers to legal and…