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 x3allamerican/skills --skill ifta-audit-defensegit clone --depth 1 https://github.com/x3allamerican/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/x3allamerican/skills/ifta-audit-defense)<a href="https://agentmods.dev/skills/x3allamerican/skills/ifta-audit-defense"><img src="https://agentmods.dev/badge/skills/x3allamerican/skills/ifta-audit-defense/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/x3allamerican/skills/ifta-audit-defense"><img src="https://agentmods.dev/badge/skills/x3allamerican/skills/ifta-audit-defense.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 | $0.00034 | $0.00771 |
| Opus 5.5 | $0.00014 | $0.00308 |
| Sonnet 5.5 | $0.00007 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
ifta-audit-defense 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IFTA Audit Defense
When an IFTA audit selects your carrier, defense matters. Goal: minimize additional tax + penalties.
Initial response (within 30 days of notice)
- Acknowledge receipt
- Request copies of audit notification
- Ask for specific records they want to see
- Note the audit period (which quarters)
Records to gather
- Quarterly returns for the audit period
- Fuel receipts (organized by quarter + state)
- Mileage records (ELD or trip sheets)
- Vehicle records (VINs, plate numbers, gross weight)
- Tax-paid fuel logs
- Sales invoices and receipts
During the audit
- Auditor visits your office (or you ship records)
- Sample period selected
- Records reviewed in detail
- Discrepancies identified
- Adjustments calculated
- Initial findings shared
How to defend
- Documentation quality — well-organized, complete records reduce audit time + findings
- ELD data — when available, ELD is highly persuasive
- Reasonable explanation — for any anomaly, have a story (driver took different route, weather event, etc.)
- Industry comparison — if your data is consistent with industry norms, that helps
- Personal use exclusion — if you exclude personal use, show your accounting
Common audit findings + defenses
- Mileage shortfall: actual miles > reported. Defense: re-examine the data source; may be auditor error.
- Fuel allocation off: state distribution doesn't match actual operation. Defense: provide route documentation.
- Tax-paid double-counting: same fuel claimed twice. Defense: receipts show single purchase; cross-reference dates.
- Personal use miles: claimed as business. Defense: provide written personal-use policy + driver records.
After the audit
- No additional tax: you're done.
- Small adjustment: pay it; document the change in your books.
- Significant adjustment: request administrative review (state-level appeal).
- Egregious finding or penalty: consider attorney representation.
Right of appeal
- Administrative review (typically 30 days to request)
- State-level hearing (varies by state)
- Civil action (rare, time-consuming)
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 First seen · 81 lines · 34 tokens per session scan A e96e83a1c70e
ifta-audit-defense is a skill published in the GitHub repository x3allamerican/skills (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 771 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
lians
Use Lians financial-grade agent memory - store and recall facts with a bitemporal model so stale revisions never contaminate context. Use whenever an agent needs persistent memory in finance, healthcare, or legal work, or when a task asks "what did we know on/before ", needs an audit trail, or must erase a data…
bartender
Use when a task needs the judgment of a Bartender — reconciling actual pour cost against theoretical liquor cost by drink category, deciding whether and how to cut off a guest, pricing a drink menu across well/call/premium tiers, closing out a till and comp log at shift end, or sequencing bar-top service against a…
bill-account-collector
Use when a task needs the judgment of a bill and account collector — prioritizing a delinquent-account portfolio by recovery likelihood, structuring a payment plan against a debtor's stated ability to pay, drafting an FDCPA/Reg F-compliant collection communication, handling a cease-and-desist or debt dispute, or…
einvoicing-zatca-peppol-compliance
Implement government electronic invoicing standards including UBL 2.1 XML, Peppol BIS Billing 3.0, and Saudi ZATCA (FATOORA Phase 2) compliance. Generate cryptographic invoice hashes (SHA-256), ECDSA secp256k1 digital signatures, TLV-encoded Base64 QR codes, and clearance/reporting API integrations. Trigger when…
connect-required-verification-information
Use this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required…
deal-desk
Use to manage pricing, packaging, and approval workflows for renewal negotiations.