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.
git clone --depth 1 https://github.com/Goldziher/ai-rulezWrote 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/commands/goldziher/ai-rulez/refund-order)<a href="https://agentmods.dev/commands/goldziher/ai-rulez/refund-order"><img src="https://agentmods.dev/badge/commands/goldziher/ai-rulez/refund-order/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/commands/goldziher/ai-rulez/refund-order"><img src="https://agentmods.dev/badge/commands/goldziher/ai-rulez/refund-order.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 | $0.00015 | $0.00098 |
| Opus 5.5 | $0.00006 | $0.00039 |
| Sonnet 5.5 | $0.00003 | $0.00020 |
| Haiku 4.5 | $0.00002 | $0.00010 |
Grade A, and why
refund-order 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 today.
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.
What it actually says
Refund order
- Run
billing refund --order $ARGUMENTS --dry-run --idempotency-key <key>and show the result to the user. - After the user confirms, run the same command without
--dry-run.
Done when
The refund id is printed and the order shows status refunded.
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.
- today First seen · 14 lines · 15 tokens per session scan A f73f524fc830
refund-order is a command published in the GitHub repository Goldziher/ai-rulez (163 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 98 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 2026-10-17.
Other commands, from other repositories
signed-policy-agentic-commerce
Run an agentic commerce chain under a signed Work Mandate, trip the escalation gate on purpose, and replay the gates on the ledger.
add
Add a second payment provider alongside an existing integration, without touching the one already running.
fields
Extract vendor, invoice number, PO, dates, subtotal, tax, total and currency from invoices, receipts and statements with the carrel CLI, and optionally save them as desk fields.
add-checkout
Create comprehensive shopping cart and checkout flow. Implement cart state management with Context API or Zustand. Create cart UI component with item list, quantity controls, and remove buttons. Calculate totals including subtotal, tax, shipping, and discounts. Add shipping address form with validation. Implement…
CLAUDE_CODE_F071_F073_F115_CHECKOUT
A checkout review task for replacing a fixed exchange rate with a current one. An exchange rate determines how an amount in one currency converts to another.
checklist
Generate a custom checklist for the current feature based on user requirements.