Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Hainrixz/agente-pagokitnpx agentmods add commands/hainrixz/agente-pagokit/compareWrote 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/hainrixz/agente-pagokit/compare)<a href="https://agentmods.dev/commands/hainrixz/agente-pagokit/compare"><img src="https://agentmods.dev/badge/commands/hainrixz/agente-pagokit/compare/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/hainrixz/agente-pagokit/compare"><img src="https://agentmods.dev/badge/commands/hainrixz/agente-pagokit/compare.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 | $0.00036 | $0.00608 |
| Opus 5 | $0.00018 | $0.00304 |
| Sonnet 5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
compare 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 5d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pagokit:compare
Comparisons in blog posts are generic. This one is for their situation, with arithmetic.
- Read the arguments. If country, amount or currency are missing, either infer them from
project-analyzeror ask once — a comparison without a concrete amount is just a feature table. - Run the engine for the situation:
node scripts/advise.js --country <ISO2> --amount <n> --currency <CUR> [--billing ...] [--methods ...]
- Pull the named providers out of
candidatesandrejected. A provider that was ruled out is often the most useful row in the table — say which filter removed it. - Read
skills/payment-advisor/data/providers/<id>.jsonfor each one, for the detail the index does not carry.
Output
<A> vs <B> — selling from <country>, charging <amount> <currency>
<A> <B>
Cost per charge <fee.explanation> <fee.explanation>
You receive <net> <net>
Buyer coverage ... ...
Subscriptions ... ...
Merchant of record ... ...
Onboarding <model>, ~<days> days ...
PagoKit can <integration_level> <integration_level>
Notification model <webhook | ...> ...
Settlement <payout_delay_days> ...
Where they actually differ:
• <the one or two things that would change the decision>
Ruled out for your situation:
• <name> — <filter>: <reason>
Lead with cost, because that is what they came for — but do not stop there. The decision is usually made by something the fee table does not show: an onboarding gate, a missing local rail, a merchant-of-record trade-off, or the fact that one of them will not send you a webhook at all.
Anti-patterns
- Do not compare providers on a generic 2.9% + 30¢ when the catalog has real figures for the actual amount and currency.
- Do not present a provider as available if the engine rejected it on merchant domicile or onboarding. Show it in the ruled-out list with the reason.
- Do not hide the
integration_leveldifference. "PagoKit builds A completely and only advises on B" is frequently the deciding factor. - Do not invent a fee. If the catalog has no figure, say so and link the pricing page.
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.
- 5d ago First seen · 61 lines · 36 tokens per session scan A 24de1a13ce38
compare is a command published in the GitHub repository Hainrixz/agente-pagokit (46 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 608 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
research
Professional equity research analysis with institutional-grade formatting.
close-review
Month-end close / GL compliance check — invokes accounting-reviewer to produce TM-accounting-{slug}.md with double-entry integrity, ASC 606 revenue-recognition, period-lock, and SOX ITGC gaps.
procurement-review
Procurement / source-to-pay compliance check — invokes procurement-reviewer to produce TM-procurement-{slug}.md with three-way match, segregation-of-duties, OFAC-screening, and SOX procurement-controls gaps.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
merit-customers
Find or create a Merit Aktiva customer (or vendor).
merit-invoices
List, find, or inspect Merit Aktiva sales/purchase invoices.