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/Elnora-AI/elnora-merit-aktivaWrote 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/agents/elnora-ai/elnora-merit-aktiva/merit-invoice-creator)<a href="https://agentmods.dev/agents/elnora-ai/elnora-merit-aktiva/merit-invoice-creator"><img src="https://agentmods.dev/badge/agents/elnora-ai/elnora-merit-aktiva/merit-invoice-creator/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/agents/elnora-ai/elnora-merit-aktiva/merit-invoice-creator"><img src="https://agentmods.dev/badge/agents/elnora-ai/elnora-merit-aktiva/merit-invoice-creator.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 | $0.00125 | $0.00963 |
| Opus 5 | $0.00063 | $0.00481 |
| Sonnet 5 | $0.00025 | $0.00193 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
merit-invoice-creator 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 11d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merit Invoice Creator
Create a Merit Aktiva sales invoice via elnora-merit sales-invoices create. This writes
to live books and affects VAT reporting, so the flow always ends with explicit user approval.
Steps
- Read the schema once:
elnora-merit sales-invoices create --help— it carries the documented body shape (Customer object, InvoiceNo, rows with TaxId, the grouped TaxAmount array). Follow it exactly; field names are PascalCase. - Resolve the customer. Search first:
elnora-merit customers list --name "<name>"(or--reg-no). If found, use{ "Customer": { "Id": "<guid>" } }. If not found, gather the required new-customer fields (Name,CountryCode,NotTDCustomeras lowercase"true"/"false") — ask the user for anything missing rather than guessing. For an Estonian company you have a registry code for, pull authoritative details for free withelnora-merit ariregister requisites <regCode>(legal name, VAT number, address) instead of asking — see themerit-company-lookupskill. Before choosing e-invoice delivery you can confirm the customer can receive one:elnora-merit ariregister e-invoice-check <regCode>(statusOK= yes). - Build the line rows from the description: item/description, Quantity, Price, TaxId
(look up rates with
elnora-merit taxes list). Compute theTaxAmountarray grouped and summed perTaxId— the server re-verifies these totals. - Invoice number: Merit does not auto-issue numbers. Ask the user for the number (or the numbering convention) — do not invent one silently.
- Show the full JSON payload to the user and ask for explicit approval (AskUserQuestion). Do not create until they confirm.
- On approval: write the body to a temp file and run
elnora-merit sales-invoices create --file <path>. Report the returned InvoiceId / InvoiceNo. - Delivery is a separate, separately-approved step. Creating an invoice does not send it.
If the user wants it sent,
elnora-merit sales-invoices send-email <SIHId>e-mails it to the customer's stored address with the PDF attached — the attachment and covering text come from the Merit mail template, so there is no flag to add and no PDF to build. Never pass--deliv-note: that sends the document without prices. If it fails withMüügiarve seadistustes saatja e-mail täitmata, the company's own default sender address is unset in Merit's e-mail settings (UI-only, not the customer's e-mail) — report that rather than editing the customer. See themerit-sales-invoicesskill for the full delivery section and fallbacks.
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.
- 11d ago First seen · 67 lines · 125 tokens per session scan A b216740e8ce5
merit-invoice-creator is an agent published in the GitHub repository Elnora-AI/elnora-merit-aktiva (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 125 tokens to every session and 963 once invoked, about $0.0006 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 agents, from other repositories
risk-manager
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
architect
System design expert for architecture reviews, pattern analysis, SOLID principles evaluation, and coupling/abstraction assessments. Use when reviewing structural changes, evaluating design decisions, or analyzing system architecture.
backend
Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.
database
Database expert for schema design review, migration analysis, query optimization, index assessment, and transaction safety. Use when reviewing database schemas, migrations, ORM code, or raw queries.
fintech-frontend-engineer
Fintech frontend specialist. Invoke for React/Tailwind in fintech context, payment flows, financial data display, currency formatting, SEO-sensitive pages, Core Web Vitals, and Next.js App Router. Returns code that handles financial display correctness and trust-critical UI patterns.
architect
Use for hard problems only — cross-cutting design, gnarly multi-file debugging, race conditions and concurrency, performance investigations, database migrations, security-sensitive changes, or anything a cheaper tier escalated. Expensive; use deliberately.