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 Elnora-AI/elnora-merit-aktiva --skill merit-tsdgit 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/skills/elnora-ai/elnora-merit-aktiva/merit-tsd)<a href="https://agentmods.dev/skills/elnora-ai/elnora-merit-aktiva/merit-tsd"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-tsd/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/elnora-ai/elnora-merit-aktiva/merit-tsd"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-tsd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 133 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00298 | $0.02965 |
| Opus 5 | $0.00149 | $0.01483 |
| Sonnet 5 | $0.00060 | $0.00593 |
| Haiku 4.5 | $0.00030 | $0.00297 |
Grade A, and why
merit-tsd 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 12d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merit — TSD lisa 5 & lisa 6 (the non-payroll annexes)
An Estonian company files one TSD per calendar month, due the 10th of the following month. Payroll is only part of it. Two annexes come from the accounting side and are routinely missed:
- lisa 5 — kingitused, annetused, vastuvõtukulud (gifts, donations, entertainment)
- lisa 6 — ettevõtlusega mitteseotud kulud (expenses unrelated to business)
Merit does not file either. Merit Palk's "Saada TSD" submits the payroll annexes (lisa 1 / lisa 2) and knows nothing about lisa 5 or lisa 6; Merit Aktiva files no TSD at all. If a month has a lisa 5 or lisa 6 item, complete the return in e-MTA → Maksud → Tulu- ja sotsiaalmaksu deklaratsioon (TSD) — and if payroll was already sent from Palk, add the missing annex there before the 10th rather than leaving it off.
Is a TSD mandatory this month?
TuMS § 54 lg 2 — a resident legal person must declare the costs and payments named in §§ 49–53 for the previous calendar month. So a single entertainment cost or one euro of tax-authority interest makes the return mandatory, even when the tax works out to zero. There is no de-minimis threshold and no "not worth it" exemption.
Practical check each month: any payroll (lisa 1/2), any fringe benefit (lisa 4), any gift, donation or partner hospitality (lisa 5), any fine / sunniraha / tax-interest / undocumented payment (lisa 6), any distribution (lisa 7)? Any one of them → file.
Rate — always 22/78
TuMS § 4 lg 1 sets 22%, and § 4 lg 1¹ divides the taxable amount by 0,78 before
applying it. So the tax on a base amount is base ÷ 0,78 × 22%, i.e. 22/78 ≈ 28,205 %
of the base. Compute it that way, never as 22% of the base.
Pay to the tax authority by the same 10th (§ 54 lg 4).
lisa 6 — ettevõtlusega mitteseotud kulud
TuMS § 51 lg 1 taxes a resident company on expenses unrelated to business. § 51 lg 2 defines them:
| § 51 lg 2 | What |
|---|---|
| p 1 | the costs in § 34 punktid 3–6, 11 ja 13 |
| p 2 | joining/membership fees to non-profits where participation is not directly business-related |
| p 3 | payments with no source document meeting the Accounting Act's requirements |
| p 4 | buying services unrelated to the company's business |
| p 5 | discharging obligations unrelated to the company's business |
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.
- 12d ago First seen · 181 lines · 298 tokens per session scan A c568f48c4ea9
merit-tsd is a skill published in the GitHub repository Elnora-AI/elnora-merit-aktiva (8 stars, last pushed 5d ago), licensed Apache-2.0. It adds 298 tokens to every session and 2,965 once invoked, about $0.0015 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 skills, from other repositories
capitoltrades-cli
Queries US congressional stock trades (STOCK Act disclosures) on capitoltrades.com via the cli-web-capitoltrades command-line tool — trades with rich filters, politician profiles and leaderboards, issuer lookup with price history, plus insight articles, buzz, and press. Use when the user asks about congress trades…
watch
Watch live IDX turnover and order books for unusual activity — value surges, auto-reject approach, one-sided depth, walls appearing or withdrawn, quiet stocks waking up, UMA flags — plus delayed print-by-print attribution and end-of-day broker context. Use when the user runs /watch, or asks what is trading right now…
stockbit-status
Check whether the Stockbit session is still valid — main session expiry, whether trading credentials are stored, and the current trading mode. Use when the user asks "am I still logged in to Stockbit", "has my session expired", "is trading on", or when a stockbit MCP tool starts failing with an auth error.
stockbit-auth
Log in to Stockbit and capture the session for this server — opens the browser login flow and verifies the token was stored. Use when the user asks to log in or re-authenticate to Stockbit, or after a status check reports the session expired, HTTP 401, or logged out.
trade-with-guardrails
Place an order through the user's own Stockbit account safely — check the mode, size the position from a risk budget, preview, read the summary back to the human, and only then write. Use when the user asks to buy, sell, amend or cancel an order, or to size a trade.
bandar-check
Answer "who is accumulating this stock?" for an IDX ticker using Stockbit broker-flow data. Use when the user asks about bandar, big money, accumulation, distribution, foreign flow, asing, or who is on the other side of the tape.