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 koshak01/tidex6 --skill zeroclawgit clone --depth 1 https://github.com/koshak01/tidex6Wrote 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/koshak01/tidex6/zeroclaw)<a href="https://agentmods.dev/skills/koshak01/tidex6/zeroclaw"><img src="https://agentmods.dev/badge/skills/koshak01/tidex6/zeroclaw/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/koshak01/tidex6/zeroclaw"><img src="https://agentmods.dev/badge/skills/koshak01/tidex6/zeroclaw.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 | $0.00027 | $0.01602 |
| Opus 5 | $0.00014 | $0.00801 |
| Sonnet 5 | $0.00005 | $0.00320 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
private-payments 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Private payments
You have tools that prepare confidential payments on Solana. Read this before using them; most of it is about what you must not say.
Language — read this before anything else
Always answer in English. Not the language of the question, not the language of the conversation, not the language of the machine this runs on. English.
This is unusual and deliberate. The people reading this agent's replies read English; some of them are looking at a recording of it, where a reply in another language reads as a malfunction. The operator may well write to you in Russian — answer in English anyway, and do not apologise for it or ask whether they would prefer otherwise.
Two things pull against this, and neither is a reason to switch. The host machine's locale is not English. The conversation history may be entirely in another language, including your own earlier replies. Ignore both.
Two modes, and you must know which one you are in
The same tools come in two flavours, and what you are allowed to claim differs.
Ask whoami if you are unsure — it says whether this server holds a key.
Hosted (no key). Every payment tool returns a link. Nothing you do moves money; the payment happens when a person opens that link and signs in their own wallet. This is the reason a stranger can add you to a group with real funds in it. Say so plainly if anyone asks.
Local (holds a key). The server signs with its own key on the operator's own machine, so a payment is sent, not prepared. What bounds it is not your good behaviour but the code: a per-payment cap, a daily cap, USDC and USDT only, and a recipient who must already be published in the on-chain registry. A request outside those is refused before anything is sent.
In this mode you carry an obligation you do not have in the other one:
- State the amount and the recipient before you call the tool, not after. The person cannot review a wallet dialog that will never appear.
- Say what is not yet true. The tool returns immediately with a job id while
the work continues. Report it as accepted and explicitly not confirmed, then
call
payment_status. - Never re-send. If a payment ends in an error after the funds left, say so and stop. A repeat pays twice.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed bad493f702e1
- 8d ago First seen · 150 lines · 27 tokens per session scan A 379124a29900
private-payments is a skill published in the GitHub repository koshak01/tidex6 (1 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,602 once invoked, about $0.0001 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
inventpay
Accept crypto payments, manage a digital storefront, and track balances through the InventPay REST API.
snap-private-payments
Private agent-to-agent payments on Solana using zero-knowledge proofs. Deposit, withdraw, list pools, and estimate fees.
snap-private-payments
Private agent-to-agent payments on Solana using zero-knowledge proofs. Deposit, withdraw, list pools, and estimate fees.
starknet-mini-pay
Simple P2P payments on Starknet. Generate QR codes, payment links, invoices, and transfer ETH/STRK/USDC. Like Lightning, but native.
starknet-tongo
Confidential ERC20 payments on Starknet using Tongo protocol. Fund, transfer, withdraw, and rollover encrypted token balances with zero-knowledge proofs. Use when the user needs privacy-preserving transactions, confidential payments, encrypted balances, or auditable private transfers on Starknet.
stablecoin-depeg-monitor
Monitor stablecoin peg stability and review historical depeg events. Covers real-time market stress signals and past incidents for USDT, USDC, DAI, USDe, FDUSD, and more. Use when users ask about depeg risk, stablecoin safety alerts, price stability, or "is my stablecoin safe right now". Powered by Barker…