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 nakazanie-ton/myrocket --skill xrocket-exchangegit clone --depth 1 https://github.com/nakazanie-ton/myrocketWrote 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/nakazanie-ton/myrocket/xrocket-exchange)<a href="https://agentmods.dev/skills/nakazanie-ton/myrocket/xrocket-exchange"><img src="https://agentmods.dev/badge/skills/nakazanie-ton/myrocket/xrocket-exchange/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/nakazanie-ton/myrocket/xrocket-exchange"><img src="https://agentmods.dev/badge/skills/nakazanie-ton/myrocket/xrocket-exchange.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 | $0.00087 | $0.01189 |
| Opus 5 | $0.00044 | $0.00594 |
| Sonnet 5 | $0.00017 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
xrocket-exchange 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.
xRocket Exchange
Use semantic xRocket MCP tools. Keep public analysis fast and keep every private or financial action fail-closed.
Start safely
- Identify the requested environment and operation. The environment is fixed when the MCP server starts. Public reads default to mainnet; before any write, name and verify the returned environment and prefer a testnet-configured server unless the user explicitly chose mainnet.
- Use
publicfor market data. Useprivate-readonly when account state is needed. Usefullonly when the user explicitly requests a supported financial action. - Never ask for the API token in chat or pass it as a tool argument. If account or order tools are unavailable, call
xrocket_onboarding_linkswhen present, ask the user to sign in, and direct them tonpx -y [email protected] trading-config --limit 100 --asset USDfor testnet-first local setup. Let the user choose the limit; do not solicit the secret. - Read references/api-map.md for tool selection. Read references/safety.md before any write, references/errors.md for failures, and references/advanced-workflows.md for multi-step work.
Public market workflow
- For a broad current-market question, call
xrocket_market_snapshot; it resolves an exact symbol or unambiguous base asset and returns rules, ticker, orderbook, trades, and fees together. - Use
xrocket_market_symbols,xrocket_asset_info, candles, rates, or another narrow tool only when the question needs more detail. - Preserve timestamps and decimal strings. Label stale or missing fields; do not synthesize funding rate, open interest, positions, leverage, or derivatives data because the audited API does not expose them.
- Describe the result as an xRocket REST snapshot, not a live WebSocket stream.
Private read workflow
- Confirm the user wants their account data and that
private-readorfullis configured locally. - Use
xrocket_account_overviewfor a whole-account question. Use balances, orders, transfers, withdrawals, or quotas for a narrow question. - Minimize disclosure in the answer. Do not echo the bearer token, full withdrawal addresses, or unrelated account data.
- Distinguish trading and funding balances. Describe Exchange transfers only as internal
funding↔tradingmoves.
What ships with it
7 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.
- 11d ago First seen · 67 lines · 87 tokens per session scan A 811f70ab936a
xrocket-exchange is a skill published in the GitHub repository nakazanie-ton/myrocket (0 stars, last pushed 17d ago), licensed MIT. It adds 87 tokens to every session and 1,189 once invoked, about $0.0004 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
alpha-arcade-interaction
Trade on Alpha Arcade prediction markets on Algorand — browse markets, read orderbooks, place limit/market orders, manage positions, cancel/amend orders, split/merge shares, and claim winnings. Use when user asks about prediction markets, event betting, YES/NO shares, orderbooks, or Alpha Arcade.
haystack-router-interaction
Route and execute optimal token swaps on Algorand using Haystack Router via Algorand MCP tools. Use when getting best-price quotes across multiple Algorand DEXes and LST protocols, executing atomic swaps, and checking asset opt-in — all through the Algorand MCP server.
algorand-x402-payment
Execute x402 payments at runtime using Algorand MCP tools. Use whenever an HTTP request returns 402 Payment Required (or a PAYMENT-REQUIRED header), the user needs to access a paid API or x402-protected resource, or the user mentions x402, micropayments, paying for an endpoint, or "payment required" — even if they…
openclaw-crypto-payments
Skill "openclaw-crypto-payments" from yedanyagamiai-cmd/openclaw-mcp-servers, covering openclaw crypto payments v2.0, what's new in v2.0, quick start, detection triggers and named protocols.
conviction-fm
Compete in daily crypto prediction competitions on conviction.fm. Create AI agents with natural language strategies, enter token pair pools, and climb the leaderboard. Uses MCP to provide tools for pool data, agent creation, position entry, and strategy management.
x402-payments
Quote and settle OpenMesha x402 paywalled services (USDC on Base). Use when metering tool calls, outcome fees, or agent-to-agent settlement.