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 anhermon/spark-ordernet-mcp --skill ordernetgit clone --depth 1 https://github.com/anhermon/spark-ordernet-mcpWrote 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/anhermon/spark-ordernet-mcp/ordernet)<a href="https://agentmods.dev/skills/anhermon/spark-ordernet-mcp/ordernet"><img src="https://agentmods.dev/badge/skills/anhermon/spark-ordernet-mcp/ordernet/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/anhermon/spark-ordernet-mcp/ordernet"><img src="https://agentmods.dev/badge/skills/anhermon/spark-ordernet-mcp/ordernet.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 | $0.00088 | $0.02258 |
| Opus 5 | $0.00044 | $0.01129 |
| Sonnet 5 | $0.00018 | $0.00452 |
| Haiku 4.5 | $0.00009 | $0.00226 |
Grade A, and why
ordernet 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.
This is a copy
86% identical to ingest — 181 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ordernet / Spark (Meitav Trade)
Read-only access to a Spark brokerage account, via the ordernet MCP server
(ordernet_mcp.py in this repo). Prefer the MCP tools over the browser — the UI is a
dense RTL Hebrew AngularJS app and the API returns the same numbers cleanly.
Hard boundary
Never place, modify or cancel an order, and never move money. The MCP server has no
code path for it: Session.request() enforces an exact GET allowlist; authentication is
the only POST and anything else is refused before the request is authenticated. Do not
add /api/Orders/SendOrder,
/api/Account/withdrawalAction, DepositAction, ConvertCurrencyAction or
CancelAction to that allowlist, and do not call them from a shell. If the user wants to
trade, they do it in the UI themselves.
Setup
Credentials live in the environment, never in a repo file. Copy the tracked
.mcp.example.json to the ignored local .mcp.json; keep credential values as
environment expansions:
{"mcpServers": {"ordernet": {
"command": "uv", "args": ["run", "--script", "/abs/path/ordernet_mcp.py"],
"env": {"ORDERNET_USERNAME": "${ORDERNET_USERNAME}",
"ORDERNET_PASSWORD": "${ORDERNET_PASSWORD}",
"ORDERNET_BROKER": "meitav"}
}}}
Export the two variables from the shell profile (or a keychain helper) that launches
Claude Code. Never write the password into .mcp.json, the skill, or any tracked file.
ORDERNET_BROKER selects the host: spark{broker}.ordernet.co.il — meitav, psagot,
ibi, nesua, gaon.
Health checks: uv run --script ordernet_mcp.py selfcheck (no credentials — decoder +
allowlist), ... livecheck (credentials — one call per read path, prints shapes only).
Tools
| Tool | Use it for |
|---|---|
accounts() |
account keys/numbers; needed only if the login has more than one |
portfolio(account?) |
current positions, cash, totals — the snapshot to analyse |
transactions(start_date, end_date, account?, dollar?) |
buys/sells/dividends/fees/deposits |
orders(date?, account?) |
that day's orders and fills |
order_history(order_key, date?) |
status/execution trail for one order from orders() |
standing_orders() |
standing-order definitions |
yields(year, monthly?, account?) |
monthly or daily return series |
resolve_securities(identifiers) |
exact bulk resolution to safe public metadata |
search_securities(query) |
resolve a name/symbol to a topic key |
price_history(topic_key, points?) |
daily OHLCV for a security |
latest_news() |
latest market-news items |
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 · 160 lines · 88 tokens per session scan A 61e507434636
ordernet is a skill published in the GitHub repository anhermon/spark-ordernet-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 2,258 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to ingest, differing in 181 lines, and is treated as a copy.
Other skills, from other repositories
okx-cex-portfolio
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
stripe
Query and manage Stripe resources (customers, payments, subscriptions). Reads from apps/website/.env. Write operations blocked on live keys.
recurrent-payment
A recurring-payment workflow for T-Kassa, a payment service. It links a customer's card during an initial payment and later charges that saved payment authorisation for a subscription.
refund-payment
A payment procedure for refunding a completed T-Kassa payment or cancelling a payment that is still on hold. T-Kassa is a payment service, and the procedure can also send the required closing receipt.
reconcile-day
Reconcile a day of MercadoPago activity — payments by status plus merchant orders.