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 MangroveTechnologies/mangrove-agent --skill connect-krakengit clone --depth 1 https://github.com/MangroveTechnologies/mangrove-agentWrote 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/mangrovetechnologies/mangrove-agent/connect-kraken)<a href="https://agentmods.dev/skills/mangrovetechnologies/mangrove-agent/connect-kraken"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/connect-kraken/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/mangrovetechnologies/mangrove-agent/connect-kraken"><img src="https://agentmods.dev/badge/skills/mangrovetechnologies/mangrove-agent/connect-kraken.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 | $0.00138 | $0.00897 |
| Opus 5 | $0.00069 | $0.00449 |
| Sonnet 5 | $0.00028 | $0.00179 |
| Haiku 4.5 | $0.00014 | $0.00090 |
Grade A, and why
connect-kraken 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Kraken (keyless, OAuth)
The agent's job here: connect the user's Kraken account for trading through the agent without the user ever creating, copying, or holding an API key.
The model — say this up front
- No key, ever. The user consents once on Kraken's own site (a browser OAuth screen). Mangrove's platform holds the resulting grant, KMS-encrypted, and mints a short-lived, scoped key per order — nothing long-lived exists anywhere, and no credential is ever pasted in chat or stored on this machine.
- You choose what you authorize. At connect time you pick a mode:
- view — read-only: balances and history. (default)
- execute — view plus order placement/cancellation. The choice drives what Kraken's consent screen grants; Mangrove can never do more than you approved. Deposits/withdrawals are never requested.
- Revocable two ways. Disconnect in Mangrove, or revoke the app under Kraken's Connected Apps settings.
- Contrast with BYOK (
setup-kraken): that mode keeps your own key on your machine and talks to Kraken directly, no Mangrove account needed. This mode needs a Mangrove account but never asks you to touch a key.
Step 1 — Start the connect
Call POST /api/v1/agent/cex/oauth/connect-start with {"mode": "view"} or
{"mode": "execute"}. It returns {authorize_url, state}.
Show the user the authorize_url and tell them: open this in your browser,
sign in to Kraken, and approve. If they chose execute, the consent screen
will list trading permissions; if view, it won't. That screen is the consent
— read it before approving.
Step 2 — Wait for the connection
Poll GET /api/v1/agent/cex/oauth/status until connected is true. Confirm the
returned connection.mode matches what they intended (view vs execute).
Step 3 — Use it
GET /api/v1/agent/cex/oauth/balances— balances (works in either mode).POST /api/v1/agent/cex/oauth/orders— place or dry-run an order. Always run once with"validate_only": truefirst and show the user the venue's own description of what would execute; place the live order only on their explicit go-ahead. Anexecute-mode connection is required — aviewconnection is refused by the platform.
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.
- 10d ago First seen · 74 lines · 138 tokens per session scan A 079b433e58c3
connect-kraken is a skill published in the GitHub repository MangroveTechnologies/mangrove-agent (5 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 897 once invoked, about $0.0007 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
t2000-job
Escrow USDC for agent-to-agent deliverable work (A2A jobs). Use when hiring another agent for async work (research reports, builds, SLA tasks) or when selling deliverable work yourself (list a service: fixed price + SLA, no server needed), or posting/claiming open jobs on the board (t2 job open / claim) — anything…
t2000-receive
Generate a payment request for the t2000 Agent Wallet — print the wallet address, an ANSI QR code, and (via MCP) a Payment Kit URI (sui:pay?…). Use when asked to receive a payment, share a wallet address, create a payment link, or set up a fund-me link.
t2000-send
Send USDC, USDsui, or SUI from the t2000 Agent Wallet to another Sui address. Use when asked to pay someone, transfer funds, send money, tip a creator, or make a payment to a specific Sui address or SuiNS name. Do NOT use for API payments — use the t2000-pay skill for x402-protected services.
t2000-swap
Swap tokens on Sui via Cetus Aggregator (20+ DEXs, best-route across SUI, USDC, USDsui, USDT, USDe, ETH, GOLD, NAVX, WAL, vSUI, and more). Use when asked to swap, trade, convert, exchange, or "turn X into Y". Do not use for sending — use the t2000-send skill for transfers.
t2000-financial-amounts
Money and token-metadata safety — floor display amounts (never round up), per-token decimal precision, preset/chip amount math, and the canonical token registry that owns every coin type and decimal count. Use when formatting or displaying a balance, computing a max/percentage/preset amount, converting between display…
t2000-check-balance
Check the t2000 Agent Wallet balance on Sui. Use when asked about wallet balance, how much USDC / USDsui / SUI is available, or total funds. Also use before any send, swap, or pay operation to confirm sufficient funds exist.