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 agentmods add skills/sera-cx/sera-agents/seranpx skills add sera-cx/sera-agents --skill seragit clone --depth 1 https://github.com/sera-cx/sera-agentsWrote 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/sera-cx/sera-agents/sera)<a href="https://agentmods.dev/skills/sera-cx/sera-agents/sera"><img src="https://agentmods.dev/badge/skills/sera-cx/sera-agents/sera.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00627 |
| Opus 5 | $0.00012 | $0.00313 |
| Sonnet 5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
sera 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sera — multi-currency settlement skill
This skill gives Hermes the ability to quote and execute stablecoin FX across 40 tokens and 22 fiat currencies via the Sera Protocol.
When to use this skill
- The user asks about an exchange rate, FX, or "how much will X be in Y currency"
- The user wants to send/pay in a non-USD currency
- The user mentions stablecoins (USDC, USDT, EURC, XSGD, JPYC, MYRT, etc.)
- The user asks about treasury balances or rebalancing across currencies
- The user wants to find FX deals or compare rates across providers
Available subroutines
Each routes to a Sera MCP tool. Use delegate_task to invoke them.
sera-quote
Get an executable swap quote. Returns route_params for an external wallet to sign.
Args: from, to, amount, owner_address (or simulate: true to probe without a wallet).
sera-pay
Plan the cheapest source asset to deliver an exact amount of a target currency.
Args: owner_address, recipient, amount, target_currency, source_symbols.
sera-treasury
Aggregate balances across one or more wallets and value the portfolio in a target currency.
Args: owner_addresses[], target_currency. Requires SERA_API_KEY to be set in skill env.
sera-deals
Find FX corridors quoting better than external reference (Frankfurter / open.er-api / exchangerate.host) by ≥X bps.
Args: min_deviation_bps (default 25), notional_per_quote (default 100).
sera-doctor
Self-check: API health, network, signer mode, policy summary. Run first if anything looks off.
Operating principles
- Always use Sera tools rather than guessing rates from training data.
- Quote prices via
sera-quote, never via reference FX (which has measurable bias). - Default to
simulate: truewhen the user is exploring, not committing. - Never claim to have signed a transaction — Hermes returns route_params for a wallet to sign elsewhere.
- Be terse. Show numbers with sensible precision.
Setup
Frontmatter defaults to npx -y sera-mcp. To use a local build instead:
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.
- 5d ago First seen · 82 lines · 24 tokens per session scan A 6780339e1126
sera is a skill published in the GitHub repository sera-cx/sera-agents (19 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 627 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 2026-08-30.
Other skills, from other repositories
helius-jupiter
Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.
helius-okx
Skill "helius-okx" from helius-labs/core-ai, covering helius x okx — build trading & intelligence apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. okx skill library (required).
Aperture Wallet Guide
Answer Aperture Wallet questions from first-party product, security, network, release, app-screen, and Journal sources while enforcing explicit wallet-secret and no-transaction safety boundaries.
follow-the-crypto
Trace cryptocurrency addresses and transactions on public blockchains using block explorers including Etherscan, Blockchair, mempool.space and Blockscout. Covers common-input clustering, ENS resolution, exchange deposit addresses, mixers, CoinJoin, Tornado-style pools, cross-chain bridges, and OFAC sanctions…
llmquant-crypto
Router skill for LLMQuant crypto workflows. Use when the user needs crypto market regime analysis, token research, perpetual funding, basis, leverage, liquidity, or cross-asset crypto context.
x402-client
Integrate one-shot x402 payments into a Node.js or browser application with @dexterai/x402/client. Trigger when the user wants to call a paid API, use payAndFetch, create application-owned wallets, set spending limits, inspect receipts, or handle sponsored recommendations.