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/stakekit/agentkit/yield-xyz-agentkit-buildernpx skills add stakekit/agentkit --skill yield-xyz-agentkit-buildergit clone --depth 1 https://github.com/stakekit/agentkitWhat 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 | $0.00075 | $0.04969 |
| Opus 5 | $0.00037 | $0.02485 |
| Sonnet 5 | $0.00015 | $0.00994 |
| Haiku 4.5 | $0.00007 | $0.00497 |
Grade A, and why
yield-xyz-agentkit-builder scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`https://api.yield.xyz` directly — via the `@yieldxyz/sdk` or REST/curl. **Nothing the How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yield.xyz AgentKit — Builder Skill
This skill helps developers build applications that integrate with the Yield.xyz API. It generates integration code, guides architecture decisions, and helps ensure correct API usage across all supported chains and protocols.
Scope: this skill builds Yield integrations — staking, lending, vaults, and RWA across 80+ networks.
What ships vs. what's build-time: the integration you ship always calls
https://api.yield.xyz directly — via the @yieldxyz/sdk or REST/curl. Nothing the
user ships calls the MCP. The MCP's doc tools are only a build-time reference for you
(the builder) — they let you ground field names against the live spec/docs while
generating code. The MCP is not a runtime dependency and not a hard prerequisite; if it's
unavailable, fetch https://api.yield.xyz/docs.json directly.
Quickstart — minimal end-to-end (Yield)
The shortest happy path from nothing to a confirmed position. Language-agnostic REST;
swap curl for fetch/requests/etc. Always confirm exact field names against the
live spec (yield_get_api_spec or https://api.yield.xyz/docs.json) before generating
code — the shapes below are a map, not a contract.
- Discover —
GET /v1/yields?network=<network>&token=<token>to find a yield id. - Read the schema —
GET /v1/yields/{id}and readmechanics.arguments.enter.fields[]to learn exactly which arguments the enter action requires (e.g.amount, sometimes a validator address). - Build the action —
POST /v1/actions/enterwith{ yieldId, address, arguments }(amounts are human-readable strings, not wei). Returns HTTP 201 with atransactions[]array. - Sign + broadcast each transaction — iterate
transactions[]instepIndexorder; for each, parse and sign itsunsignedTransactionwith the wallet for that chain, then broadcast. Never modifyunsignedTransaction(Critical Rule #5). - Report the hash —
PUT /v1/transactions/{id}/submit-hashwith the broadcast hash so Yield.xyz can track it. - Poll to confirm —
GET /v1/transactions/{id}until status isCONFIRMED(there are no webhooks — poll with backoff).
What ships with it
26 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.
- README.md 5.9 KB
- references/api-field-mapping.md 7.0 KB
- references/api-limits.md 4.9 KB
- references/chains/aptos.md 4.6 KB
- references/chains/cardano.md 3.8 KB
- references/chains/cosmos.md 5.8 KB
- references/chains/evm.md 9.1 KB
- references/chains/near.md 3.2 KB
- references/chains/solana.md 7.0 KB
- references/chains/stellar.md 5.1 KB
- references/chains/substrate.md 3.8 KB
- references/chains/sui.md 4.3 KB
- references/chains/tezos.md 1.7 KB
- references/chains/ton.md 3.7 KB
- references/chains/tron.md 3.1 KB
- references/common-pitfalls.md 16 KB
- references/dashboard-and-api-keys.md 2.6 KB
- references/integration-patterns.md 13 KB
- references/mcp-tools.md 9.8 KB
- references/output-formats.md 2.6 KB
- references/policies.md 5.4 KB
- references/scaffold.md 4.0 KB
- references/setup.md 11 KB
- references/signing-patterns.md 14 KB
- references/transaction-lifecycle.md 27 KB
- references/yield-types.md 9.6 KB
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.
- 2d ago First seen · 389 lines · 75 tokens per session scan A e1305a1a113a
yield-xyz-agentkit-builder is a skill published in the GitHub repository stakekit/agentkit (3 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 4,969 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hyperliquid-reader
Read Hyperliquid (app.hyperliquid.xyz) perp + spot market data via opencli (read-only, public info API). Use whenever the user wants Hyperliquid perpetual or spot markets, mark/oracle/mid prices, 24h change, funding rates (hourly or annualized APR), open interest, volume, the L2 order book, OHLCV candles, historical…
grayscale-crypto-sectors
Use when evaluating crypto through a Grayscale-style Crypto Sectors lens: sector taxonomy, FTSE/Grayscale index eligibility, fee/usage fundamentals, sector-share valuation, ETP/trust wrappers, and Zcash-style privacy-as-money theses.
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
arthur-hayes-liquidity
Use when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.
placeholder-token-networks
Use when evaluating crypto networks through a Placeholder-style lens: open networks, token investment frameworks, network participation, and long-duration crypto network ownership.
a16z-crypto
Use when evaluating crypto networks and companies through an a16z crypto lens: web3 adoption, infrastructure vs apps, open networks, and long-duration crypto ecosystem investing.