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-agentkitnpx skills add stakekit/agentkit --skill yield-xyz-agentkitgit 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 | $0.00046 | $0.06087 |
| Opus 5 | $0.00023 | $0.03044 |
| Sonnet 5 | $0.00009 | $0.01217 |
| Haiku 4.5 | $0.00005 | $0.00609 |
Grade A, and why
yield-xyz-agentkit 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.
**Always call tools via the connected MCP server (`https://mcp.yield.xyz/mcp`). Never fall back to curl, bash, or raw HTTP requests.** How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yield.xyz AgentKit
A skill for discovering and acting on DeFi yield opportunities via the Yield.xyz MCP server.
Integration Boundary
This skill is the yield layer — it discovers yields, inspects their schemas, and builds unsigned transactions. It never holds keys, signs, or broadcasts, and it's tied to no wallet or custody product. Drop it into any agent or app that can already sign, and it becomes that agent's expertise for earning yield.
Responsibility splits cleanly on every transaction:
- This skill builds the
unsignedTransaction(actions_enter/actions_exit/actions_manage). - Your side signs and broadcasts it. Whatever does that is your signer — a user's wallet, your agent's own custody (MPC / KMS / HSM), or a provider like Privy or MoonPay. This skill doesn't care which.
- This skill records the result —
submit_hashwith the returned hash, thenget_transactionuntilCONFIRMED.
This holds whether signing is human-approved or fully autonomous. Where a human is in the loop, confirm before signing; where the host signs on its own, skip the confirmation and let it run.
How to Call Tools — Read This First
Always call tools via the connected MCP server (https://mcp.yield.xyz/mcp). Never fall back to curl, bash, or raw HTTP requests.
The MCP server exposes these tools directly — call them like any other tool:
- yields_get_all — list/filter yields
- yields_get — get one yield by ID
- yields_get_validators — list validators for a yield
- yields_get_balances — check wallet balances
- yields_get_reward_rate_history — historical APY/reward rate data for a yield
- yields_get_tvl_history — historical TVL data for a yield
- yields_get_risk — detailed risk parameters for a yield
- yields_get_kyc_status — check a wallet's KYC/eligibility status for a permissioned (RWA) yield
- actions_enter — enter a position
- actions_exit — exit a position
- actions_manage — claim rewards / manage position
- actions_get — get status of a specific action
- actions_get_all — list action history for a wallet
- submit_hash — submit on-chain tx hash after signing and broadcasting (mandatory)
- get_transaction — poll transaction confirmation status
- networks_get_all — list all supported networks
- providers_get_all — list all supported protocols and providers
What ships with it
8 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.
- 2d ago First seen · 455 lines · 46 tokens per session scan A 9d9bd4d9ca90
yield-xyz-agentkit is a skill published in the GitHub repository stakekit/agentkit (3 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 6,087 once invoked, about $0.0002 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
quick-recap
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.