sap-agentkit

sap-agentkit is a skill for Claude Code, Codex from OOBE-PROTOCOL/sap-mcp. It costs 0 tokens per session (510 once invoked), scanned A, original, MIT.

A guide for using Synapse AgentKit tools with Solana, a blockchain network, and its tokens, NFTs, markets, finance, staking, bridges, and games. It also describes safety checks for actions that can submit transactions.

In plain words
What is it for?
Use it for Solana wallet and token tasks, NFT and Metaplex workflows, DeFi and market operations, staking, bridging, gaming, and related blockchain actions.
Why use it?
It helps an agent choose the relevant tools and handle blockchain actions carefully, especially before signing transfers, swaps, mints, or other high-risk operations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for Solana wallet and token tasks, NFT and Metaplex workflows, DeFi and market operations, staking, bridging, gaming, and related blockchain actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oobe-protocol/sap-mcp/sap-agentkit
Install

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.

Any agent
npx skills add OOBE-PROTOCOL/sap-mcp --skill sap-agentkit
Clone the repo
git clone --depth 1 https://github.com/OOBE-PROTOCOL/sap-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sap-agentkit

README.md
[![agentmods](https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agentkit.svg)](https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-agentkit)
Your own site
<a href="https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-agentkit"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agentkit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 510 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00510
Opus 5 $0.00000 $0.00255
Sonnet 5 $0.00000 $0.00102
Haiku 4.5 $0.00000 $0.00051

Measured 7d ago against content hash 9b549953bf90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sap-agentkit 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 7d 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.

skills/sap-agentkit/SKILL.md · 49 lines

What it actually says

SAP AgentKit

Use this skill for Synapse AgentKit tools exposed through SAP MCP: Solana RPC, SPL token, DAS, NFT, Metaplex, DeFi, market, staking, bridge, Blinks, bounty, and gaming workflows.

This skill maps to upstream skill domains such as sap-defi, sap-nft, sap-metaplex, sap-gaming, and sap-social.

General Rules

  • Read sap_profile_current before acting.
  • Use read-only tools first.
  • Treat swap, bridge, staking, liquidity, mint, transfer, market, and order tools as write/high-risk operations.
  • For tools that produce or submit transactions, preview and policy-check before signing.
  • Never inspect keypair files or ask the user for secret key bytes.

Solana And Token

Use sol_get_balance, spl-token_*, pyth_*, coingecko_*, and das_* tools for wallet, token, price, and asset context.

NFT And Metaplex

Use 3land_* and metaplex-nft_* tools for collection, minting, royalty, authority, and verification flows.

DeFi And Markets

Use lulo_*, manifest_*, meteora_*, openbook_*, orca_*, raydium-pools_*, pump_*, bridging_*, staking_*, and jito_* tools for DeFi execution when the tool is available in the current runtime and the required signing route is explicit.

For perps, prefer SAP MCP analysis tools first: sap_perp_trade_plan, sap_perp_markets, sap_perp_position_info, sap_perp_liquidation_zones, sap_perp_signal_score, sap_perp_risk_check, and sap_chart_*. For execution, use the hosted Adrena unsigned builders (sap_adrena_build_*) only when sap_perp_builder_status reports the operation available, then finalize the returned transactionBase64 locally with sap_payments_finalize_transaction. SAP MCP never signs user-owned Adrena transactions on the hosted server.

Use blinks_*, gibwork_*, and send-arcade_* tools when the task is about actions, bounties, or games rather than direct SAP protocol operations.

Changes

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.

  1. 7d ago First seen · 49 lines · 0 tokens per session scan A 9b549953bf90

Subscribe to this mod's changes

sap-agentkit is a skill published in the GitHub repository OOBE-PROTOCOL/sap-mcp (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 510 tokens. 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.