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 x402agent/solana-clawd --skill magicblockgit clone --depth 1 https://github.com/x402agent/solana-clawdWrote 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/x402agent/solana-clawd/magicblock)<a href="https://agentmods.dev/skills/x402agent/solana-clawd/magicblock"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/magicblock/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/x402agent/solana-clawd/magicblock"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/magicblock.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 | $0.00124 | $0.01653 |
| Opus 5 | $0.00062 | $0.00826 |
| Sonnet 5 | $0.00025 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00165 |
Grade A, and why
magicblock 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 9d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MagicBlock Ephemeral Rollups Skill
What this Skill is for
Use this Skill when the user asks for:
- MagicBlock Ephemeral Rollups integration
- Delegating/undelegating Solana accounts to ephemeral rollups
- High-performance, low-latency transaction flows
- Crank scheduling (recurring automated transactions)
- VRF (Verifiable Random Function) for provable randomness
- Magic Actions — base-layer instructions chained to an ER commit
- Topping up a delegated account's lamports via
lamportsDelegatedTransferIx - Dual-connection architecture (base layer + ephemeral rollup)
- Gaming and real-time app development on Solana
- Private payments (deposits, transfers, withdrawals, and swaps via the Payments API, with optional bearer-token auth for private reads)
- Lifting the default 10-commit sponsorship cap with
magic_fee_vault
Key Concepts
Ephemeral Rollups enable high-performance, low-latency transactions by temporarily delegating Solana account ownership to an ephemeral rollup. Ideal for gaming, real-time apps, and fast transaction throughput.
Delegation transfers account ownership from your program to the delegation program, allowing the ephemeral rollup to process transactions at ~10-50ms latency vs ~400ms on base layer.
MagicIntentBundleBuilder (SDK 0.11+) is the current way to schedule commit and commit-and-undelegate intents. The free functions commit_accounts and commit_and_undelegate_accounts are deprecated.
Private Ephemeral Rollups (PER) add a permission account that gates who can interact with a delegated account inside a TEE-backed validator. The recommended pattern is to delegate the permission account itself alongside the permissioned account, so member updates execute on the ER in milliseconds instead of base-layer round-trips.
Magic Actions are base-layer instructions scheduled inside an ER transaction via MagicIntentBundleBuilder.add_post_commit_actions(...). They execute atomically once the commit is sealed back to base layer — useful for leaderboard updates, reward distribution, and any side-effect that must run as part of the commit.
What ships with it
9 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.
- 9d ago First seen · 119 lines · 124 tokens per session scan A 793e4f178db7
magicblock is a skill published in the GitHub repository x402agent/solana-clawd (24 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 1,653 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
yoink
Play Yoink capture-the-flag game on Base - yoink the flag, check scores, compete for trophy.
enum-struct
Create, modify, and introspect UserDefinedEnums and UserDefinedStructs (EnumStructService). Use when the user asks to create a Blueprint enum or struct, add enum values or struct members, or inspect an enum/struct's fields. Useful for defining a DataTable row struct.
authoring-godot-prompter-skills
Use when writing or editing a SKILL.md or an agent definition in this repo — required frontmatter, section ordering, and the GDScript-then-C# example convention.
erc1155-patterns
Use when building multi-token contracts with ERC-1155. Covers batch operations, URI handling, supply tracking, hybrid fungible and non-fungible patterns, and game item architectures.
metaverse-expert
Create production-ready metaverse experiences including VR/AR applications, virtual worlds, social platforms, and blockchain-integrated digital assets. Use when the user mentions VR/AR/XR, virtual worlds, spatial computing, 3D avatars and scenes, Unity or Unreal for immersive apps, or NFT-backed digital assets.
cattown
Interact with Cat Town — a Farcaster-native game world on Base. Covers KIBBLE staking (stake, claim, unlock, unstake, leaderboard, deposit history); live world state (season, weather, time of day, weekend flag); fishing drops filtered by world state; Isabella's weekend fishing competition with live prize-pool math…