magicblock

A development guide for building applications on Solana with MagicBlock, a system for running some blockchain activity in temporary, faster environments before settling results on Solana.

In plain words
What is it for?
Use it for MagicBlock features such as Ephemeral Rollups, delegated accounts, private payments, randomness, scheduled actions, temporary authority, and security checks.
Why use it?
It explains how to handle fast-changing or temporary state without confusing it with durable balances, ownership, or settlement data on the main blockchain.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/magicblock-labs/magicblock-dev-skill/skill
Any agent
npx skills add magicblock-labs/magicblock-dev-skill --skill skill
Clone the repo
git clone --depth 1 https://github.com/magicblock-labs/magicblock-dev-skill

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00070 $0.03410
Opus 5 $0.00035 $0.01705
Sonnet 5 $0.00014 $0.00682
Haiku 4.5 $0.00007 $0.00341

Measured 2d ago against content hash 8d88f08303ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

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.

skill/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MagicBlock Development Skill

Pair with the solana-dev skill

Use this skill for MagicBlock-specific concerns: ER/PER, delegation, oracles, Session Keys, cranks, VRF, Magic Actions, eSPL, and private payments. For general Solana or Anchor work such as scaffolding, PDAs, account layouts, SPL tokens, clients, wallets, or LiteSVM/Mollusk testing, also load solana-dev.

Key Concepts

Ephemeral Rollups enable high-performance, low-latency transactions by locking a delegated account on the base layer while an ER clone continues to execute under the account's original program owner. They are useful for gaming, real-time apps, and fast transaction throughput.

Ephemeral Accounts are born, used, and closed only inside an ER. They are useful for temporary high-frequency state, but they never commit to Solana and therefore cannot be the only copy of durable ownership, balances, rewards, or settlement results.

Delegation temporarily assigns the base-layer account to the Delegation Program and clones it into the ER with its original program owner. Normal program ownership, signer, authority, and account constraints still apply on the ER; delegation status is a routing and lifecycle concern, not a new application authorization rule.

Delegation debugging invariant: a properly delegated account looks owned by the delegation program on base, owned by the original program on the ER endpoint returned by router getDelegationStatus, and cloned into the ER with delegated=true.

For the verified SDK v0.16.2 snapshot, use MagicIntentBundleBuilder to schedule commit and commit-and-undelegate intents. Do not use the deprecated free functions commit_accounts and commit_and_undelegate_accounts.

Private Ephemeral Rollups (PER) gate a delegated account inside a TEE-backed validator with an ER-local EphemeralPermission. Delegate only the data account on the base layer, then create, update, and close its permission on the ER with CreateEphemeralPermissionCpi, UpdateEphemeralPermissionCpi, and CloseEphemeralPermissionCpi. Do not create or delegate a separate base-layer permission account.

Read the full file on GitHub · 252 lines

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. 2d ago First seen · 252 lines · 70 tokens per session scan A 8d88f08303ef

Subscribe to this mod's changes

magicblock is a skill published in the GitHub repository magicblock-labs/magicblock-dev-skill (9 stars, last pushed 12d ago), licensed MIT. It adds 70 tokens to every session and 3,410 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens