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 magicblock-labs/magicblock-dev-skill --skill skillgit clone --depth 1 https://github.com/magicblock-labs/magicblock-dev-skillWrote 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/magicblock-labs/magicblock-dev-skill/skill)<a href="https://agentmods.dev/skills/magicblock-labs/magicblock-dev-skill/skill"><img src="https://agentmods.dev/badge/skills/magicblock-labs/magicblock-dev-skill/skill/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/magicblock-labs/magicblock-dev-skill/skill"><img src="https://agentmods.dev/badge/skills/magicblock-labs/magicblock-dev-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.03658 |
| Opus 5.5 | $0.00028 | $0.01463 |
| Sonnet 5.5 | $0.00014 | $0.00732 |
| Haiku 4.5 | $0.00007 | $0.00366 |
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 today.
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 — 264 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.
Post-delegation actions attach instructions to a base-layer delegation with
delegate_account_with_actions. The Delegation Program stores them in the delegation record; the
validator runs them on the ER after cloning. Base-layer delegation success does not prove that the
action ran. For public or encrypted payloads, signer handling, and recovery, read
delegation-actions.md. These are distinct from post-commit
Magic Actions, which run on the base layer.
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.
What ships with it
21 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.
- agents/openai.yaml 295 B
- references/architecture-planning.md 16 KB
- references/composition-patterns.md 4.8 KB
- references/cranks.md 7.4 KB
- references/debugging.md 6.9 KB
- references/delegation-actions.md 6.1 KB
- references/delegation.md 19 KB
- references/ephemeral-accounts.md 4.7 KB
- references/ephemeral-spl-token.md 35 KB
- references/fees-and-commit-economics.md 18 KB
- references/lamports-topup.md 7.1 KB
- references/local-development.md 4.7 KB
- references/magic-actions.md 20 KB
- references/pricing-oracle.md 6.0 KB
- references/private-payments.md 32 KB
- references/resources.md 10 KB
- references/security.md 13 KB
- references/session-keys.md 4.7 KB
- references/typescript-setup.md 5.4 KB
- references/vrf.md 8.5 KB
- VERSION 6 B
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.
- today Changed · +3 lines da3030fcae66
- 27d ago Changed · +9 lines 4cd631d41571
- 1mo ago First seen · 252 lines · 70 tokens per session scan A 8d88f08303ef
magicblock is a skill published in the GitHub repository magicblock-labs/magicblock-dev-skill (9 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 3,658 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…