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 Parad0x-Labs/openclaw-skills --skill magicblock-archivegit clone --depth 1 https://github.com/Parad0x-Labs/openclaw-skillsWrote 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/parad0x-labs/openclaw-skills/magicblock-archive)<a href="https://agentmods.dev/skills/parad0x-labs/openclaw-skills/magicblock-archive"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/magicblock-archive/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/parad0x-labs/openclaw-skills/magicblock-archive"><img src="https://agentmods.dev/badge/skills/parad0x-labs/openclaw-skills/magicblock-archive.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 | $0.00073 | $0.00448 |
| Opus 5.5 | $0.00029 | $0.00179 |
| Sonnet 5.5 | $0.00015 | $0.00090 |
| Haiku 4.5 | $0.00007 | $0.00045 |
Grade A, and why
magicblock-archive 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 23d 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.
What it actually says
MagicBlock Archive
Compresses MagicBlock Ephemeral Rollup (ER) session logs into Liquefy vaults and
computes a per-session 32-byte commitment (session_commitment) for the receipt_anchor
accumulator. Fills the MagicBlock auditability gap by keeping a verifiable,
tamper-evident record of every ER session.
This skill does not anchor: archive_session(anchor=True) raises
ReceiptAnchorUnavailableError before the session is fetched or anything is written.
Archive with anchor=False; the result carries the session_commitment hex. A devnet
receipt_anchor is available at HSdEQWunzPtNqdzv5HfXuA3zwPLpgTXRyfbndnGamhXs (2026-10-06, fresh
key); pass it explicitly to a client that anchors. The mainnet
receipt_anchor (6HSRGivdYR5D7yTDy1TFMCM8h3LzXxRtKU1RA3RnCMRN) was retired 2026-07-14;
its historical anchors remain readable.
x402 session playback pricing is included — charge per replay access.
When to use
- Running MagicBlock Ephemeral Rollup sessions and need an audit trail
- Want a reproducible 32-byte commitment of an ER session outcome without storing full logs
- Need x402-gated access to ER session history playback
Tests
python3 -m unittest discover -s tests -v # hermetic, stdlib only
Source
github.com/Parad0x-Labs/openclaw-skills/tree/main/plugins/magicblock-archive
What ships with it
2 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.
- 23d ago Changed · +14 lines · +10 tokens per session f38355b37a84
- 2mo ago First seen · 27 lines · 63 tokens per session scan A 3d3b3867ce9f
magicblock-archive is a skill published in the GitHub repository Parad0x-Labs/openclaw-skills (23 stars, last pushed 17d ago), licensed MIT. It adds 73 tokens to every session and 448 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 2026-08-30.
Other skills, from other repositories
crypto-trading
Use ccxt (Python) for crypto prices, balances, and order actions across 100+ exchanges.
agent-freelance-bounty-marketplace
Earn USDC completing bounties, post jobs, join multi-agent raids, build reputation, rank up. AI agent freelance marketplace with x402 escrow on Solana. Free SOL airdrop on signup. Guilds, ranks, vouching, disputes, Castle Town, leaderboard.
agent-commerce-identity-payments-arbitration
ERC-8004 identity, x402 payments, and arbitration protocol for autonomous agent commerce. The three rails for the machine economy.
agent-arbitrage-tool
6 open tasks paying 1-3 ROSE ($3-9 each). Zero claimed. Workers keep 95%.
agent-micropayments-via-x402-protocol
Enable AI agents to make micropayments via x402 protocol. Use when purchasing browser sessions on Browserbase, scraping with Firecrawl, or any x402-compatible API. Handles wallet creation, funding, and automatic payment flows.
agent-evm-wallet-signing
Use this skill to safely create a wallet the agent can use for transfers, swaps, and any EVM chain transaction. Also supports raw signing.