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 widnyana/eyay-toolkits --skill sui-walrusgit clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/widnyana/eyay-toolkits/sui-walrus)<a href="https://agentmods.dev/skills/widnyana/eyay-toolkits/sui-walrus"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/sui-walrus/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/widnyana/eyay-toolkits/sui-walrus"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/sui-walrus.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 | $0.00097 | $0.05652 |
| Opus 5 | $0.00048 | $0.02826 |
| Sonnet 5 | $0.00019 | $0.01130 |
| Haiku 4.5 | $0.00010 | $0.00565 |
Grade B, and why
sui-walrus scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X PUT "$PUBLISHER/v1/blobs" -d "some string" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X PUT "$PUBLISHER/v1/blobs" -d "some string" How it starts
The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walrus Skill
Integrate Walrus — Mysten Labs' decentralized blob storage layer. Walrus stores immutable byte arrays ("blobs"); Sui handles coordination, payments, metadata, and object ownership. Storage is provided by erasure-coded slivers across ~1000 shards with Byzantine fault tolerance up to 1/3 malicious nodes. Follow these rules precisely.
Critical: All blobs on Walrus are public and discoverable by anyone. Deletion does not remove cached copies. If the data is sensitive, encrypt before uploading (see the
sui-sealskill for the canonical pattern).
1. Mental model (read first)
A successful Walrus upload is three Sui transactions plus distributed storage work:
- Register the blob on Sui (reserve storage, mint a
Blobobject). - Upload slivers (erasure-coded fragments) to ~2/3 of storage nodes — roughly 2200 HTTP requests direct.
- Certify availability on Sui once enough nodes have acknowledged — this is the "Point of Availability" (PoA).
Reading a blob is ~335 requests to reconstruct from slivers. These numbers are why most apps do not call storage nodes directly — they use one of:
- Publishers / Aggregators (public or self-hosted HTTP gateways) — simplest; a single HTTP PUT/GET.
- Upload relay — the SDK writes via one request to a relay that fans out to nodes. Recommended for browsers and mobile.
- Direct SDK (
@mysten/walrus) — full control; carries the request overhead. Best for backends with custom retry logic.
Blob identity and lifecycle:
- Blobs are identified by a
BlobId(content hash of the encoding). Identical content → identicalBlobId→ no duplicate storage cost. - Storage is per epoch. Testnet epoch = 1 day; Mainnet epoch = 2 weeks. Max 53 epochs per registration (~2 years on Mainnet).
- A
Blobobject on Sui carries theBlobIdplus ownership/deletability flags. Burn the object to reclaim a small SUI rebate; burning does not delete storage. - Max blob size: ~13.6 GiB. Max per-file inside a Quilt: ~4 GiB.
- Memory: uploads need ~2–3× blob size in RAM via SDK/relay; raw direct uploads need ~4.5×. Reads need ~1.5–2× (erasure-coding overhead).
What ships with it
4 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.
- 11d ago First seen · 506 lines · 97 tokens per session scan B 5c437b3f9702
sui-walrus is a skill published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 5,652 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web3-protocol-gtm
Go-to-market strategy for web3 builders - protocols, products, services, and solo founders. Use when planning growth for a crypto protocol, building developer community, crafting CT narrative, planning ecosystem partnerships, preparing grant applications, launching tokens, pricing crypto-native products, or growing as…
solana-development
Build, test, deploy, and audit Solana programs with Anchor or native Rust, plus ZK Compression (Light Protocol). Use for Solana contracts, token operations, compute optimization, deployment, program audits, or compressed tokens and PDAs.
x402
Build internet-native payments with x402 - HTTP 402 for on-chain micropayments, no accounts or API keys. Use for paid APIs, paywalled content, agent payment flows, or per-call MCP tools. TypeScript, Python, and Go SDKs across EVM and Solana.
privy-integration
Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React SDK (PrivyProvider, hooks, wagmi), Node.js SDK, smart wallets (ERC-4337), x402 and MPP machine payments, Tempo chain, and agentic wallets with policies. Use when setting up Privy auth, creating…
metengine-data-agent
Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.
erc-8004
Build with ERC-8004 Trustless Agents - on-chain agent identity, reputation, validation, and discovery on EVM chains. Use when registering agents on-chain, building agent reputation, or using the Agent0 SDK. Triggers on ERC-8004 and Agent0.