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 agentmods add skills/validatorsdao/slv/slv-jetstreamernpx skills add ValidatorsDAO/slv --skill slv-jetstreamergit clone --depth 1 https://github.com/ValidatorsDAO/slvWrote 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/validatorsdao/slv/slv-jetstreamer)<a href="https://agentmods.dev/skills/validatorsdao/slv/slv-jetstreamer"><img src="https://agentmods.dev/badge/skills/validatorsdao/slv/slv-jetstreamer.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.02143 |
| Opus 5 | $0.00039 | $0.01071 |
| Sonnet 5 | $0.00016 | $0.00429 |
| Haiku 4.5 | $0.00008 | $0.00214 |
Grade B, and why
slv-jetstreamer scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `/mnt` defaulting to mode 0700 (some Solana host images) blocks the `clickhouse` system user from traversing — `chmod 0755 /mnt`. How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SLV Jetstreamer Skill
jetstreamer is anza-xyz's high-throughput Solana ETL engine: it streams the Old
Faithful CAR archive directly into a local ClickHouse instance and produces
query-ready aggregations (program invocation counts, slot statuses, pubkey
mentions, …). Together with the slv-rpc of1 rolling cache, it gives a
clean separation:
| Layer | Component | Role |
|---|---|---|
| JSON-RPC (per-call) | yellowstone-faithful (Index RPC) + 30-epoch index cache |
getTransaction / getBlock / getBlockTime etc. |
| SQL analytics (bulk) | jetstreamer + ClickHouse |
Cross-epoch aggregations, program-level joins, MEV / DEX research |
Jetstreamer is not a server. It runs as a one-shot ETL per epoch and exits; ClickHouse is the long-running query surface.
Hardware target
| Resource | Recommended |
|---|---|
| CPU | AMD EPYC 64C+ (jetstreamer hits 2.7 M TPS+ ingest with all cores) |
| RAM | 128 GB+ (754 GB optimal for full-fat ClickHouse buffers) |
| Disk | 4-8 TB NVMe (RAID0 recommended for max write bandwidth — derived data is rebuildable from Old Faithful) |
| Network | 10 Gbps+ (50 Gbps demonstrated to fully saturate ingest path) |
| OS | Ubuntu 24.04, kernel 6.14+ |
| Toolchain | Clang 16 (RocksDB compatibility — Clang 17/18 do not work), GCC 13, Rust (rustup, toolchain pinned by rust-toolchain.toml in jetstreamer repo) |
Disk layout
The reference layout combines two NVMes into one mdadm RAID0 stripe:
/dev/nvme0n1 ─┐
├─ mdadm RAID0 (chunk=1M) ─► /dev/md0 ─► XFS @ /mnt/jetstreamer
/dev/nvme1n1 ─┘ (noatime,inode64,
logbufs=8,logbsize=256k)
Mount options chosen for sequential write bandwidth + many-small-files (CH parts):
noatime,nodiratime,inode64,logbufs=8,logbsize=256k. Format with
mkfs.xfs -d agcount=64 -l size=1g for parallel allocation groups + a 1 GiB
internal log (XFS log max).
Production benchmark on this layout: 8.1 GB/s sequential write, 13.0 GB/s sequential read (direct I/O).
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.
- 4d ago First seen · 161 lines · 78 tokens per session scan B ade4b3090984
slv-jetstreamer is a skill published in the GitHub repository ValidatorsDAO/slv (89 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,143 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
zhin-plugin-standard-development
Implement Zhin.js plugins with Plugin Runtime. Use when asked to create a plugin, add commands, middleware, components, cron, AI tools/skills/agents, config, database, router, or console pages. 适用于 definePlugin / 约定目录能力落地。.
stellar-forge
Eval-driven coding harness for building production Stellar dApps. Routes tasks to 6 specialist agents, verifies output with structured evals, steers on failure, e2e-tests with Stellar Agentic Kit hooks, and knowledge-graphs every project. Use when building any Stellar app — tokens, DeFi, NFTs, payment APIs, or full…
stellar-mcp
MCP (Model Context Protocol) tools for Stellar development. Gives Claude direct access to the Stellar blockchain, filesystem, GitHub, and Playwright through configured MCP servers. Use when querying chain data, deploying contracts, managing repos, or running e2e tests from within the agent.
alchemy-agentic-gateway
Use when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features. Also use when the user mentions "SIWE", "SIWS", "x402", "MPP", "mppx", or "agentic gateway" — this skill covers wallet-based auth flows for Alchemy's x402 and MPP…
alchemy-api
Integrates Alchemy blockchain APIs using an API key. Requires $ALCHEMYAPIKEY to be set; if unavailable, use the alchemy-agentic-gateway skill instead. Use when user asks about EVM JSON-RPC calls, token balances, NFT ownership or metadata, transfer history, token prices, portfolio data, transaction simulation…
transform
Use this to author and change a dbt project: bootstrap a project in a repo that has none (transform init), write or refactor model SQL from staging to marts, add tests and docs in schema.yml, manage dependencies, and define or update the semantic layer (dbt semantic models / MetricFlow: entities, dimensions, measures…