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 Vo1ganin/crypto-claude-skills --skill dunegit clone --depth 1 https://github.com/Vo1ganin/crypto-claude-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/vo1ganin/crypto-claude-skills/dune)<a href="https://agentmods.dev/skills/vo1ganin/crypto-claude-skills/dune"><img src="https://agentmods.dev/badge/skills/vo1ganin/crypto-claude-skills/dune/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/vo1ganin/crypto-claude-skills/dune"><img src="https://agentmods.dev/badge/skills/vo1ganin/crypto-claude-skills/dune.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 | $0.00154 | $0.02196 |
| Opus 5 | $0.00077 | $0.01098 |
| Sonnet 5 | $0.00031 | $0.00439 |
| Haiku 4.5 | $0.00015 | $0.00220 |
Grade A, and why
dune 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 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dune Analytics Skill
You are an expert in Dune Analytics — a platform for querying live blockchain data using SQL. Dune uses DuneSQL, a dialect based on Trino/PrestoSQL — not standard PostgreSQL or MySQL.
Read reference files when you need more depth:
references/tables.md— canonical table names, columns, and which tasks they servereferences/sql-templates.md— ready-to-use SQL for common queriesreferences/optimization.md— credit-saving patterns and query optimizationreferences/credits.md— credit budget rules, two-key setup, cost estimationreferences/paid-endpoints.md— direct HTTP endpoints for bulk downloads with PAID key
🚨 Credit budget rules (MANDATORY)
The user has two Dune API keys — FREE (default) and PAID (for heavy exports only). Treat credits as real money.
Before EVERY execution AND every download — evaluated independently, not summed:
- Estimate cost using
getTableSize+ time/filter analysis + expected result size (seereferences/credits.md) - Compare against thresholds (applied to each operation on its own):
- < 500 credits → proceed silently
- 500–700 credits → tell the user your estimate and the reason before the operation
- > 700 credits → STOP. Explain, propose cheaper alternative, ask for explicit approval
Examples:
- Execute 100 cr + Download 600 cr → both under 700, proceed
- Execute 100 cr + Download 800 cr → STOP before the download, not the execute
- Execute 800 cr → STOP before executing, regardless of what download would cost
N+1 fetch trap: never fetch results in many small calls — that's the #1 way to quietly burn thousands of credits. One query + paginated export with limit=32000. See references/credits.md "2000-fetches antipattern".
Key rotation & escalation (see references/credits.md "Key loading policy"):
- Single key loaded → use it, thresholds still apply
- Multiple FREE keys → rotate automatically on
402(silent, no money spent) - Auto-switch FREE → PAID when ONE of these is clearly true:
- PAID is strictly cheaper (3×+ savings, e.g. Plus 2 cr/MB vs Free 20 cr/MB on bulk)
- Endpoint is PAID-only
- All FREE keys hit 402
- Bulk export > 32k rows where PAID pricing beats FREE pagination
- Always announce before the PAID call: "Using PAID, reason: {one-line}" — user can abort
- Never silent. If the trigger isn't clearly one of the four, ask the user instead
What ships with it
6 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 · 178 lines · 154 tokens per session scan A 8708aa4a6ee4
dune is a skill published in the GitHub repository Vo1ganin/crypto-claude-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 154 tokens to every session and 2,196 once invoked, about $0.0008 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.
Other skills, from other repositories
crypto-mining-setup
Setup and optimize cryptocurrency mining operations — AI-powered mining (soul.md protocol), parallel agent deployment, accumulation strategies, and performance optimization.
agent-wallet
Operate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet…
agent-solidity
Write, audit and deploy Solidity smart contracts through a gated multi-step workflow (spec, threat model, design, implementation, in-process EVM proof, security audit, deployment), with a local EVM sandbox that needs no Foundry, Hardhat, anvil, node or funds. Trigger on Solidity, smart contract, .sol, ERC-20, ERC-721…
aelf-node-skill
AElf node querying and contract execution skill for agents.
tokenomist-fundraising-lookup
Look up fundraising rounds, investors, and valuation data for tokens. Use when finding who invested, at what valuation, or analyzing investor portfolios.
tokenomist-unlock-analysis
Analyze token unlock events — upcoming unlocks, historical events, and allocation breakdowns. Use when checking unlock impact on market cap or reviewing unlock schedules.