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 coinmarketcapgit 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/coinmarketcap)<a href="https://agentmods.dev/skills/vo1ganin/crypto-claude-skills/coinmarketcap"><img src="https://agentmods.dev/badge/skills/vo1ganin/crypto-claude-skills/coinmarketcap/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/coinmarketcap"><img src="https://agentmods.dev/badge/skills/vo1ganin/crypto-claude-skills/coinmarketcap.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 | $0.00183 | $0.02309 |
| Opus 5 | $0.00092 | $0.01154 |
| Sonnet 5 | $0.00037 | $0.00462 |
| Haiku 4.5 | $0.00018 | $0.00231 |
Grade A, and why
coinmarketcap scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "X-CMC_PRO_API_KEY: $CMC_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoinMarketCap Skill
Reference files:
references/endpoints.md— full catalog by category with credit formulasreferences/credits.md— budget rules, cost estimation, plan tiersreferences/patterns.md— batching, caching, CMC vs alternativesreferences/examples/*.py— working Python scripts
🚨 Rule #1: credits, not requests
CoinMarketCap meters by credits, not by request count. The formula is:
credits_per_call = max(1, ceil(data_points_returned / 100))
Where data_points ≈ rows × columns × (1 + extra_convert_currencies).
Cheap calls (1 credit):
- Up to 100 cryptos on
quotes/latest - Up to 200 cryptos on
listings/latest - Any single-token lookup (map, info, pools)
global-metrics,key/info,fiat/map
Expensive calls:
listings/latest?limit=5000= 25 credits (verified)ohlcv/historicalwith many points × many cryptos = points / 100market-pairs/latestwith 500+ pairs- Adding
convert=USD,EUR,GBP→ +1 credit per extra currency
Always check status.credit_count in response and log it.
🚨 Rule #2: budget thresholds (applied per call)
| Estimated credits | Action |
|---|---|
< 50 |
Proceed silently |
50–200 |
Announce cost + reason before calling |
> 200 |
STOP. Propose alternative (narrower limit, targeted id list, cached data, different endpoint). Execute only with approval. |
For batch jobs (N calls): threshold applied to total. 100 × 2 credits = 200 → announce. 100 × 5 = 500 → stop.
Check budget via GET /v1/key/info (free, 0 credits) before big sessions.
🚨 Rule #3: use CMC IDs, not symbols
Symbols collide (BTC might point to any of several tokens), can change, and break over time. CMC IDs are stable numeric identifiers.
Always:
- Resolve symbols/names once via
/v1/cryptocurrency/map - Cache the ID → (symbol, name) mapping on your side
- Use IDs for all subsequent
/quotes/*,/ohlcv/*,/infocalls
What ships with it
7 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.
- 12d ago First seen · 215 lines · 183 tokens per session scan A a4d970658da1
coinmarketcap is a skill published in the GitHub repository Vo1ganin/crypto-claude-skills (2 stars, last pushed 22d ago), licensed MIT. It adds 183 tokens to every session and 2,309 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (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
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…
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.
tokenomist-burn-buyback
Check token burn and buyback activity. Use when analyzing deflationary mechanisms — burns, buybacks, and net inflation.
tokenomist-emission-report
Get daily or weekly token emission data with allocation breakdowns. Use when analyzing token inflation, comparing emission rates, or understanding supply increases.
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-token-overview
Get a summary list of all tracked tokens with market data and supply info. Use when browsing tokens, comparing market caps, or finding which tokens have fundraising/burn/buyback data.