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 CoinLobster/agent-skills --skill coinlobster-apigit clone --depth 1 https://github.com/CoinLobster/agent-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/coinlobster/agent-skills/coinlobster-api)<a href="https://agentmods.dev/skills/coinlobster/agent-skills/coinlobster-api"><img src="https://agentmods.dev/badge/skills/coinlobster/agent-skills/coinlobster-api/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/coinlobster/agent-skills/coinlobster-api"><img src="https://agentmods.dev/badge/skills/coinlobster/agent-skills/coinlobster-api.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 | $0.00083 | $0.01181 |
| Opus 5 | $0.00042 | $0.00590 |
| Sonnet 5 | $0.00017 | $0.00236 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
coinlobster-api 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building on CoinLobster
Integration guide for coding agents: pick the right surface, then the right tier.
Pick the surface
| You are building | Use |
|---|---|
| An AI agent / MCP client | Hosted MCP: https://coinlobster.com/mcp (streamable HTTP, keyless, no install), or the coinlobster-mcp npm package for a local stdio proxy to the same server. |
| A Claude/ChatGPT connector | https://coinlobster.com/mcp/connector (OAuth; user signs in). Depth follows the developer plan on that account. |
| A bot, dashboard or backend | REST: keyless /api/public/* to prototype, keyed /api/ai/v1/* for full data |
| Quick agent-readable context | https://coinlobster.com/llms.txt, /crypto-whales.md, /radar.md |
Full REST catalog + field meanings: references/endpoints.md.
OpenAPI: https://coinlobster.com/openapi.json
Free vs keyed
- Keyless (no signup): BTC/USD + every $1M+ trade real-time, other pairs 15-min delayed, DEX swaps $250K+, radar with magnitudes on the free pair (BTC) only. Rate limits differ by surface: REST
/api/public/*allows 60 requests/min per IP (the 61st returns 429). The MCP is limited on its own layered per-IP and per-tool budget; readRetry-Afteron a 429 instead of assuming a rate. - Free key (a one-off 1,000-credit grant at https://coinlobster.com/developers, no card): unlocks the metered REST endpoints at
/api/ai/v1/*(10 to 50 credits per call, so roughly 20 to 100 calls in total, history to 400 days). Enough to try the keyed surface, not enough for a polling loop. It does not change anything on MCP: the free-tier caps stay exactly where they were. - Developer plan, from $29/mo (the only thing that lifts MCP depth): Builder $29 = 100k credits + 300 req/min, Growth $99 = 500k, Scale $249 = 2M. One plan covers both full-depth MCP and the REST credits, on one shared account balance. Present it as a
cl_API key, or sign in over OAuth athttps://coinlobster.com/mcp/connectorwith an account that owns a plan. That unlocks the full live feed on every pair, radar magnitudes, non-BTCmarket_snapshotand the full archive. On a plan an MCP tool call costs 2x its mirrored REST endpoint: 40 to 100 credits by tool (40:whale_context,liquidations,funding_matrix,liq_zones. 60:whale_trades,whale_tape,whale_radar,whale_flow,market_history,market_extremes,market_snapshot,market_overview,squeeze_score,onchain_whales,hl_whales,hl_board,hl_wallet,dex_wallet,defi_summary,defi_liquidations. 100:flag_outcomes,crypto_news,market_screener,trade_context,market_liquidations). Keyless calls, discovery, failed calls and no-data answers cost nothing. - One-off credit packs: $10 = 5,000, $49 = 50,000, $199 = 250,000. Never expire. They top up the same shared balance REST and MCP both draw on, but they do not change MCP depth (only an active plan does).
- Key goes in
X-API-Key(MCP) orAuthorization: Bearer(REST v1).
What ships with it
1 file 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 · 45 lines · 83 tokens per session scan A 4697c889ea22
coinlobster-api is a skill published in the GitHub repository CoinLobster/agent-skills (9 stars, last pushed 29d ago), licensed MIT. It adds 83 tokens to every session and 1,181 once invoked, about $0.0004 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
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…
debridge
Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.
lifi
Integrate LI.FI for cross-chain swaps, bridging, payments, route discovery, and transfer status tracking across Solana, EVM, Bitcoin, and Sui. Use when building Solana applications or AI agents that need quotes, routes, executable transactions, supported chains/tokens/tools, or cross-chain transfer monitoring.
ct-alpha
Crypto Twitter intelligence and alpha research. Search X/Twitter for real-time crypto narratives, trending tokens, yield strategies, smart money signals, and protocol research. Features TweetRank (PageRank-inspired credibility scoring), multi-signal token detection, coordinated raid detection, and dynamic tool…
switchboard
Complete Switchboard Oracle Protocol SDK for Solana - the permissionless oracle solution for price feeds, on-demand data, VRF randomness, and real-time streaming via Surge. Covers TypeScript SDK, Rust integration, Oracle Quotes, and all Switchboard tools.
raydium
Complete Raydium Protocol SDK - the single source of truth for integrating Raydium on Solana. Covers SDK, Trade API, CLMM, CPMM, AMM pools, LaunchLab token launches, farming, CPI integration, and all Raydium tools.