agentleFS
Vo1ganinVo1ganin/crypto-claude-skills/skills/dexscreener/SKILL.md

dexscreener

Skill2 starsChanged 3 months agoMITView on GitHub

Expert assistant for DexScreener API — free, unauthenticated public API for current DEX pair data across 20+ chains (Solana, Ethereum, Base, BSC, TON, etc.).

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No history: Only current state. For historical: use Dune or Bitquery.

    line 32
  2. Distinctive:

    Search max 30 results, no pagination: Don't try to scroll past 30.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

DexScreener Skill

Reference files:

  • references/endpoints.md — full endpoint list with rate limits per group
  • references/examples/ — working Python scripts (batch token lookup, search, monitor)

🚨 Key facts (memorize)

  1. No auth, no key, no paid tier. Public API, free for everyone.
  2. No history. Only current state. For historical: use Dune or Bitquery.
  3. No WebSocket. Polling only. For real-time pump.fun: PumpPortal; for others: direct RPC.
  4. Search max 30 results, no pagination. Don't try to scroll past 30.
  5. Two rate tiers: 60 rpm (profiles/boosts/metas/orders) vs 300 rpm (latest/dex/*).
  6. Terms prohibit competing products and aggressive scraping. Fair analytical use is fine.

Base URL

https://api.dexscreener.com

When to use vs alternatives

NeedBest tool
Quick current price, any token, any chainDexScreener /tokens/v1/{chain}/{addr}
Discover trending memecoinsDexScreener /token-boosts/top/v1 + /token-profiles/latest/v1
Batch price for 30 tokensDexScreener /tokens/v1/{chain}/{addrs} (one call)
Full liquidity/volume for a pairDexScreener /latest/dex/pairs/{chain}/{pair}
Historical pricedune-skill (prices.usd) or Birdeye
Real-time trade streampumpfun-skill (PumpPortal WS) or solana-rpc-skill (LaserStream)
Deep wallet analysissolscan-skill or nansen-skill
NFT datasolana-rpc-skill (DAS API)

Step-by-step workflow

1. Identify input

  • User pastes token address → /tokens/v1/{chain}/{address} or /latest/dex/search?q={address}
  • User mentions name/symbol → /latest/dex/search?q={query} (max 30 results)
  • User asks for trending → /token-boosts/top/v1 or /metas/trending/v1
  • User has pair/pool address → /latest/dex/pairs/{chain}/{pair}

2. Detect chain Chain IDs: solana, ethereum, base, bsc, polygon, arbitrum, optimism, avalanche, ton, sui, tron, hyperliquid, etc. If unknown, use /search first (it returns chainId in results).

3. Call the endpoint

  • Plain curl or httpx.get() — no headers needed
  • Honor 60/300 rpm rate limit: if batch-polling, asyncio.Semaphore(5) keeps safe

4. Extract what's needed Typical fields: priceUsd, volume.h24, liquidity.usd, priceChange.h24, txns.h24.buys/sells, marketCap, fdv, pairCreatedAt.

5. Present

  • Format USD with commas
  • Shorten addresses (4+4 chars)
  • Link to DexScreener UI: https://dexscreener.com/{chainId}/{pairAddress}

Common patterns

Quick price lookup

curl "https://api.dexscreener.com/latest/dex/search?q=BONK"

Returns up to 30 matching pairs sorted by relevance. Pick the top Raydium/Jupiter pair on Solana for BONK.

Batch 30 tokens at once

curl "https://api.dexscreener.com/tokens/v1/solana/MINT1,MINT2,MINT3,...,MINT30"

Single request covers 30 tokens — way cheaper than 30 individual calls.

Monitor a token's all pairs

curl "https://api.dexscreener.com/token-pairs/v1/solana/{TOKEN}"

Useful when a token trades on multiple DEXes (Raydium, Meteora, Orca) — get liquidity for each.

Trending + boosts combination

# What paid advertisers are pushing
curl https://api.dexscreener.com/token-boosts/top/v1

# Organic trends
curl https://api.dexscreener.com/metas/trending/v1

Compare these — divergence signals pump-or-rug patterns.


Error handling

StatusMeaningAction
200OKParse JSON
429Rate limitedBack off 30-60s, drop concurrency
404Token/pair not foundVerify chainId and address
500-502Upstream errorRetry with backoff

429 doesn't include Retry-After — just exponentially back off.

Reference files

  • references/endpoints.md — all endpoints, rate tiers, response shapes
  • references/examples/search_token.py — quick symbol/name lookup
  • references/examples/batch_prices.py — bulk price fetch for N tokens
  • references/examples/trending_monitor.py — periodic trending dump

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.