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 x402agent/solana-clawd --skill dex-screener-scannergit clone --depth 1 https://github.com/x402agent/solana-clawdWrote 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/x402agent/solana-clawd/dex-screener-scanner)<a href="https://agentmods.dev/skills/x402agent/solana-clawd/dex-screener-scanner"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/dex-screener-scanner/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/x402agent/solana-clawd/dex-screener-scanner"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/dex-screener-scanner.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 | $0.00090 | $0.02867 |
| Opus 5 | $0.00045 | $0.01434 |
| Sonnet 5 | $0.00018 | $0.00573 |
| Haiku 4.5 | $0.00009 | $0.00287 |
Grade A, and why
dex-screener-scanner 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DexScreener Solana Scanner
Autonomous agent skill for scanning and screening Solana tokens on DexScreener using browser automation (Playwright/Puppeteer). The goal is to navigate dexscreener.com/solana, extract token data from live listings, apply screening filters, and identify the best trading opportunities.
Overview
This skill uses browser automation to:
- Navigate to DexScreener's Solana board
- Scrape live token listings (new, trending, gainers, etc.)
- Extract key metrics for each token
- Apply configurable screening filters to find the best opportunities
- Return ranked results with rationale
Workflow
Step 1: Launch Browser & Navigate
Use a browser automation tool (Playwright or Puppeteer) to open https://dexscreener.com/solana.
# Example with Playwright
page = await browser.new_page()
await page.goto("https://dexscreener.com/solana", wait_until="domcontentloaded")
Important: DexScreener is a heavy React SPA. Wait for the token table rows to render before scraping. The table typically appears within 3-8 seconds.
Step 2: Wait for Token Table to Load
The token listing is a dynamic table. Watch for:
- CSS selector for table rows:
div[data-group="token-row"]or.ds-table-rowortr[data-id] - The table has multiple tabs: New, Trending, Gainers, Recently Copied, etc.
- Wait for at least one row to be visible before scraping
Recommended wait strategy:
# Wait for first token row to appear
await page.wait_for_selector('[data-group="token-row"]', timeout=15000)
# Or wait for the table body
await page.wait_for_selector('table tbody tr', timeout=15000)
If the wait times out, the page may be loading slowly — retry once with a longer timeout.
Step 3: Parse Token Listing Data
Each token row typically contains these fields (column order may vary slightly):
| Field | Description | Example |
|---|---|---|
| # | Rank/position | 1, 2, 3 |
| Name/Symbol | Token name + ticker | "dogwifhat / WIF" |
| Price | Current SOL or USD price | "$0.0042" |
| Price Change | 5m/1h/6h/24h change % | "+15.3%" |
| Volume | 24h trading volume | "$1.2M" |
| Liquidity | Pool liquidity | "$45K" |
| Market Cap | Fully diluted market cap | "$2.1M" |
| Age | How long since creation | "3m" (3 minutes), "1h" |
| Txns | Transaction count (buys/sells) | "1.2K / 800" |
| Holders | Unique holder count | "450" |
| FDV / Liq | FDV-to-Liquidity ratio | "12.5x" |
What ships with it
3 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 · 285 lines · 90 tokens per session scan A 6e3c82684d72
dex-screener-scanner is a skill published in the GitHub repository x402agent/solana-clawd (24 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 2,867 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
walkeros-create-source
Use when creating a new walkerOS source to capture events (browser source, dataLayer interception, server/HTTP source, webhook receiver, event capture), web or server-side. Example-driven workflow: research the input format and define step examples before implementing the push interface, createTrigger, and env pattern.
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.
bitcoin-infrastructure-caravan
Caravan: open-source web-based multisig coordinator (no install). Read-only by default; HW wallet support via HWI bridge. USE WHEN: setting up multisig without installing software, educational multisig flows.
vivado-constraints
Use this skill when the user needs help writing XDC/SDC timing or physical constraints for Vivado FPGA designs. This includes clock definitions (createclock, creategeneratedclock, virtual clocks), I/O delay constraints (setinputdelay, setoutputdelay, DDR timing), timing exceptions (setfalsepath, setmulticyclepath…
setup-solana-browser-app
Set up a vanilla browser (non-React) app with @metamask/connect-solana using wallet-standard features directly. Use when integrating MetaMask Solana without a framework or wallet adapter library.
wallet-operations
All on-chain interactions: connecting an injected wallet extension to a target dApp, signing payloads, managing token approvals, checking balances, and claiming testnet faucets.