Nansen Web Searcher
- 600 installs
- 127 repo stars
- Updated August 4, 2026
- nansen-ai/nansen-cli
nansen-web-searcher is a Claude Code skill that runs parallel Serper-backed web searches via the nansen CLI for developers who need fresh organic results, knowledge graphs, and current pricing or news in agent context.
About
nansen-web-searcher is an agent skill in nansen-ai/nansen-cli that executes parallel web searches through the Serper API using the nansen web search command. It requires the nansen binary and a NANSEN_API_KEY environment variable, and supports single or multiple --query flags with optional --num-results limits such as 5. Developers reach for nansen-web-searcher when coding agents need up-to-date market prices, ecosystem news, or general web facts alongside on-chain Nansen data. Example invocations include nansen web search "bitcoin price" and parallel queries for ethereum ETF and bitcoin ETF headlines. The skill is scoped to Bash(nansen:*) tooling and Node-installed nansen-cli package distribution.
- Run multiple web queries in a single parallel call
- Returns structured results with organic listings, titles, links, snippets, dates and optional knowledge graphs
- Supports --num-results (1–20) and --pretty for readable JSON output
- Combines positional arguments with repeatable --query flags
- Requires NANSEN_API_KEY and pairs with nansen web fetch for full page content
Nansen Web Searcher by the numbers
- 600 all-time installs (skills.sh)
- +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,585 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/nansen-ai/nansen-cli --skill nansen-web-searcherAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 600 |
|---|---|
| repo stars | ★ 127 |
| Last updated | August 4, 2026 |
| Repository | nansen-ai/nansen-cli ↗ |
How do agents fetch fresh web search results?
Run parallel web searches that return fresh organic results, knowledge graphs, and current pricing or news when the agent's context is outdated.
Who is it for?
Developers building crypto or finance agents who already use nansen-cli and need current web news or prices beyond on-chain datasets.
Skip if: Projects without a NANSEN_API_KEY, teams that cannot install the nansen CLI binary, or workflows that only need static repository context.
When should I use this skill?
Agent context is outdated and the task needs current web prices, news, or multi-query search results via nansen.
What you get
Parallel Serper search result sets with organic listings, knowledge graph snippets, and configurable result counts returned to the agent shell session.
- Parallel web search result payloads
- Current pricing and news snippets for agent prompts
By the numbers
- Example usage shows --num-results 5 per query
- Install manifest lists nansen-cli Node package with nansen binary
Files
Web Search
Search the web for one or more queries in parallel via the Serper API.
nansen web search "bitcoin price"
nansen web search "solana ecosystem news" --num-results 5
nansen web search --query "ethereum ETF" --query "bitcoin ETF" --num-results 3Positional args and --query flags can be combined — all become queries.
| Flag | Values | Default | Purpose |
|---|---|---|---|
--query | string | — | Query string (repeatable for multiple queries) |
--num-results | 1–20 | 10 | Results per query |
--pretty | flag | off | Human-readable JSON |
Returns results[] — one entry per query, each with organic[] (title, link, snippet, date) and optional knowledge_graph.
Note: Some domains are excluded from results (paywalled/unfetchable sites like bloomberg.com, twitter.com). Use nansen web fetch to retrieve content from specific URLs.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Choose nansen-web-searcher when web freshness must pair with Nansen on-chain tooling, not for generic offline codebase search.
FAQ
What does nansen web search require?
nansen-web-searcher requires the nansen binary on PATH, a NANSEN_API_KEY environment variable as primaryEnv, and Node installation of the nansen-cli package before agents can call nansen web search commands.
Can nansen-web-searcher run multiple queries at once?
nansen-web-searcher supports parallel searches by passing multiple --query flags to nansen web search, for example querying ethereum ETF and bitcoin ETF news in one invocation with optional --num-results limits.