nansen-general-search — Claude Code skill: find tokens by name
This skill looks up tokens and entities by name through the Nansen CLI and returns the address, ticker and chain. Handy when all you have is a token name.
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a claude-codeWhat nansen-general-search does
The skill wraps nansen research search and tells the agent which flags to pass. Matching is case-insensitive and runs on names. Set the kind with --type (token or entity), narrow by network with --chain, cap the output with --limit (default 25, max 50), and pick columns with --fields.
Address lookup is out of scope. The skill description points to profiler labels for that, so if you already hold a contract address, this is the wrong tool.
You need a selected API key or a saved browser session before any research call. Run nansen auth status first, and nansen login for a fresh browser approval. NANSEN_API_KEY overrides the saved session. Every call can spend from the configured wallet through x402, loops included, so check your spending limits before firing off a batch of searches. If authentication fails, don't unset the key or fall back to anonymous access — follow the CLI error guidance instead.
What it helps with
- get a token address from a name alone
- filter search hits down to one chain
- pull address, ticker and chain in a single call
- find an entity by name with a five-row cap
- check how a token is spelled in Nansen's index
Example prompts for the agent
- Search for the token jupiter and show its address and chain
- Look up the entity Vitalik, limit to five results
- Find bonk on solana and return only address, name, symbol, chain
How to install nansen-general-search
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a claude-code2Manually: put the files in place
~/.claude/skills/nansen-general-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nansen-general-search/
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a codex2Manually: put the files in place
.agents/skills/nansen-general-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a cursor2Manually: put the files in place
.cursor/skills/nansen-general-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nansen-ai/nansen-cli nansen-general-search2Manually: put the files in place
.github/skills/nansen-general-search/SKILL.md1Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/nansen-ai/nansen-cli --path skills/nansen-general-searchManually: put the files in place
.devin/skills/nansen-general-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about nansen-general-search
How do I install nansen-general-search in Claude?
Run npx skills add nansen-ai/nansen-cli --skill nansen-general-search -a claude-code. The skill lands at ~/.claude/skills/nansen-general-search/SKILL.md.
What does nansen-general-search do?
It searches tokens and entities by name via nansen research search, returning the address, ticker and chain when you ask for those fields.
Can it find a token by contract address?
No, matching is name-only. The skill description points to profiler labels for address lookup.
Source text
SKILL.md · MIT
---
name: nansen-general-search
description: Search for tokens or entities by name. Use when you have a token name and need the full address, or want to find an entity.
metadata:
openclaw:
requires:
bins:
- nansen
primaryEnv: NANSEN_API_KEY
install:
- kind: node
package: nansen-cli
bins: [nansen]
allowed-tools: Bash(nansen:*)
---
## Authentication
Browser login requests `nansen:api` for API-key-equivalent account API permissions; existing OAuth/MCP `nansen:read` semantics and separate wallet authorization are unchanged.
Before any research command or loop, require an explicitly selected API key or saved browser session. Run `nansen auth status` first. Its cached/unverified metadata does not prove credential validity or unlocked storage. Cached access-token expiry alone does not mean the session is unusable: the CLI normally renews a selected session automatically during an already-authorized research task, without another consent request or a separate account check. Stop on anonymous selection, invalid authentication state, blocked or uncertain renewal/cleanup, or an actual authentication failure, including rejected or expired refresh authority. Follow the CLI error guidance; use the free `nansen account` check when troubleshooting calls for it. Do not unset a failed key, erase a session or switch to anonymous access to retry.
Use `nansen login` for fresh browser approval within the documented platform scope, or configure a conventional API key. `NANSEN_API_KEY` overrides the saved session. OpenClaw's optional `primaryEnv` mapping preserves configured API-key injection; it is not a required-key gate or proof of authentication. Normal credits and entitlements apply. Login does not purchase credits. Browser login is available in CLI 2.0.0 within the [macOS arm64 preview scope](https://github.com/nansen-ai/nansen-cli/blob/main/docs/browser-login.md#preview-platform-scope).
API keys and browser sessions use the same automatic x402 payment behavior: a supported HTTP 402 challenge can spend funds from the configured wallet under existing wallet authorization, payment policy and spending limits. Each call, including calls in loops, can incur a payment. Authentication, authorization and session-renewal failures never trigger payment; login verification and `nansen account` never pay automatically. Anonymous x402 remains available as a separate paid workflow requiring explicit user intent and payment setup. Do not run this research workflow anonymously or switch to anonymous access after authentication fails.
# Search
```bash
nansen research search "jupiter" --type token
nansen research search "Vitalik" --type entity --limit 5
nansen research search "bonk" --chain solana --fields address,name,symbol,chain
```
| Flag | Purpose |
|------|---------|
| `--type` | `token` or `entity` |
| `--chain` | Filter by chain |
| `--limit` | Number of results (default 25, max 50) |
| `--fields` | Select specific output fields |
Case-insensitive. Does NOT match by address — use `profiler labels` for address lookup.
© nansen-ai · MIT · nansen-ai/nansen-cli