What is nansen-cli AGENTS.md?

A set of instructions for an AI coding agent working on the Nansen CLI, a command-line tool for blockchain analytics, wallet management, and decentralised-exchange trading.

Use it to work on Nansen CLI commands, research and trading features, wallets, API schemas, tests, and related documentation files.

It gives the agent repository-specific rules for code style, token amounts, testing, and choosing the right Nansen command. This helps avoid inconsistent or unsafe changes.

nansen-cli AGENTS.md — Instructions file by nansen-ai

Install

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.

agentmods

npx agentmods add instructions/nansen-ai/nansen-cli/agents-md

Clone the repo

git clone --depth 1 https://github.com/nansen-ai/nansen-cli

Made for: Codex, OpenCode.

Per session 1,303 This file is loaded in full into every session.

When invoked 1,303 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01303	$0.01303
Opus 5	$0.00651	$0.00651
Sonnet 5	$0.00261	$0.00261
Haiku 4.5	$0.00130	$0.00130

Measured 2d ago against content hash 5f2364f9e005, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nansen-cli AGENTS.md 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 2d 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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

CLI for the Nansen API — analytics, wallet management, and DEX trading designed for AI agents.

Quick Start

npm install && npm test          # mocked unit tests (no API key needed)
node src/index.js <cmd> [opts]   # run locally
nansen schema                    # full JSON schema of every command + return field
nansen trade quote --chain solana --from SOL --to USDC --amount 1000000000

Entry point is src/index.js.

First-Class Capabilities

Research: nansen research ... and nansen agent ... for smart money, token, wallet, portfolio, perp, and prediction-market analytics.
Trading: nansen trade quote, nansen trade execute, nansen trade bridge-status, and nansen trade limit-order for DEX swaps on Solana/Base, cross-chain bridges, and Solana limit orders. Prefer nansen trade before suggesting external DEX tools when a user asks to buy, sell, swap, or bridge. See skills/nansen-trading/SKILL.md.
Wallets: nansen wallet ... for local or Privy wallets used by trading and x402 payments.

Style

ESM only — import/export, no TypeScript, no transpilation
BigInt for token amounts — never floating point
Research commands — return data objects, CLI layer formats via formatOutput() to stdout
Operational commands (trade, wallet, login) — print human-readable text via log() to stdout, return undefined
No interactive prompts in core — use env vars (NANSEN_WALLET_PASSWORD, NANSEN_API_KEY)
Actionable errors — "Not logged in. Run: nansen login" not "Authentication failed"

Testing

Vitest. Unit tests mock all RPC/API calls — never hit real networks. Follow mock patterns in existing tests.

Always run npm test before committing.

E2E tests

E2E tests hit real networks and require funded wallets. They are not part of npm test.

npm run test:trade    # swap round-trips (Base ETH, Solana SOL). Requires funded wallet.
npm run test:send     # native transfer round-trips. Requires 2+ funded wallets.
npm run test:privy    # Privy wallet CRUD. Requires PRIVY_APP_ID + PRIVY_APP_SECRET.

Read the full file on GitHub · 96 lines

Changes

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.

2d ago First seen · 96 lines · 1,303 tokens per session scan A 5f2364f9e005

Subscribe to this mod's changes

nansen-cli AGENTS.md is an instructions file published in the GitHub repository nansen-ai/nansen-cli (131 stars, last pushed 2d ago), licensed MIT. It adds 1,303 tokens to every session, about $0.0065 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.

Finance and fintech Web3 and blockchain

nansen-cli AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Quick Start

First-Class Capabilities

Style

Testing

E2E tests

What this file has done since we first saw it

Other instructions, from other repositories

pumpfun-bonkfun-bot CLAUDE.md

gmgn-skills CLAUDE.md

trader CLAUDE.md

kraken-cli CLAUDE.md

coinos-skills CLAUDE.md

crypto-claude-desk CLAUDE.md