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 agentmods add instructions/daoleno/wooo-cli/claude-mdgit clone --depth 1 https://github.com/daoleno/wooo-cliWhat 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 | $0.01639 | $0.01639 |
| Opus 5 | $0.00820 | $0.00820 |
| Sonnet 5 | $0.00328 | $0.00328 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
wooo-cli CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Development Commands
bun run dev- Run CLI in development modebun run dev -- <command>- Run specific command (e.g.bun run dev -- cex okx balance)bun run dev:docs- Run the Fumadocs documentation and landing appbun test- Run CLI testsbun run type-check- TypeScript type checkingbun run lint- Biome lintingbun run lint:fix- Auto-fix lint issuesbun run build- Build all apps
Architecture
This is a Bun-managed monorepo. The publishable CLI package is under
apps/cli, and the user-facing docs plus landing page are under apps/docs.
The CLI is a crypto all-in-one command app using Citty (unjs). Protocols are
grouped by type under apps/cli/src/protocols/ and exposed as
wooo <group> <protocol> <action> (e.g. wooo cex okx buy,
wooo perps hyperliquid long). Wallets are stored and managed via OWS (Open
Wallet Standard) vault at ~/.ows/.
Key Directories
apps/cli/src/core/- Config (c12), output engine, OWS wallet integration, signer protocol/adapters, EVM/Solana clients, loggerapps/cli/src/core/chain-ids.ts- CAIP-2 chain identifiers and aliasesapps/cli/src/core/external-wallets.ts- External wallet registryapps/cli/src/protocols/- Each protocol has commands.ts + client.ts + types.ts + constants.tsapps/cli/src/protocols/cex-base/- Shared CEX base client and command templates (CCXT)apps/cli/src/commands/- Universal commands (wallet, config, market, portfolio, chain, swap)apps/cli/tests/- Mirrors src structureapps/docs/- Fumadocs/Next.js documentation app and landing page~/.ows/- OWS vault directory (wallet keys, policy, audit logs)
Command Structure
wooo
├── config # Configuration management
├── wallet # Wallet management
│ ├── create / import / export / list / info / delete / switch / balance
│ ├── connect / disconnect / discover
│ ├── policy create / list / show / delete
│ └── key create / list / revoke
├── market # Aggregated market data (price, search)
├── portfolio # Cross-protocol portfolio (overview)
├── chain # On-chain operations (tx, balance, ens, call)
├── swap # Aggregated swap — auto-selects best DEX route
├── cex <exchange> # CEX: okx, binance, bybit
├── dex <protocol> # DEX: uniswap, curve, jupiter
├── defi <protocol> # DeFi: aave, lido
├── perps <protocol> # Perps DEX: hyperliquid, gmx
└── bridge <protocol> # Bridges: stargate
Grouping is automatic via ProtocolDefinition.type → PROTOCOL_TYPE_TO_GROUP mapping in apps/cli/src/protocols/types.ts.
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 · 117 lines · 1,639 tokens per session scan A b445cf626794
wooo-cli CLAUDE.md is an instructions file published in the GitHub repository daoleno/wooo-cli (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,639 tokens to every session, about $0.0082 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 2026-08-31.
Other instructions, from other repositories
pumpfun-bonkfun-bot CLAUDE.md
Instructions for chainstacklabs/pumpfun-bonkfun-bot, covering agent guide, ground rules, layout, naming inside learning-examples/ and commands.
gmgn-skills CLAUDE.md
Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
bitbank-mcp-server CLAUDE.md
Claude Code instructions for bitbankinc/bitbank-mcp-server, covering rules for bitbank-mcp-server, プロジェクト概要, 技術スタック, コマンド and アーキテクチャ.
x402-plugin-template CLAUDE.md
Claude Code instructions for MangroveTechnologies/x402-plugin-template, covering x402 plugin template, structure and rules.
gensyn-delphi-skills CLAUDE.md
Instructions for gensyn-ai/gensyn-delphi-skills, a project described as: Skills for agents to view markets and place trades on Gensyn's Delphi prediction markets.
x402-stellar-kit CLAUDE.md
Claude Code instructions for CodeStrux/x402-stellar-kit, a project described as: x402 payment primitives for Stellar: intent binding, a deterministic policy engine, a pluggable approver, and an agent surface. Apache-2.0.