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/calhooon/bsv-wallet-cli/claude-mdgit clone --depth 1 https://github.com/Calhooon/bsv-wallet-cliWrote 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/instructions/calhooon/bsv-wallet-cli/claude-md)<a href="https://agentmods.dev/instructions/calhooon/bsv-wallet-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/calhooon/bsv-wallet-cli/claude-md.svg" alt="Measured on agentmods" 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 | $0.01579 | $0.01579 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
bsv-wallet-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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bsv-wallet-cli
Single Rust binary providing both a CLI wallet and an HTTP server that implements all 28 BRC WalletInterface endpoints, wire-compatible with the MetaNet Client.
Architecture
The binary has two modes: CLI commands for interactive wallet use, and an HTTP server (port 3322) that is wire-compatible with MetaNet Client.
src/
main.rs — CLI entrypoint, routes clap subcommands
context.rs — WalletContext: loads ROOT_KEY, opens SQLite, configures services
cli.rs — Clap argument definitions
commands/ — One file per CLI command (init, send, daemon, serve, split, etc.)
server/
mod.rs — Axum router setup, CORS, auth middleware, SpendingLock
handlers.rs — All 28 endpoint handlers, each translating MetaNet JSON ↔ SDK types
types.rs — MetaNet Client JSON request/response structs (the translation layer)
Dependency chain: bsv-wallet-cli → bsv-wallet-toolbox-rs (wallet engine, SQLite storage, signing, broadcasting) → bsv-rs (WalletInterface trait, crypto primitives). Both are published on crates.io.
Conventions
- MetaNet Client wire compatibility is the top constraint. The HTTP server must produce identical JSON to the MetaNet Client so existing tools (x402 skill, BRC-31 auth) work without modification.
- Translation layer (
server/types.rs): MetaNet Client uses different JSON shapes than the Rust SDK. Key differences:protocolID: mixed array[2, "name"]vs SDK'sProtocol { security_level, protocol_name }counterparty: hex string vsCounterparty::Other(PublicKey)- Binary data (
tx,signature): JSON number arrays[0,1,2,...]vs hex strings - Field names: MetaNet Client uses
protocolID/keyID(capital D). Use#[serde(alias = "protocolID")]sincerename_all = "camelCase"produces lowercased.
- SpendingLock: A FIFO mutex serializes
createActioncalls. With limited UTXOs, concurrent spending races on SQLite's write lock. Non-spending endpoints (crypto, queries) run fully concurrent. - Daemon vs Serve:
daemon= Monitor (background sync tasks) + HTTP server.serve= HTTP server only (dev mode, no background sync).
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.
- 4d ago First seen · 120 lines · 1,579 tokens per session scan A 8c6e5fa4287d
bsv-wallet-cli CLAUDE.md is an instructions file published in the GitHub repository Calhooon/bsv-wallet-cli (10 stars, last pushed today), licensed MIT. It adds 1,579 tokens to every session, about $0.0079 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
Get-Started-with-Web3 AGENTS.md
AGENTS.md instructions for beihaili/Get-Started-with-Web3, covering get started with web3 agent notes, 项目定位, ceo 运营目标, 常用命令 and ai-native 内容层.
hub.fabric.pub AGENTS.md
AGENTS.md instructions for FabricLabs/hub.fabric.pub, covering hub.fabric.pub — agent guidelines, release posture, project overview, recent work (important) and architecture.
maestro-mcp-server CLAUDE.md
Claude Code instructions for maestro-org/maestro-mcp-server, covering maestro mcp server - developer guide, architecture, key components, code generation and performance optimizations (2026-02).
aibtc-mcp-server CLAUDE.md
Claude Code instructions for aibtcdev/aibtc-mcp-server, covering claude.md, project overview, api sources, build commands and publishing & releases.
go-crypto-wallet copilot-instructions.md
Copilot instructions for hiromaily/go-crypto-wallet, covering github copilot instructions for go-crypto-wallet, project overview, quick reference, general guidelines and code suggestions.
go-crypto-wallet AGENTS.md
AGENTS.md instructions for hiromaily/go-crypto-wallet, covering agent guidelines for go-crypto-wallet, project identity, core values (priority order), expected behavior and always do.