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 commands/calhooon/bsv-wallet-cli/claudegit clone --depth 1 https://github.com/Calhooon/bsv-wallet-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 | $0.00000 | $0.01465 |
| Opus 5 | $0.00000 | $0.00732 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
CLAUDE 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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commands
One file per CLI subcommand, each exposing a single
pub async fn run(...). Plusui.rs, which is a standalone web-based wallet inspector.
Files
| File | Signature | Purpose |
|---|---|---|
init.rs |
run(db_path, key?) |
Generate or import root key, create SQLite DB, write .env |
daemon.rs |
run(&Cli) |
Monitor + Wallet + HTTP server (production mode) |
serve.rs |
run(WalletContext, port) |
HTTP server only, no monitor (dev mode) |
send.rs |
run(&WalletContext, address, satoshis) |
P2PKH send, outputs AtomicBEEF hex |
fund.rs |
run(&WalletContext, beef_hex, vout) |
Internalize external BEEF (faucet/exchange funding) |
split.rs |
run(&WalletContext, count) |
Split all UTXOs into N equal outputs |
balance.rs |
run(&WalletContext) |
Sum all spendable sats (paginates through all outputs) |
address.rs |
run(&WalletContext) |
Derive and display BRC-29 receiving address |
identity.rs |
run(&WalletContext) |
Show identity key, address, chain |
actions.rs |
run(&WalletContext, label?) |
List transaction actions, optional label filter |
outputs.rs |
run(&WalletContext, basket?, tag?) |
List UTXOs, optional basket/tag filters |
services.rs |
run(&Cli) |
Check chain services health (block height) |
compact.rs |
run(&WalletContext) |
Debug BEEF compaction on largest stored BEEF blob |
ui.rs |
run(db_path, port) |
Web-based wallet inspector (standalone Axum server) |
Decisions
- Three initialization patterns: (1) Most commands take
&WalletContext. (2)inittakes rawdb_path+ optional key (no context exists yet). (3)daemon,services, anduitake&Clior raw args because they manage their own storage/services. daemonvsserve:daemoncreates its ownArc<Storage>+Arc<Services>for the Monitor (background sync tasks) + Wallet + HTTP server, with a periodic UTXO count check (every 5 min, threshold viaMIN_UTXOSenv var, default 3).servetakes an ownedWalletContextand runs the HTTP server only — no monitor, no UTXO warnings. Useservefor dev,daemonfor production.- TLS support: Both
daemonandservereadTLS_CERT_PATHandTLS_KEY_PATHenv vars. If both are set, the server binds with TLS. Otherwise plain HTTP. sendoutput tagging: Send outputs are tagged"relinquish"to mark them as belonging to the recipient, not this wallet. This prevents the wallet from counting sent funds in its own balance. The result also builds AtomicBEEF hex from the returned BEEF for wallet-to-wallet transfers.AUTH_TOKENenv var: BothdaemonandservepassAUTH_TOKENtoServerConfig. When set, the HTTP server requires bearer auth on all endpoints.- JSON output mode: All
WalletContext-based commands checkctx.json_outputand emit structured JSON when--jsonis passed. Commands using&Clicheckcli.json. uiis a separate web server: It opens its own SQLite connection (read-only queries) and serves an embedded HTML dashboard at a configurable port. It does NOT go through the wallet engine — it queries the database directly via sqlx.
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.
- 3d ago First seen · 52 lines · 0 tokens per session scan A eace053d68f2
CLAUDE is a command published in the GitHub repository Calhooon/bsv-wallet-cli (10 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,465 tokens. 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 commands, from other repositories
agent-wallet
Use the bundled agent-wallet skill to operate a non-custodial wallet directly on-chain (EVM and Bitcoin).
fix-btc-e2e-p11
Fix errors in BTC E2E test (Pattern 11: P2TR Tapscript M-of-N).
fix-btc-e2e-p4
Fix errors in BTC E2E test (Pattern 4: P2SH-P2WSH 2-of-3 Multisig).
fix-btc-e2e-p6
Fix errors in BTC E2E test (Pattern 6: P2WSH 2-of-3 Multisig).
balance
Universal Crypto MCP API Reference v1.0.0.
pay
Universal Crypto MCP API Reference v1.0.0.