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/lqwdtech/saturnzap/copilot-instructionsgit clone --depth 1 https://github.com/lqwdtech/SaturnZapWrote 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/lqwdtech/saturnzap/copilot-instructions)<a href="https://agentmods.dev/instructions/lqwdtech/saturnzap/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/lqwdtech/saturnzap/copilot-instructions.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 | $0.01176 | $0.01176 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
SaturnZap copilot-instructions.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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaturnZap — Copilot Instructions
CLI-first, non-custodial Lightning Network wallet for AI agents. Python 3.12, LDK Node, mainnet default.
Build & Test
uv sync # Install deps (never pip)
uv run ruff check src/ tests/ # Lint
uv run pytest tests/ -v # Unit tests (-m "not live" to skip droplet tests)
uv build # Build wheel
After code changes, run uv sync to reinstall the package before testing.
Architecture
All source lives in src/saturnzap/. Key modules:
| Module | Role |
|---|---|
cli.py |
Typer CLI entry point (sz). Each command → JSON output |
node.py |
LDK Node lifecycle. _require_node() lazy-starts; _use_ipc() auto-detects daemon |
output.py |
ok(**fields) → stdout JSON, error(code, msg) → stderr JSON + exit |
config.py |
TOML config + Esplora fallback resolver (3s probe timeout) |
keystore.py |
BIP39 seed + Fernet encryption (PBKDF2, 600K iterations, 16-byte salt) |
ipc.py |
Unix Domain Socket daemon. Newline-delimited JSON, 23 methods, threading.Lock |
payments.py |
BOLT11 invoices, keysend, spending caps, history |
l402.py |
HTTP 402 interceptor, token cache (SHA256-hashed URL) |
liquidity.py |
Channel health scoring (0–100), recommendations |
lqwd.py |
LQWD peer directory — 18 regions + agent-focused AI-Grid (LSPS1/LSPS2 JIT), default on mainnet |
mcp_server.py |
FastMCP stdio server, 25 tools |
service.py |
Systemd service generator |
See docs/architecture.md for diagrams and IPC protocol details.
Conventions
- Output is always JSON:
{"status": "ok", ...}or{"status": "error", "code": "...", "message": "..."}. Never print plain text. Useoutput.ok()/output.error(). - IPC routing: CLI commands check
_use_ipc()first. If daemon is running, route through UDS; otherwise start ephemeral node. - Network-namespaced paths:
~/.local/share/saturnzap/<network>/— each network (signet, bitcoin) has separate seed, socket, config. - Passphrase:
SZ_PASSPHRASEenv var or interactive prompt. No caching. - Module-level singletons:
_node,_ipc_mode,_active_network,_pretty— useglobalwith# noqa: PLW0603. - Mainnet safety:
_confirm_mainnet(yes)gate on any command touching bitcoin network. - LDK Node v0.7.0: Vendored wheel at
vendor/. API:builder.set_entropy_bip39_mnemonic(mnemonic, None),generate_entropy_mnemonic(None). - Commit messages: Plain English, no conventional-commit prefixes (
feat:,fix:,chore:). Lead with the outcome. Avoid alarm words (fix,bug,warning,error,vulnerability). Examples:Add smart health alerts for payments and balances,Security hardening — payment proofs, graceful shutdown, and integrity checks. Bodies may include technical detail.
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.
- 5d ago First seen · 74 lines · 1,176 tokens per session scan A 74cd6a1557e5
SaturnZap copilot-instructions.md is an instructions file published in the GitHub repository lqwdtech/SaturnZap (7 stars, last pushed 18d ago), licensed MIT. It adds 1,176 tokens to every session, about $0.0059 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
sparkbtcbot CLAUDE.md
Claude Code instructions for echennells/sparkbtcbot, covering sparkbtcbot, what this skill does, structure, trigger phrases and dependencies.
lightning-enable-mcp CLAUDE.md
Claude Code instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.
sparkbtcbot AGENTS.md
AGENTS.md instructions for echennells/sparkbtcbot, covering agents.md — sparkbtcbot, what this repo does (why the rules below are not optional), non-negotiable rules, if you run git clone + npm install for the user and full guidance.
polar CLAUDE.md
Instructions for jamaljsr/polar, covering claude.md, about polar, essential commands, development and testing individual files.
polar copilot-instructions.md
Instructions for jamaljsr/polar, covering polar - ai coding assistant instructions, core architecture, network orchestration via docker compose, state management (easy-peasy + redux) and visual designer (react flow chart).
raspibolt CLAUDE.md
Claude Code instructions for raspibolt/raspibolt, covering raspibolt: development guidelines, working rules, autonomy model, level 0: autonomous and level 1: inform.