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/testsgit clone --depth 1 https://github.com/lqwdtech/SaturnZapWhat 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 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
SaturnZap tests.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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Conventions
Fixtures (autouse)
conftest.py provides three autouse fixtures that reset state between tests:
_reset_active_network(conftest.py) — resetsconfig._active_networktoNone_clean_data_dir(per-file) — redirectsXDG_DATA_HOMEtotmp_path(no real seed touched)_reset_pretty(per-file) — resetsoutput._prettytoFalse_reset_node(per-file) — resetsnode._nodeandnode._ipc_modesingletons
New test files automatically pick these up. If a test needs the real data dir, override _clean_data_dir locally.
CLI Testing
from typer.testing import CliRunner
from saturnzap.cli import app
runner = CliRunner()
result = runner.invoke(app, ["balance"])
data = json.loads(result.output)
assert data["status"] == "ok"
Mocking LDK Node
Use unittest.mock.MagicMock with types.SimpleNamespace for nested return values:
n = MagicMock()
n.node_id.return_value = "02abc"
n.list_balances.return_value = SimpleNamespace(
total_onchain_balance_sats=100_000,
spendable_onchain_balance_sats=90_000,
total_lightning_balance_sats=50_000,
total_anchor_channels_reserve_sats=0,
)
Patch at the consumer: @patch("saturnzap.node.Builder"), not the ldk_node import.
ANSI Stripping
NO_COLOR=1 is set in conftest. For extra safety, use strip_ansi():
from tests.conftest import strip_ansi
assert "init" in strip_ansi(result.output)
Markers
@pytest.mark.live— requires running droplet nodes. Deselected in CI with-m "not live".- No marker needed for unit tests (default).
Assertions
- Parse JSON output:
json.loads(result.output)orjson.loads(capsys.readouterr().out) - Check error output on stderr:
json.loads(capsys.readouterr().err) - File permissions:
assert (path.stat().st_mode & 0o777) == 0o600
Don'ts
- Don't create a new
conftest.py— extend the root one - Don't mock at the
ldk_nodepackage level — mock atsaturnzap.nodeorsaturnzap.cli - Don't skip the
_clean_data_dirfixture unless testing real filesystem behavior
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 · 73 lines · 606 tokens per session scan A 0daf2da4943c
SaturnZap tests.instructions.md is an instructions file published in the GitHub repository lqwdtech/SaturnZap (7 stars, last pushed 17d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 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
Instructions for echennells/sparkbtcbot, covering sparkbtcbot, what this skill does, structure, trigger phrases and dependencies.
lightning-enable-mcp CLAUDE.md
Instructions for refined-element/lightning-enable-mcp, covering claude.md — lightning enable mcp, project overview, bug fix workflow and engineering standards.
sparkbtcbot 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
Instructions for raspibolt/raspibolt, covering raspibolt: development guidelines, working rules, autonomy model, level 0: autonomous and level 1: inform.