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/solanabr/solana-ai-kit/test-rustgit clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/commands/solanabr/solana-ai-kit/test-rust)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/test-rust"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/test-rust.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 | $0.00010 | $0.02376 |
| Opus 5 | $0.00005 | $0.01188 |
| Sonnet 5 | $0.00002 | $0.00475 |
| Haiku 4.5 | $0.00001 | $0.00238 |
Grade A, and why
test-rust 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running Rust tests. This command covers Solana program testing (Mollusk, LiteSVM, Surfpool, Trident) and backend service testing.
Related Skills
- testing.md - Testing strategy details
- security.md - Security testing checklist
- programs/anchor.md - Anchor test patterns
- programs/pinocchio.md - Pinocchio test patterns
Step 1: Identify Project Type
echo "🔍 Detecting project type..."
if [ -f "Anchor.toml" ]; then
echo "📦 Anchor project detected"
PROJECT_TYPE="anchor"
elif grep -q "pinocchio" Cargo.toml 2>/dev/null; then
echo "🎯 Pinocchio program detected"
PROJECT_TYPE="pinocchio"
elif grep -q "solana-program" Cargo.toml 2>/dev/null; then
echo "⚙️ Solana native program detected"
PROJECT_TYPE="solana"
elif grep -q "axum\|tokio" Cargo.toml 2>/dev/null; then
echo "🌐 Rust backend service detected"
PROJECT_TYPE="backend"
else
echo "🦀 Standard Rust project detected"
PROJECT_TYPE="standard"
fi
Solana Program Testing
Testing Pyramid
- Unit tests (fastest): Mollusk - individual instruction tests
- Integration tests (fast): LiteSVM - multi-instruction flows
- Realistic state tests: Surfpool - mainnet/devnet state locally
- Fuzz tests: Trident - edge case discovery
Mollusk Unit Tests
Fast, isolated tests for individual instructions:
echo "🐚 Running Mollusk unit tests..."
cargo test --lib -- --nocapture
#[cfg(test)]
mod tests {
use mollusk_svm::Mollusk;
use solana_sdk::{account::Account, pubkey::Pubkey, instruction::Instruction};
#[test]
fn test_initialize() {
let program_id = Pubkey::new_unique();
let mollusk = Mollusk::new(&program_id, "target/deploy/my_program.so");
// Setup accounts
let user = Pubkey::new_unique();
let accounts = vec![
(user, Account::new(1_000_000_000, 0, &program_id)),
];
// Create instruction
let instruction = Instruction {
program_id,
accounts: vec![],
data: vec![0], // Initialize discriminator
};
// Process and verify
let result = mollusk.process_instruction(&instruction, &accounts);
assert!(result.program_result.is_ok());
// Check CU usage
println!("CU consumed: {}", result.compute_units_consumed);
assert!(result.compute_units_consumed < 50_000);
}
}
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 · 404 lines · 10 tokens per session scan A 3930d45f8cfe
test-rust is a command published in the GitHub repository solanabr/solana-ai-kit (98 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 2,376 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
dmaic-fit-improvement
Drive a Six Sigma DMAIC (Define / Measure / Analyze / Improve / Control) cycle for a clinic-wide socket-fit improvement programme — produces the project charter, measurement plan, analysis findings, improvement piloting, and control-phase lock-in.
derive-access-deliverables
Define and batch-produce the public-facing deliverables derived from preservation masters — access copies, IIIF tile pyramids, OCR/transcription, and thumbnails — so the digitized collection is usable, not just safely stored.
recap-module
Generate the four-audience recap that closes a module: a learner recap, a manager nudge, a facilitator log, and (when sponsor is Definitive) a sponsor highlight.
map-evidence
Bind each learning objective to the assessment items that evidence it and define the evidence model — the slip and guess parameters that make Bayesian updating possible (ECD evidence model).
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.