Borrowing it
Nothing to install: this file belongs to solanabr/solana-glossary. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/solanabr/solana-glossary/main/.claude/commands/audit-solana.mdgit clone --depth 1 https://github.com/solanabr/solana-glossaryWrote 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-glossary/audit-solana)<a href="https://agentmods.dev/commands/solanabr/solana-glossary/audit-solana"><img src="https://agentmods.dev/badge/commands/solanabr/solana-glossary/audit-solana/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/solanabr/solana-glossary/audit-solana"><img src="https://agentmods.dev/badge/commands/solanabr/solana-glossary/audit-solana.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00010 | $0.02831 |
| Opus 5 | $0.00005 | $0.01416 |
| Sonnet 5 | $0.00002 | $0.00566 |
| Haiku 4.5 | $0.00001 | $0.00283 |
Grade A, and why
audit-solana scanned grade A with 1 finding 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 12d 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.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- [ ] Code compiles without warnings Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
This is a copy
100% identical to audit-solana — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are conducting a security audit for Solana programs. This is CRITICAL - take your time.
Related Skills
- security.md - Comprehensive security checklist
- programs/anchor.md - Anchor security patterns
- programs/pinocchio.md - Pinocchio security patterns
- testing.md - Fuzz testing with Trident
Pre-Audit Checklist
- All tests passing
- Code compiles without warnings
- Documentation complete
- No hardcoded keys or secrets
Step 1: Automated Analysis
echo "🔍 Running automated security analysis..."
# Dependency audit (check for known vulnerabilities)
echo " 📦 Checking dependencies..."
cargo audit
# Supply chain security (check for malicious dependencies)
if command -v cargo-geiger >/dev/null 2>&1; then
echo " ☢️ Checking unsafe code usage..."
cargo geiger
fi
# Clippy with strict security lints
echo " 🔎 Running clippy security lints..."
cargo clippy --all-targets -- \
-W clippy::all \
-W clippy::pedantic \
-W clippy::unwrap_used \
-W clippy::expect_used \
-W clippy::panic \
-W clippy::arithmetic_side_effects \
-D warnings
# Format check
echo " 📝 Checking format..."
cargo fmt --check
# Run full test suite
echo " 🧪 Running tests..."
if [ -f "Anchor.toml" ]; then
anchor build && anchor test
else
cargo build-sbf && cargo test
fi
echo "✅ Automated analysis complete"
Step 2: Account Validation Review
CRITICAL: Every account MUST be validated. Check each instruction:
Owner Checks
// ✓ CORRECT: Validate account owner
if *account.owner != expected_program_id {
return Err(ProgramError::IncorrectProgramId);
}
// ✗ WRONG: Assuming owner without check
Signer Checks
// ✓ CORRECT: Verify signer
if !authority.is_signer {
return Err(ProgramError::MissingRequiredSignature);
}
// ✗ WRONG: Privileged operation without signer check
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.
- 12d ago First seen · 453 lines · 10 tokens per session scan A 44a93d69507a
audit-solana is a command published in the GitHub repository solanabr/solana-glossary (18 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 2,831 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). It is 100% identical to audit-solana, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
question
Read-only code Q&A. Spawns the code-explorer subagent (Haiku-class) to grep, glob, and read excerpts of the codebase, then synthesizes a cited answer with file:line citations. No plan, no gates, no implementation. Fast. Triggers: "where is X defined", "what calls Y", "how does Z work", "find references to", "explain…
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.