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.
git clone --depth 1 https://github.com/beriktassuly/solana-audit-skillWrote 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/beriktassuly/solana-audit-skill/audit-solana)<a href="https://agentmods.dev/commands/beriktassuly/solana-audit-skill/audit-solana"><img src="https://agentmods.dev/badge/commands/beriktassuly/solana-audit-skill/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/beriktassuly/solana-audit-skill/audit-solana"><img src="https://agentmods.dev/badge/commands/beriktassuly/solana-audit-skill/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 | $0.00036 | $0.00651 |
| Opus 5 | $0.00018 | $0.00326 |
| Sonnet 5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
audit-solana 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 10d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Solana
Use ../skill/SKILL.md as the canonical instruction source. Load only the references needed for the current scope.
Workflow
- Confirm intake and scope: programs, instructions, token programs, upgrade authority, admin model, client or wallet boundary, tests, and deployment target.
- Classify attack surface before reviewing details: account validation, signer and authority, PDA seeds and bumps, CPI trust boundaries, token integration, arithmetic and accounting, state machines, lifecycle and closure, oracle assumptions, governance and upgrade risk, liveness, client and wallet UX, Token-2022, durable nonce governance, or ZK proof soundness.
- Review by taxonomy class, not by tool output alone. Use the closest reference under
../skill/references/taxonomy/when a class is relevant. - Triage severity with ../skill/references/severity-triage.md. Separate confirmed exploitability, hardening, false-positive conditions, and residual risk.
- Write findings with ../skill/references/workflows/finding-writeup-workflow.md: evidence, exploit path, impact, fix, and verification.
- Verify remediation with targeted tests, local reproduction, invariant checks, or simulation. Do not present a fix as verified until the verification step is actually reviewed.
- Generate the final report from confirmed findings, unresolved assumptions, residual risks, and remediation status.
Required Output Contract
For each finding, lead with:
- Evidence: file, line, transaction, report citation, or reproduced behavior.
- Impact: what an attacker can gain, break, or block, and under what preconditions.
- Fix: the smallest credible mitigation tied to the protected invariant.
- Verification: the test, invariant, reproduction, or review step that proves the fix.
Label unverified suspicions as hypotheses. Do not imply exploit reproduction from pattern similarity alone.
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.
- 10d ago First seen · 39 lines · 36 tokens per session scan A 81d576067aef
audit-solana is a command published in the GitHub repository beriktassuly/solana-audit-skill (4 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 651 once invoked, about $0.0002 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 commands, from other repositories
scan
Scan a path against the Solana Security Standard (SOL-0XX) and report findings with fixes.
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
setup-x402
Wire x402 pay-per-call onto a provider's already-comprehended API via PayAI — point tools at the provider's OWN x402 endpoint, prove the handshake offline (X402MODE=stub), keep the provider at 100%. Gecko never the rail, no cut. Usage: /setup-x402.
krait-quick
Run a streamlined audit: Recon → Detection → Verification → Report. Skips state inconsistency analysis and cross-feed iteration for speed.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.