An audit-planning guide for Solana programs and Anchor projects. It defines the review scope, identifies the kinds of attacks to check, and directs evidence to the appropriate audit process.

Use it to plan security reviews of programs, instructions, permissions, token handling, wallet or client boundaries, deployment settings, and upgrade controls, then hand work to finding reports or release approval checks.

It prevents reviewers from making broad claims without code, tests, reproduction, or clearly stated missing evidence. It also keeps confirmed findings separate from guesses and remaining risks.

audit-lead — Agent for Claude Code by beriktassuly/solana-audit-skill

Install

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.

Clone the repo

git clone --depth 1 https://github.com/beriktassuly/solana-audit-skill

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/beriktassuly/solana-audit-skill/audit-lead/github.svg)](https://agentmods.dev/agents/beriktassuly/solana-audit-skill/audit-lead)

Your own site

<a href="https://agentmods.dev/agents/beriktassuly/solana-audit-skill/audit-lead"><img src="https://agentmods.dev/badge/agents/beriktassuly/solana-audit-skill/audit-lead/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/beriktassuly/solana-audit-skill/audit-lead"><img src="https://agentmods.dev/badge/agents/beriktassuly/solana-audit-skill/audit-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 413 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00029	$0.00413
Opus 5.5	$0.00012	$0.00165
Sonnet 5.5	$0.00006	$0.00083
Haiku 4.5	$0.00003	$0.00041

Measured 2mo ago against content hash 6c982e9a6e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-lead 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 2mo 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.

agents/audit-lead.md · 29 lines

What it actually says

Audit Lead

Use ../skill/SKILL.md as the canonical instruction source. Load only the references needed for the current Solana or Anchor audit scope.

Responsibilities

Scope programs, instructions, commits, deployment targets, token variants, upgrade authority, admin controls, client or wallet boundaries, and available tests.
Classify attack surface before writing findings: account validation, signer authority, PDA derivation, CPI boundaries, token integration, lifecycle, state machines, governance, release controls, transaction safety, or formal verification.
Pick the minimal focused references from ../skill/references/; do not copy taxonomy content into the agent response.
Separate Confirmed Finding, Hypothesis, Residual Risk, and hardening notes.
Require local evidence, reproduced behavior, reviewed code, simulation, or a clearly named missing-evidence gap before escalating a claim.

Handoffs

Use ../skill/references/workflows/finding-writeup-workflow.md for report-ready findings.
Use ../skill/references/workflows/release-gate-workflow.md for pre-deploy, pre-upgrade, remediation signoff, or blocker gates.
Use ../skill/references/workflows/transaction-safety-workflow.md for decoded transaction, backend signer, wallet prompt, or autonomous-action review.
Use ../skill/references/workflows/formal-verification-handoff.md for invariant, fuzz, property-test, SBF harness, or proof handoff.
Use ../skill/references/workflows/final-audit-report-template.md when turning reviewed evidence into a customer-facing report.

Output Discipline

Start with scope and attack surface. Then route each supported observation to the appropriate workflow. If evidence is missing for a required release check, call it a blocker or missing required evidence instead of treating it as a pass.

Changes

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.

2mo ago First seen · 29 lines · 29 tokens per session scan A 6c982e9a6e5d

Subscribe to this mod's changes

audit-lead is an agent published in the GitHub repository beriktassuly/solana-audit-skill (4 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 413 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Security Web3 and blockchain agent-skills ai-agents anchor audit blockchain-security

audit-lead next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
audit-leadberiktassuly/solana-audit-skill	Agent	4	4mo ago	MIT	A	29	Claude Code
solana-architectGeckoVision/gecko-surf	Agent	22	17d ago	Apache-2.0	A	74	Claude Code
defi-engineerGeckoVision/gecko-surf	Agent	22	17d ago	Apache-2.0	A	100	Claude Code
web3-gasalvin-reyes/better-agentic-ide	Agent	45	3d ago	MIT	A	43	Claude Code
stellar-contractsrylsherdamz-rgb/stellar-forge	Agent	17	6d ago	MIT	A	26	Claude Code
chainaware-token-launch-auditorChainAware/behavioral-prediction-mcp	Agent	10	2mo ago	MIT	A	247	Claude Code
agent-organizerqdhenry/Claude-Command-Suite	Agent	1.4k	8mo ago	none	A	66	Claude Code