xete-mcp: Skill for Claude Code

.claude/skills/solana-security-hardening/SKILL.md

solana-security-hardening is a skill for Claude Code from xetenet/xete-mcp. It costs 111 tokens per session (1,281 once invoked), scanned A, original, MIT.

A security checklist and review process for Solana programs, Rust smart contracts, cryptographic clients, and related servers. Solana is a blockchain platform, and a smart contract is code that runs on it.

In plain words
What is it for?
Use it when reviewing or changing Solana or Rust contract code, cryptographic code, relays, permit servers, or MCP servers. It checks validation, permissions, arithmetic, and external-program calls.
Why use it?
It catches unsafe account handling, signer checks, token arithmetic, key handling, and similar mistakes before they can affect deployed or financial code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is xetenet/xete-mcp's own configuration. It tells Claude Code how to work on xete-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything xete-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xetenet/xete-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xetenet/xete-mcp/main/.claude/skills/solana-security-hardening/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xetenet/xete-mcp

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.

agentmods badge for solana-security-hardening

README.md
[![agentmods](https://agentmods.dev/badge/skills/xetenet/xete-mcp/solana-security-hardening/github.svg)](https://agentmods.dev/skills/xetenet/xete-mcp/solana-security-hardening)
Your own site
<a href="https://agentmods.dev/skills/xetenet/xete-mcp/solana-security-hardening"><img src="https://agentmods.dev/badge/skills/xetenet/xete-mcp/solana-security-hardening/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.

agentmods 80×15 button for solana-security-hardening

Your own site · 80×15
<a href="https://agentmods.dev/skills/xetenet/xete-mcp/solana-security-hardening"><img src="https://agentmods.dev/badge/skills/xetenet/xete-mcp/solana-security-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,281 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.01281
Opus 5 $0.00056 $0.00641
Sonnet 5 $0.00022 $0.00256
Haiku 4.5 $0.00011 $0.00128

Measured 12d ago against content hash b73113b57381, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

solana-security-hardening 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 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.

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.

.claude/skills/solana-security-hardening/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solana Security Hardening

Run this checklist against every diff in scope. Each item is a gate: pass, or document why it does not apply. "Probably fine" fails the gate. Items tagged (BM-…) were added because this codebase shipped that exact bug once — the benchmark file holds the doubt prompt.

On-chain (xete-tab / Xete Swap)

Account validation

  • Every account's owner is checked against the expected program
  • Every signer requirement is enforced (is_signer), including on close/settle paths
  • PDA derivations re-verified in the program, never trusted from client-supplied bump/address
  • Account discriminators / type checks prevent substituting one account type for another
  • Writable accounts justified — no account writable that doesn't need to be
  • CPI account-list completeness across asset variants: for every external-program CPI, the callee's optional/conditional accounts are enumerated and each input variant (standalone vs collection-member, Token vs Token-2022, …) is either supported or explicitly rejected, with a test per variant (BM-swap-core-cpi-collection)

Arithmetic

  • All token/lamport math uses checked ops (checked_add, checked_sub, checked_mul) or saturating with explicit rationale
  • overflow-checks = true in release profile confirmed in Cargo.toml
  • Rounding direction on any division is explicit and favors the protocol/counterparty as intended

State & flow

  • Commitment scheme preimages include all fields that must not be malleable (SHA256 inputs enumerated in a comment)
  • No instruction can be replayed to double-settle a tab; replay protection identified by name
  • Close/settle paths zero or reassign lamports correctly (no resurrection attacks)
  • Any state referenced by address is re-validated against the agreed terms at settle time — a closed PDA can be recreated at the same address with different contents; takers/acceptors supply expected-terms (slippage) bounds (BM-swap-pda-reopen-rug)
  • Degenerate economics rejected at creation time: zero amounts, born-expired timestamps (BM-swap-zero-amount-listings)
  • Every value transfer moves a priced/consented amount the caller agreed to — never a balance read (BM-relay-payment-drainer)
  • CPI targets validated by program ID, not by account position

Read the full file on GitHub · 62 lines

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.

  1. 12d ago First seen · 62 lines · 111 tokens per session scan A b73113b57381

Subscribe to this mod's changes

solana-security-hardening is a skill published in the GitHub repository xetenet/xete-mcp (0 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,281 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

legacy-shield

Secure zero-knowledge document vault for AI agents. Persistence for your secrets.

bitatlas-group/bitatlas · 19 tokens

blockrun

Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana). No API keys, no accounts, no subscriptions. Start here when you have the BlockRun MCP installed and need to know WHICH tool answers a question, how the wallet works, or how to make a…

BlockRunAI/blockrun-mcp · 241 tokens

crypto-data

Use for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain; also when the user asks for on-chain SQL, wallet labels/net worth, social mindshare or crypto news, so they are told plainly what BlockRun…

BlockRunAI/blockrun-mcp · 194 tokens

surf

Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…

BlockRunAI/blockrun-mcp · 110 tokens

rpc

Use when the user needs raw blockchain JSON-RPC access — contract reads (ethcall), native balances, blocks, transactions, logs, gas estimates, or any chain-native RPC method across 40 chains. One endpoint per chain via BlockRun's Tatum-backed gateway, $0.0030 per call, no node, no API key. Prefer blockrunprice /…

BlockRunAI/blockrun-mcp · 92 tokens

ironmesh-send

Send an application message (MSG) to a specific IronMesh peer. Use when the user asks to "send X to agent Y" or "ping peer Z". Has side effects — only invoke when the user explicitly asks.

WizTheAgent/IronMesh · 49 tokens