proxy-upgrade-safety

proxy-upgrade-safety is a skill for Claude Code from quillai-network/quillshield_skills. It costs 96 tokens per session (2,944 once invoked), scanned A, original, MIT.

A security review guide for upgradeable Ethereum smart contracts, where a proxy stores data and forwards calls to an implementation contract. It covers Transparent, UUPS, Beacon, Diamond, and Minimal proxy patterns.

In plain words
What is it for?
Use it when auditing proxy architectures, reviewing implementation upgrades, checking initialization, examining delegatecall-based designs, or managing Diamond facets.
Why use it?
It helps explain and check risks such as incompatible storage layouts, unsafe initialization, conflicting function selectors, delegatecall mistakes, and unauthorized upgrades. These errors can corrupt data or allow control of the contract.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the proxy-upgrade-safety plugin — 1 skill shipped together

Good fit Use it when auditing proxy architectures, reviewing implementation upgrades, checking initialization, examining delegatecall-based designs, or managing Diamond facets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/quillai-network/quillshield_skills/proxy-upgrade-safety
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.

Any agent
npx skills add quillai-network/quillshield_skills --skill proxy-upgrade-safety
Clone the repo
git clone --depth 1 https://github.com/quillai-network/quillshield_skills

Made for: Claude Code.

Or install proxy-upgrade-safety, the plugin that ships this one along with the rest of its 1 skill.

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 proxy-upgrade-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/quillai-network/quillshield_skills/proxy-upgrade-safety/github.svg)](https://agentmods.dev/skills/quillai-network/quillshield_skills/proxy-upgrade-safety)
Your own site
<a href="https://agentmods.dev/skills/quillai-network/quillshield_skills/proxy-upgrade-safety"><img src="https://agentmods.dev/badge/skills/quillai-network/quillshield_skills/proxy-upgrade-safety/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 proxy-upgrade-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/quillai-network/quillshield_skills/proxy-upgrade-safety"><img src="https://agentmods.dev/badge/skills/quillai-network/quillshield_skills/proxy-upgrade-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,944 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 $0.00096 $0.02944
Opus 5 $0.00048 $0.01472
Sonnet 5 $0.00019 $0.00589
Haiku 4.5 $0.00010 $0.00294

Measured 12d ago against content hash 8ae9817008e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

proxy-upgrade-safety 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.

plugins/proxy-upgrade-safety/skills/proxy-upgrade-safety/SKILL.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proxy & Upgrade Safety

Detect vulnerabilities specific to upgradeable proxy architectures — the most widely deployed contract pattern on Ethereum (54.2% of contracts). Proxy bugs cause storage corruption, unauthorized upgrades, and complete contract takeover.

When to Use

  • Auditing any contract using proxy/implementation pattern (Transparent, UUPS, Beacon, Diamond)
  • Reviewing implementation contract upgrades for storage layout compatibility
  • Analyzing delegatecall-based architectures and library usage
  • Verifying initialization safety (can initialize() be front-run?)
  • Checking Diamond (EIP-2535) facet management for selector collisions

When NOT to Use

  • Non-upgradeable contracts without proxy patterns
  • Pure logic audits without proxy architecture (use behavioral-state-analysis)
  • Token standard compliance (use external-call-safety)

Core Concept: The Delegatecall Storage Model

When Proxy calls Implementation via delegatecall:

┌─────────────────────┐     delegatecall     ┌─────────────────────┐
│       PROXY         │ ──────────────────→   │   IMPLEMENTATION    │
│                     │                       │                     │
│ Storage:            │  Implementation code  │ Code only:          │
│   slot 0: admin     │  executes in proxy's  │   No persistent     │
│   slot 1: impl addr │  storage context      │   storage           │
│   slot 2: user data │                       │                     │
│   slot 3: user data │                       │                     │
└─────────────────────┘                       └─────────────────────┘

Key Rule: The implementation's code reads/writes the PROXY's storage slots. If storage layouts don't match, data corruption occurs.

Five Vulnerability Classes

Class 1: Storage Layout Collision

Between Proxy and Implementation:

// Proxy contract
contract Proxy {
    address public admin;           // slot 0
    address public implementation;  // slot 1

    fallback() external payable {
        delegatecall(implementation);
    }
}

// Implementation contract
contract ImplementationV1 {
    uint256 public totalSupply;     // slot 0 — COLLIDES with admin!
    mapping(address => uint256) public balances; // slot 1 — COLLIDES with implementation!
}

Read the full file on GitHub · 342 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 342 lines · 96 tokens per session scan A 8ae9817008e6

Subscribe to this mod's changes

proxy-upgrade-safety is a skill published in the GitHub repository quillai-network/quillshield_skills (121 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 2,944 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

ansem-crypto

Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.

questflowai/investorskills · 41 tokens

arthur-hayes-liquidity

Use when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.

questflowai/investorskills · 38 tokens

cobie-cycle-filter

Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.

questflowai/investorskills · 35 tokens

cryptocred-structure

Use when evaluating crypto charts through a CryptoCred-style structure lens: levels, confluence, market structure, risk definition, and educational technical process.

questflowai/investorskills · 35 tokens

willy-woo-onchain

Use when evaluating Bitcoin and crypto cycles through a Willy Woo-style on-chain lens: holder behavior, realized value, supply dynamics, and on-chain demand.

questflowai/investorskills · 37 tokens

prompt-proximity-architecture

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…

elvisun/newsjack · 67 tokens