audit-breadth-scan

audit-breadth-scan is a skill for Claude Code, Codex from ccashwell/evm-cortex. It costs 44 tokens per session (1,303 once invoked), scanned A, original, MIT.

A broad, contract-by-contract method for reviewing a smart-contract codebase during a security audit. It checks every function once to identify areas that need a closer investigation.

In plain words
What is it for?
It helps map attack surfaces, assess contracts and functions, record risk factors, and select leads for deeper analysis.
Why use it?
It reduces the chance that an entire contract or important function is missed during an audit and helps prioritize higher-risk code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps map attack surfaces, assess contracts and functions, record risk factors, and select leads for deeper analysis.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccashwell/evm-cortex/audit-breadth-scan
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 ccashwell/evm-cortex --skill audit-breadth-scan
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex

Made for: Claude Code, Codex.

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 audit-breadth-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-breadth-scan/github.svg)](https://agentmods.dev/skills/ccashwell/evm-cortex/audit-breadth-scan)
Your own site
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/audit-breadth-scan"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-breadth-scan/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 audit-breadth-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/audit-breadth-scan"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-breadth-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,303 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.01303
Opus 5.5 $0.00018 $0.00521
Sonnet 5.5 $0.00009 $0.00261
Haiku 4.5 $0.00004 $0.00130

Measured 1mo ago against content hash a2f9e9465e29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-breadth-scan 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 1mo 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.

skills/audit-breadth-scan/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Breadth Scan

Purpose

The breadth scan is a systematic, contract-by-contract review that ensures every function is examined at least once. The goal is NOT to find every bug — it's to identify high-risk areas that warrant depth analysis.

Methodology

Pass 1: Contract-Level Assessment

For each contract in scope, assess:

## [Contract Name] — Breadth Assessment

### Overview
- Lines of code: X
- Inheritance chain: A -> B -> C
- State variables: Y
- External calls: Z

### Complexity Rating: [Low | Medium | High | Critical]
Factors: math complexity, external interactions, state machine logic,
         upgrade mechanics, cross-contract dependencies

### Initial Risk Notes
- [Any patterns that stand out]

Pass 2: Function-Level Risk Assessment

Rate each function on a risk matrix:

Risk Factor Weight Criteria
External calls High Calls to untrusted contracts
State changes Medium Modifies critical state (balances, shares)
Math operations Medium Division, multiplication with large numbers
Access control High Missing or incorrect
Value transfer Critical ETH or token movement
User input Medium Complex parameter handling
### Function Risk Matrix

| Function | External Calls | State Change | Math | Value Transfer | Risk |
|----------|---------------|--------------|------|----------------|------|
| deposit() | transferFrom | balances, supply | share calc | tokens in | HIGH |
| withdraw() | transfer, strategy | balances, supply | share calc | tokens out | CRITICAL |
| setFee() | none | fee param | none | none | LOW |
| harvest() | aave.withdraw | deployed amount | yield calc | tokens move | HIGH |

Pass 3: Attack Surface Mapping

For each high/critical risk function, map potential attack vectors:

### Attack Surface: withdraw()

**Preconditions**: User has shares, vault has assets

**Attack Vectors**:
1. Reentrancy via token callback (ERC777, hooks)
   - Mitigation: ReentrancyGuard
   - Status: CHECK if guard applied

2. Share price manipulation
   - Donate tokens to inflate totalAssets before withdraw
   - Status: CHECK virtual shares mitigation

3. Front-running
   - Sandwich attack around large withdrawals
   - Status: CHECK slippage protection

4. Oracle manipulation
   - Stale/manipulated price affects withdrawal amount
   - Status: CHECK staleness validation

5. Integer overflow/underflow
   - Share calculation edge cases
   - Status: CHECK Solidity 0.8 overflow protection

Read the full file on GitHub · 179 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. 1mo ago First seen · 179 lines · 44 tokens per session scan A a2f9e9465e29

Subscribe to this mod's changes

audit-breadth-scan is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 1,303 once invoked, about $0.0002 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 2026-09-03.