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.
npx skills add ccashwell/evm-cortex --skill audit-breadth-scangit clone --depth 1 https://github.com/ccashwell/evm-cortexWrote 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/skills/ccashwell/evm-cortex/audit-breadth-scan)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01303 |
| Opus 5.5 | $0.00018 | $0.00521 |
| Sonnet 5.5 | $0.00009 | $0.00261 |
| Haiku 4.5 | $0.00004 | $0.00130 |
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.
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
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.
- 1mo ago First seen · 179 lines · 44 tokens per session scan A a2f9e9465e29
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.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…