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-prepgit 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-prep)<a href="https://agentmods.dev/skills/ccashwell/evm-cortex/audit-prep"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-prep/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-prep"><img src="https://agentmods.dev/badge/skills/ccashwell/evm-cortex/audit-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 198 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00043 | $0.01386 |
| Opus 5.5 | $0.00017 | $0.00554 |
| Sonnet 5.5 | $0.00009 | $0.00277 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
audit-prep 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Audit Preparation
Overview
Audit preparation maximizes audit value. A well-prepared codebase lets auditors focus on finding real vulnerabilities instead of deciphering intent or fighting build issues.
Audit Preparation Checklist
1. Scope Definition
## Audit Scope
### In Scope
| File | SLOC | Description |
|------|------|-------------|
| src/Vault.sol | 245 | Core vault logic, deposits/withdrawals |
| src/Strategy.sol | 189 | Yield strategy integration |
| src/Oracle.sol | 78 | Price feed wrapper |
| **Total** | **512** | |
### Out of Scope
- OpenZeppelin imports (v5.0.1) — audited separately
- Test files and deployment scripts
- Frontend / offchain components
### Deployment Chain(s)
- Ethereum Mainnet
- Arbitrum One
### EVM Version
- Shanghai (solc 0.8.24)
2. Architecture Documentation
Provide auditors with:
## Architecture
### Contract Relationships
Vault -> Strategy -> ExternalProtocol (Aave V3)
Vault -> Oracle -> Chainlink ETH/USD Feed
Governor -> Timelock -> Vault (parameter changes)
### Access Control
- Owner (2/3 multisig): pause, setFee, setStrategy
- Keeper (EOA): harvest, rebalance
- Users: deposit, withdraw, claim
### External Dependencies
| Dependency | Address | Trust Assumption |
|-----------|---------|-----------------|
| Aave V3 Pool | 0x8787... | Fully trusted |
| Chainlink ETH/USD | 0x5f4e... | Staleness checked |
| USDC | 0xA0b8... | Standard ERC20 |
### Value Flow
1. User deposits USDC -> Vault mints shares
2. Vault deploys USDC to Aave via Strategy
3. Strategy harvests yield -> increases share price
4. User redeems shares -> receives USDC + yield
3. Invariants Documentation
## Protocol Invariants
### Core Invariants (must NEVER be violated)
1. `vault.totalAssets() >= vault.totalSupply() * minSharePrice`
- Shares are always redeemable for at least their initial value
2. `sum(userShares) == vault.totalSupply()`
- No share inflation/deflation outside deposit/withdraw
3. `strategy.totalDeployed() + vault.idleAssets() == vault.totalAssets()`
- All assets accounted for
### Economic Invariants
4. Share price monotonically increases (no value extraction)
5. Withdrawal amount <= deposit amount + accumulated yield
6. Fees never exceed configured maximum (10%)
### Access Control Invariants
7. Only owner can change strategy/oracle/fees
8. Only keeper can trigger harvest
9. Users can always withdraw (no permanent lock, even if paused)
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 · 201 lines · 43 tokens per session scan A 5f53d57ff7f4
audit-prep is a skill published in the GitHub repository ccashwell/evm-cortex (131 stars, last pushed 17d ago), licensed MIT. It adds 43 tokens to every session and 1,386 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…