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 austintgriffith/evm-audit-skills --skill evm-audit-mastergit clone --depth 1 https://github.com/austintgriffith/evm-audit-skillsWrote 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/austintgriffith/evm-audit-skills/evm-audit-master)<a href="https://agentmods.dev/skills/austintgriffith/evm-audit-skills/evm-audit-master"><img src="https://agentmods.dev/badge/skills/austintgriffith/evm-audit-skills/evm-audit-master/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/austintgriffith/evm-audit-skills/evm-audit-master"><img src="https://agentmods.dev/badge/skills/austintgriffith/evm-audit-skills/evm-audit-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.02833 |
| Opus 5.5 | $0.00015 | $0.01133 |
| Sonnet 5.5 | $0.00008 | $0.00567 |
| Haiku 4.5 | $0.00004 | $0.00283 |
Grade A, and why
evm-audit-master 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 2mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EVM Smart Contract Security Audit — Master Index
How To Use
- Always load this skill first for any EVM smart contract audit
- Read the contract(s) under audit
- Use the routing table below to load relevant specialized skills
- Walk through each loaded skill's checklist systematically
All 20 Skills — Definitive Index
| # | Skill | Description | Items |
|---|---|---|---|
| 1 | evm-audit-master | This file. Routing table, methodology, source attribution. Load first. | — |
| 2 | evm-audit-general | Cross-cutting issues: storage pointers, struct deletion, mixed accounting, merkle proofs, msg.value in loops, try/catch, delegatecall, upgrades, downcasting, rebasing tokens, fee-on-transfer, ERC4626 inflation attack | 46+ |
| 3 | evm-audit-precision-math | Division-before-multiplication, rounding to zero, precision scaling mismatches, downcast overflow, rounding direction (protocol vs user), decimal assumption errors | 23+ |
| 4 | evm-audit-erc20 | Fee-on-transfer, rebasing, ERC777 hooks, approve race conditions, zero-transfer reverts, pausable tokens, deny lists (USDC), deflationary/inflationary tokens, multiple-address tokens | 27+ |
| 5 | evm-audit-defi-amm | AMM/DEX slippage attacks, CLM vulnerabilities (TWAP bypass, sandwich via owner functions, stuck tokens, stale approvals, retrospective fees), UniswapV3/V4 hooks, fee tier issues | 30+ |
| 6 | evm-audit-defi-lending | Liquidation vulnerabilities (20+ patterns), lending/borrowing attacks, bad debt handling, partial liquidation bypasses, front-run prevention, collateral hiding, insurance fund edge cases, non-18 decimal failures | 33+ |
| 7 | evm-audit-defi-staking | Liquid staking, restaking, EigenLayer integration, stakedButUnverified accounting, Beacon Chain proof verification (Deneb), validator front-running, cooldown exploitation, reward calculation precision | 30+ |
| 8 | evm-audit-erc4626 | Share/asset conversion, inflation attack, virtual shares, deposit/withdraw rounding, first depositor attack, multi-step operations, 85+ patterns from Dacian's ERC4626 primer | 42+ |
| 9 | evm-audit-erc4337 | Account abstraction, smart wallet security, paymaster attacks, session key exploits, UserOperation validation, bundler trust assumptions, gas griefing | 18+ |
| 10 | evm-audit-bridges | Cross-chain bridge security, LayerZero V2, CCIP, Wormhole, Across, message replay, finality assumptions, relayer trust, adapter pattern issues | 32+ |
| 11 | evm-audit-proxies | UUPS deep dive (uninitialized implementation, delegatecall to selfdestruct, broken upgrade chain, authorization schema changes), Transparent proxy, Beacon, Diamond, storage collision, immutable variable loss | 18+ |
| 12 | evm-audit-signatures | Signature replay (missing nonce, cross-chain, missing parameter, no expiration), ecrecover return check, signature malleability, EIP-712 conformance, ECDSA library version requirements | 19+ |
| 13 | evm-audit-governance | DAO attacks (flash-loan + delegation bypass, voting power destruction, totalPower manipulation, snapshot staleness, quorum impossibility, treasury delegation abuse, restriction bypass, token recycling, proposal deadlines, pre-mint exploitation), proposal execution ordering, fake proposals via CREATE2, multi-sig quorum failure | 23+ |
| 14 | evm-audit-oracles | Chainlink integration (stale prices, L2 sequencer, per-feed heartbeats, decimal assumptions, wrong addresses, front-running, unhandled reverts, depeg detection, minAnswer/maxAnswer), Sigma Prime patterns (spot price manipulation, homegrown oracle risks, gas congestion, hardcoded pegs, TWAP limitations) | 29+ |
| 15 | evm-audit-assembly | Inline assembly memory corruption (external call overwrites, stale FMPA assumptions, insufficient allocation), call to non-existent contracts, overflow/underflow without protection, uint128 overflow evading 256-bit detection | 27+ |
| 16 | evm-audit-chain-specific | L2/alt-chain quirks — Arbitrum, Optimism, zkSync, Blast, BSC, Polygon. Sequencer downtime, different opcodes, gas pricing differences, precompile availability, block time assumptions | 29+ |
| 17 | evm-audit-flashloans | Flash loan attack patterns, oracle manipulation via flash loans, governance flash loan voting, flash mint issues, composability risks | 15+ |
| 18 | evm-audit-erc721 | NFT-specific issues: onERC721Received callbacks, enumeration DoS, royalty enforcement, metadata manipulation, batch mint edge cases | 20+ |
| 19 | evm-audit-dos | Denial of service patterns: unbounded loops, block gas limit, self-destruct force-send, storage deletion costs, griefing via revert, return data bombs | 18+ |
| 20 | evm-audit-access-control | Access control patterns: missing modifiers, 2-step ownership, role-based permissions, emergency pause, time delays, admin overpowers | 15+ |
What ships with it
1 file 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.
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.
- 2mo ago First seen · 144 lines · 38 tokens per session scan A a47b92ce0327
evm-audit-master is a skill published in the GitHub repository austintgriffith/evm-audit-skills (12 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,833 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 2026-08-31.
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…