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 agentmods add skills/0xlayerghost/solidity-agent-kit/defi-securitynpx skills add 0xlayerghost/solidity-agent-kit --skill defi-securitygit clone --depth 1 https://github.com/0xlayerghost/solidity-agent-kitWhat 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 | $0.00063 | $0.01509 |
| Opus 5 | $0.00032 | $0.00754 |
| Sonnet 5 | $0.00013 | $0.00302 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
defi-security 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 2d 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.
This is a copy
94% identical to defi-security — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeFi Security Principles
Language Rule
- Always respond in the same language the user is using. If the user asks in Chinese, respond in Chinese. If in English, respond in English.
Scope: Only applicable to DeFi projects (DEX, lending, staking, LP, yield). Non-DeFi projects can ignore this skill.
Protection Decision Rules
| Threat | Required Protection |
|---|---|
| Whale manipulation | Daily transaction caps + per-tx amount limits + cooldown window |
| MEV / sandwich attack | EOA-only checks (msg.sender == tx.origin), or use commit-reveal pattern |
| Arbitrage | Referral binding + liquidity distribution + fixed yield model + lock period |
| Reentrancy | ReentrancyGuard on all external-call functions (see solidity-security skill) |
| Flash loan attack | Check block.number change between operations, or use TWAP pricing |
| Price manipulation | Chainlink oracle or TWAP — never rely on spot AMM reserves for pricing |
| Approval exploit | Use safeIncreaseAllowance / safeDecreaseAllowance, never raw approve for user flows |
| Governance attack | Voting requires snapshot + minimum token holding period; timelock ≥ 48h on proposal execution |
| ERC4626 inflation attack | First deposit must enforce minimum amount or use virtual shares to prevent share dilution via rounding |
| Cross-vault trust bypass | Router/Registry relay must verify vault authorization; never trust caller identity inside flash loan callbacks — EVMbench/noya H-08 |
| Collateral ownership exploit | Liquidation/staking operations must verify actual NFT/collateral ownership — EVMbench/benddao |
| Bonding curve manipulation | ID/pricing params in create operations must be fully determined before external calls — EVMbench/phi H-06 |
DEX pair _transfer TOCTOU |
Never distinguish operation type by balance/reserve checks in _transfer — both directions are exploitable: buy vs removeLiquidity (pair→user) and sell vs addLiquidity (user→pair); use address whitelist only; new projects prefer Uniswap V4 Hook |
| Per-address state bypass | Any mapping(address => ...) restriction (cooldown, max tx, max balance) can be bypassed via multi-address or transfer-then-trade; propagate restriction state on wallet-to-wallet transfers using max(_lastTxTime[to], _lastTxTime[from]) — never block.timestamp (griefing) or direct assignment (overwrite shortening) |
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.
- 2d ago First seen · 88 lines · 63 tokens per session scan A 0c110bf7ba0e
defi-security is a skill published in the GitHub repository 0xlayerghost/solidity-agent-kit (4 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 1,509 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to defi-security, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
web3-bug-classes
Complete reference for all 10 DeFi smart contract bug classes. Use this when hunting for specific vulnerability types, need attack patterns for accounting desync, access control, incomplete path, off-by-one, oracle manipulation, ERC4626 vaults, reentrancy, flash loans, signature replay, or proxy/upgrade bugs.
web3-methodology-research
External research synthesis from Trail of Bits, SlowMist, ConsenSys, Immunefi, and Cyfrin. Use this for advanced audit methodology, Echidna/Medusa fuzzing setup, Slither custom detector writing, attack pattern deep dives, or the 4-phase learning roadmap.
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.
web3-triage-report
Bug triage validation system, Immunefi report format, and 20 real paid bounty examples dissected. Use this when validating a finding before submitting, writing an Immunefi report, checking if a bug is actually valid, or studying real examples of paid vulnerabilities.
web3-case-study-role-misconfig
Case study - role misconfiguration bug class applied to a yield aggregator protocol. Use as a template for applying all 10 bug classes to a single target.
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.