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 UnboundCompute/security-agent-skills --skill hunting-mev-and-transaction-ordering-exposuregit clone --depth 1 https://github.com/UnboundCompute/security-agent-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/unboundcompute/security-agent-skills/hunting-mev-and-transaction-ordering-exposure)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-mev-and-transaction-ordering-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-mev-and-transaction-ordering-exposure/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/unboundcompute/security-agent-skills/hunting-mev-and-transaction-ordering-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-mev-and-transaction-ordering-exposure.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 | $0.00186 | $0.02204 |
| Opus 5.5 | $0.00074 | $0.00882 |
| Sonnet 5.5 | $0.00037 | $0.00441 |
| Haiku 4.5 | $0.00019 | $0.00220 |
Grade A, and why
hunting-mev-and-transaction-ordering-exposure 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting MEV and transaction-ordering exposure: the block producer decides the order, not you
On a public blockchain the party that builds the block chooses the order of the transactions in it, and any value that depends on that order is value they, or a searcher paying them, can take. A user who submits a swap does not control whether it lands before or after someone else's, and the pending transaction sits in a public mempool where its intent is visible before it settles. That combination is the whole class. A swap with no slippage bound can be sandwiched: an attacker buys ahead of it to push the price, lets the victim's trade execute at the worse price, and sells behind it, pocketing the difference. A liquidation or an oracle-dependent action whose profit goes to whoever is sequenced first is a race the submitter usually loses to a searcher who pays for priority. And any strategy that reveals its intent in the mempool, a large trade, an arbitrage, a governance action, invites front-running. The hunt is to find on-chain actions whose outcome depends on ordering the submitter cannot control, and no protective bound. You hunt this by reading the transaction's assumptions about order and price and checking whether an adversarial ordering breaks them.
When to use
- An on-chain action's profit or safety depends on where its transaction lands in the block (a swap, liquidation, oracle update, auction bid).
- Transactions are submitted to a public mempool where their intent is visible before they settle.
- A trade may carry no slippage or deadline bound, or a protocol may assume ordering the producer controls.
Scope check
Test ordering exposure only against protocols and deployments you own or are authorized to assess, on a testnet or a local fork. Front-running, sandwiching, and priority races execute real on-chain value movement, so use test funds on a fork and never extract from or disrupt a live protocol or another party's transaction. If you can't name the authorization, stop.
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 · 140 lines · 186 tokens per session scan A ee205592f163
hunting-mev-and-transaction-ordering-exposure is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,204 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.