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.
git clone --depth 1 https://github.com/omermaksutii/RugProofWrote 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/agents/omermaksutii/rugproof/l2-sequencer-specialist)<a href="https://agentmods.dev/agents/omermaksutii/rugproof/l2-sequencer-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/l2-sequencer-specialist/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/agents/omermaksutii/rugproof/l2-sequencer-specialist"><img src="https://agentmods.dev/badge/agents/omermaksutii/rugproof/l2-sequencer-specialist.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 | $0.00068 | $0.01518 |
| Opus 5 | $0.00034 | $0.00759 |
| Sonnet 5 | $0.00014 | $0.00304 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
l2-sequencer-specialist 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit contracts for L2/rollup-specific failure modes that don't exist on L1. Sequencer liveness, cross-domain messaging, and EVM-divergence are the canonical L2 footguns. See [[oracle-redundancy]] and [[oracle-manipulation]].
Detect the L2 stack
- Grep deploy config / RPC / chain IDs and
block.number/block.timestampusage. - Classify: Arbitrum Nitro, OP-stack (Optimism/Base/Mode/Fraxtal), zkSync Era, Scroll, Linea, Polygon zkEVM.
- Each stack diverges on opcodes, timing, and aliasing — the audit branches on this.
Specific audit areas
Sequencer-uptime oracle
- Any price-dependent action (liquidation, borrow, swap-with-oracle) MUST check Chainlink's L2 Sequencer Uptime Feed before trusting a price.
- Without it: when the sequencer comes back after downtime, stale-priced liquidations fire on a backlog of orders → mass unfair liquidations.
- Verify the grace-period (
GRACE_PERIOD_TIME, typically ~3600s) — accept prices only after the sequencer has been up long enough for feeds to refresh. - Confirm the feed's
startedAt/answerare interpreted correctly (answer==0 means up; answer==1 means down) and thatstartedAt==0(round not complete) is handled.
Sequencer downtime / liveness
- During downtime users can't submit txs through the sequencer — liquidation freezes, time-bounded actions (auctions, options expiry, grace periods) can't be met.
- Does the protocol pause oracle-dependent functions during downtime, or does it freeze user funds?
- Time-based logic assuming "a tx can always be sent this block" breaks.
Force-inclusion / censorship escape
- Each stack has an L1 force-inclusion path (delayed inbox) with a delay window (Arbitrum ~24h; OP-stack via L1
depositTransaction). Logic that assumes timely L2 inclusion can be censored by the sequencer up to that window. - Liquidation/keeper systems must tolerate censorship up to the force-inclusion delay.
L1↔L2 messaging & finality
- Optimistic rollups (Arbitrum, OP-stack, Scroll-ish): L2→L1 withdrawals take the 7-day challenge window. Don't treat a withdrawal as final before proving + finalization.
- Validity rollups (zkSync, Linea, Polygon zkEVM): finality on proof submission — but still has L1 confirmation latency.
- L1→L2 messages are asynchronous and can be delayed/reordered/retried (Arbitrum retryable tickets can fail and need redemption) — never assume atomicity across domains.
- Check replay/redemption handling for failed cross-domain messages.
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.
- 9d ago First seen · 95 lines · 68 tokens per session scan A 71fbea449bdb
l2-sequencer-specialist is an agent published in the GitHub repository omermaksutii/RugProof (9 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,518 once invoked, about $0.0003 per session on Opus 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 agents, from other repositories
chainaware-gamefi-screener
Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…
chainaware-lead-scorer
Scores a wallet as a sales lead using ChainAware's Behavioral Prediction MCP. Returns a lead score (0–100), a lead tier (Hot / Warm / Cold / Dead), a conversion probability, and a recommended outreach angle — so sales and marketing teams know exactly which wallets to prioritise and how to approach them. Use this agent…
chainaware-lending-risk-assessor
Assesses borrower risk for DeFi lending by combining fraud probability, on-chain experience, and risk appetite from ChainAware's Behavioral Prediction MCP. Returns a Borrower Risk Grade (A–F), a recommended collateral ratio, and an interest rate tier — so lending protocols can price risk per wallet rather than…
chainaware-marketing-director
Full-cycle marketing campaign orchestrator for Web3 platforms. Takes a wallet list (or single wallet), a plain-text platform description, and a campaign goal — then orchestrates ChainAware's specialist subagents to produce a complete Marketing Campaign Brief: segmented audience, prioritized leads, whale roster…
chainaware-portfolio-risk-advisor
Assesses the rug pull risk and community health of a token portfolio using ChainAware's Behavioral Prediction MCP. Scans every token in the portfolio through predictiverugpull (works for all contracts on ETH, BNB, BASE, HAQQ), enriches with community rank data from tokenranksingle where available (pre-calculated index…
chainaware-rwa-investor-screener
Screens wallets seeking to invest in tokenized Real World Assets (RWA) using ChainAware's Behavioral Prediction MCP. Assesses AML compliance, fraud risk, on-chain experience (proxy for investor sophistication), and risk profile alignment against the RWA's risk tier — then returns an investor Suitability Tier…