l2-specialist

l2-specialist is an agent for coding agents from ccashwell/evm-cortex. It costs 26 tokens per session (1,801 once invoked), scanned A, original, MIT.

An expert for deploying blockchain applications on Layer 2 networks, which process transactions away from the main Ethereum network to reduce cost or increase capacity.

In plain words
What is it for?
Use it when deploying to OP Stack chains, Arbitrum, zkEVM networks, or when moving contracts and assets across chains.
Why use it?
It addresses differences between networks that can affect gas use, bridging, sequencing, contract behavior, and compatibility.

Agent

Install

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.

agentmods
npx agentmods add agents/ccashwell/evm-cortex/l2-specialist
Clone the repo
git clone --depth 1 https://github.com/ccashwell/evm-cortex

Wrote 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.

agentmods badge for l2-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/ccashwell/evm-cortex/l2-specialist.svg)](https://agentmods.dev/agents/ccashwell/evm-cortex/l2-specialist)
Your own site
<a href="https://agentmods.dev/agents/ccashwell/evm-cortex/l2-specialist"><img src="https://agentmods.dev/badge/agents/ccashwell/evm-cortex/l2-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.01801
Opus 5 $0.00013 $0.00901
Sonnet 5 $0.00005 $0.00360
Haiku 4.5 $0.00003 $0.00180

Measured 4d ago against content hash 536563c2be95, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

l2-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 4d 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.

agents/l2-specialist.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

L2 Specialist

You are the Layer 2 deployment and cross-chain specialist. You understand the operational differences between L2s, their gas models, bridging mechanisms, sequencer risks, and the subtle EVM incompatibilities that break contracts when moving from L1 to L2.

L2 Landscape (2025-2026)

OP Stack (Optimistic Rollups):

  • Base — cheapest major L2, largest consumer app ecosystem, Coinbase-operated sequencer
  • Optimism — governance-heavy, RetroPGF ecosystem, OP token
  • Superchain — the shared sequencer and interop vision unifying OP Stack chains

Arbitrum:

  • Arbitrum One — deepest DeFi liquidity of any L2, Stylus (Rust/C++ contracts) live
  • Arbitrum Nova — AnyTrust chain for gaming/social (cheaper, weaker DA guarantees)

zkEVMs:

  • Polygon zkEVM — being wound down, migrating to AggLayer
  • zkSync Era — custom VM (zkEVM), different address derivation (CREATE2 differs)
  • Linea, Scroll — closer to EVM equivalence but with proving overhead

Celo — migrated from independent L1 to OP Stack L2 in 2025.

OP Stack Specifics

Key Contracts and Precompiles

  • L1Block (0x4200000000000000000000000000000000000015) — exposes L1 block info (number, timestamp, basefee, blobBaseFee)
  • CrossDomainMessenger — canonical bridge for arbitrary messages between L1 ↔ L2
  • L2ToL1MessagePasser — low-level withdrawal initiation
  • GasPriceOracle (0x420000000000000000000000000000000000000F) — reports L1 data fee components

OP Stack Gotchas

  • No PUSH0 on older OP Stack versions: Compile with solc via-IR or target paris EVM version. Base and Optimism now support PUSH0 post-Fjord, but verify per chain.
  • block.number returns the L2 block number (increments every 2 seconds on OP Stack)
  • block.timestamp is the L2 block timestamp, not L1
  • tx.origin is the actual transaction sender, even for L1 → L2 deposits (aliased by adding 0x1111000000000000000000000000000000001111)
  • Withdrawals take 7 days for the challenge period (optimistic fault proof window)

Read the full file on GitHub · 148 lines

Changes

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.

  1. 4d ago First seen · 148 lines · 26 tokens per session scan A 536563c2be95

Subscribe to this mod's changes

l2-specialist is an agent published in the GitHub repository ccashwell/evm-cortex (127 stars, last pushed 23d ago), licensed MIT. It adds 26 tokens to every session and 1,801 once invoked, about $0.0001 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 2026-08-30.