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 agents/verified-zkevm/evm-asm/eest-static-layoutgit clone --depth 1 https://github.com/Verified-zkEVM/evm-asmWrote 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/verified-zkevm/evm-asm/eest-static-layout)<a href="https://agentmods.dev/agents/verified-zkevm/evm-asm/eest-static-layout"><img src="https://agentmods.dev/badge/agents/verified-zkevm/evm-asm/eest-static-layout.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01144 |
| Opus 5 | $0.00000 | $0.00572 |
| Sonnet 5 | $0.00000 | $0.00229 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
eest-static-layout 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EEST Static Layout Lessons
Moved out of AGENTS.md to keep the agent guide compact. Load this when:
- changing
stateless_guest,block_state_root, BAL replay, or EEST harness memory layout; - changing static
.dataarenas used by EEST codegen programs; - adding harness filters or cap checks for EEST stateless runs.
Protocol Limits First
Do not pick static arena sizes from the failing fixture alone. Check the local
execution-specs and execution-spec-tests submodules first, then size or
gate from the protocol/test limit that actually constrains the data.
For BAL replay, Amsterdam does not use a fixed account-row cap. The rule is gas-derived:
bal_items <= block_gas_limit / 2000
bal_items = account addresses + unique storage keys
The source of truth is
execution-specs/src/ethereum/forks/amsterdam/block_access_lists.py plus
execution-specs/src/ethereum/forks/amsterdam/vm/gas.py.
This means a complete static layout is complete only relative to a declared maximum supported actual BAL item count, not merely a declared block gas limit. For the execution-specs default block gas limit of 120,000,000, the BAL item budget is 60,000. The current emitted static replay arenas are sized for 100,000 BAL items (the 200M target); the older 500,000-item/1G layout is historical. A layout with a declared capacity must cover both extreme shapes:
- many account rows, which stress
basr_*account-record arrays and the top-levelbsr_*state-change arrays; - one/few accounts with many storage keys, which stress per-account storage
replay arrays such as
baap_storage_desc,baap_storage_paths,baap_storage_delete_paths, andbaap_storage_values. Thebaap_storage_delete_pathschild is historical/probe-only in the current guest; the emittedRegionMap.dataUnionChildrenhas no such symbol.
Do not resize only the first array that failed. Follow every index that derives from the same count and resize the matching backing storage together.
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.
- 5d ago First seen · 106 lines · 0 tokens per session scan A 87f1ed508da4
eest-static-layout is an agent published in the GitHub repository Verified-zkEVM/evm-asm (55 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,144 tokens. 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.