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/specref-v050-auditgit 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/specref-v050-audit)<a href="https://agentmods.dev/agents/verified-zkevm/evm-asm/specref-v050-audit"><img src="https://agentmods.dev/badge/agents/verified-zkevm/evm-asm/specref-v050-audit.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 5.1 | $0.00000 | $0.01534 |
| Opus 5 | $0.00000 | $0.00767 |
| Sonnet 5 | $0.00000 | $0.00307 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
specref-v050-audit 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 6d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecRef v0.5.0 audit
Scope audit for evm-asm-n9rtz, against execution-specs bd8c673
([email protected]). The baseline is [email protected]
(a0c182656). This is a classification document, not a porting claim.
Result
The diff changes 27 Amsterdam Python files (+1157/-834). The current Lean
SpecRef deliberately models the stateless input/output shell, SSZ, witness
decoding helpers, and a small runtime helper module; it cuts at
execute_new_payload_request. The agreed direction is to replace that cut
only along the concrete call graph needed by run_stateless_guest: this is a
vertical-slice reference model, not a general-purpose Lean EVM or a port of
every Amsterdam VM API. EIP-8037 and VM deltas reachable from that call graph
are real reference-model gaps; unrelated generic API reshaping is not work.
Two direct v0.5.0 changes were already present on main before this audit:
| Source delta | Current status | Evidence |
|---|---|---|
ProtocolFork: remove Constantinople/ConstantinopleFix/BPO3–BPO5; add StPetersburg |
unchanged — already v0.5.0-correct | 9d5ee19a8 updated Types.lean and the enum ordering |
payload block_access_list cap becomes MAX_BYTES_PER_TRANSACTION |
unchanged — already v0.5.0-correct | 9d4f3f995 updated Ssz.lean |
Per-Module Delta Table
| Lean module | v0.5.0 sources examined | Classification | Required follow-up |
|---|---|---|---|
Guest.lean |
stateless_guest.py |
needs-update | Add _default_failed_stateless_output; make run_stateless_guest catch decoding errors and serialize the sentinel result rather than return SpecError. |
Stateless.lean |
stateless.py |
unchanged | The diff is @final and documentation only; its only semantic enum delta is already correct in Types.lean. |
Types.lean |
stateless.py, stateless_ssz.py |
unchanged | Current enum and the payload list cap match v0.5.0. No new stateless shell fields were added. |
Ssz.lean |
stateless_ssz.py |
needs-update | Update MAX_WITNESS_NODES to 2^22, MAX_WITNESS_CODES to 2^18, MAX_BYTES_PER_CODE to 2^16, MAX_BYTES_PER_WITNESS_NODE to 2^10, and MAX_PUBLIC_KEYS to 2^15. |
SszCodec.lean |
stateless_ssz.py / remerkleable use |
unchanged | No generic codec algorithm changed; only schemas/constants changed. |
WitnessState.lean |
witness_state.py, incremental_mpt.py |
new-function-to-add | v0.5.0 adds storage_clears to compute_state_root_and_trie_changes; that method is currently behind the execution seam and has no Lean port. |
Runtime.lean |
vm/runtime.py |
unchanged | vm/runtime.py is absent from the v0.4.0→v0.5.0 diff. |
Crypto.lean |
crypto helpers | unchanged | No mapped crypto helper changed. |
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.
- 6d ago First seen · 84 lines · 0 tokens per session scan A bc476172888a
specref-v050-audit is an agent published in the GitHub repository Verified-zkEVM/evm-asm (55 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,534 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
erc-implementer
Token standard implementation specialist — ERC-20, ERC-721, ERC-1155, ERC-4626, ERC-7702.
roadmap
CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
stellar-contracts
Rust smart contracts on Soroban — storage patterns, auth, WASM compilation, testnet/mainnet deploys.
oracle-reviewer
Web3-DeFi specialist pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
Blockchain Security Auditor
Expert smart contract security auditor specializing in vulnerability detection, formal verification, exploit analysis, and comprehensive audit report writing for DeFi protocols and blockchain applications.