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-execution-seam-scopegit 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-execution-seam-scope)<a href="https://agentmods.dev/agents/verified-zkevm/evm-asm/specref-execution-seam-scope"><img src="https://agentmods.dev/badge/agents/verified-zkevm/evm-asm/specref-execution-seam-scope.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 | $0.04101 |
| Opus 5 | $0.00000 | $0.02050 |
| Sonnet 5 | $0.00000 | $0.00820 |
| Haiku 4.5 | $0.00000 | $0.00410 |
Grade A, and why
specref-execution-seam-scope 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecRef execution seam: scope and decomposition
Scoping document for bead evm-asm-s1d19 (P0): replace SpecRef's
placeholder executeAlwaysOk with a real ExecutionSeam, so that
verify_stateless_new_payload's successful_validation verdict matches
execution-specs @ bd8c673 ([email protected]) on every fixture —
including the ~974 succ=0 EEST fixtures where SpecRef currently
diverges (issue #10141). Realizes obligations #7 (MPT verification
of the pre-state witness) and #8 (post-state root), both of which
sit behind the stubbed seam today.
Companion to the evm-asm-n9rtz v0.5.0 audit
(docs/agents/specref-v050-audit.md); the boundary with n9rtz is
recorded in §5.
1. The gap
EvmAsm/Stateless/SpecRef/Stateless.lean cuts the port of
stateless.py::verify_stateless_new_payload at the call to
execute_new_payload_request (stateless.py:378 in the v0.4.0 line
numbering; the function is unchanged at bd8c673). Everything above
the cut (chain-config validation, header-chain validation, witness DB
assembly, NPR root, SSZ shell) is a real port; the call itself is the
parameter execute : ExecutionSeam, defaulting to
executeAlwaysOk := fun _ => .ok (). Consequences:
successfulValidationis alwaystrue, so SpecRef wrongly accepts every block whose real EVM execution fails.- The pre-state witness is assembled (
build_node_db, keccak-keyed) but never authenticated againstparent_header.stateRoot— MPT witness verification (obligation #7) never happens. - The post-state root is never recomputed or compared to
header.state_root(obligation #8). scripts/eest-specref-check.shcan gate only the pre-execution regions (root,tail); the verdict byte (succ) is explicitly ungated.
2. What the seam must contain (execution-specs @ bd8c673)
The Python call graph below the cut, with sizes (lines at bd8c673,
src/ethereum/forks/amsterdam/):
| Layer | Source | Size | Content |
|---|---|---|---|
| Seam entry | execution_engine/new_payload.py::execute_new_payload_request |
169 | empty-tx check; block-hash check; versioned-hash check; payload→Block; execute_block |
| Payload→header/block | execution_engine/validation_helpers.py |
106 | _payload_header / _payload_block (needs unsecured trie roots over txs/withdrawals, compute_requests_hash, BAL keccak) |
| Block shell | fork.py::execute_block (+validate_header, check_transaction, receipts, system txs) |
~1,258 | RLP size cap, header validation, apply_body, eight post-execution root/gas/bloom checks incl. state_root |
| Witness reads | witness_state.py (WitnessState methods) |
307 | get_account_optional / get_storage / get_code / account_has_storage / compute_state_root_and_trie_changes |
| Witness trie | incremental_mpt.py |
1,040 | read side: compact_to_nibbles, _decode_witness_node, _resolve_child_ref, decode_witness_to_mpt; write side: mpt_set/mpt_delete/mpt_root, node encoding |
| State tracking | state_tracker.py, block_access_lists.py |
928 + 744 | BlockState/TransactionState journaling, BAL builder, EIP-8037 state-gas hooks |
| Transactions | transactions.py |
1,078 | envelope decoding, recover_sender (via supplied public keys), intrinsic costs, EIP-8037 TX_MAX_GAS_LIMIT |
| EVM | vm/ (interpreter.py, gas.py, instructions/*, eoa_delegation.py, memory.py, stack.py, runtime.py, exceptions.py) |
~5,900 | the interpreter and all 149 opcodes, incl. CALL/CREATE family, EIP-7702 one-hop delegation, EIP-8037 two-dimensional gas |
| Precompiles | vm/precompiled_contracts/ |
~2,300 | all 20: ecrecover, sha256, ripemd160, identity, modexp, bn128 (3), blake2f, KZG point-eval, bls12-381 (7+), p256verify |
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 · 222 lines · 0 tokens per session scan A 7f2c63e6f7e8
specref-execution-seam-scope 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 4,101 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
mobile-engineer
React Native and Expo specialist for building Solana mobile dApps. Handles mobile wallet adapter integration, transaction signing UX, deep linking, and mobile-specific performance optimization. Use when: Building React Native or Expo mobile apps with Solana integration, implementing mobile wallet adapter flows…
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.