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 skills add PlamenTSV/plamen --skill cross-vm-serialization-conformancegit clone --depth 1 https://github.com/PlamenTSV/plamenWrote 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/skills/plamentsv/plamen/cross-vm-serialization-conformance)<a href="https://agentmods.dev/skills/plamentsv/plamen/cross-vm-serialization-conformance"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/cross-vm-serialization-conformance.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 | $0.01683 |
| Opus 5 | $0.00000 | $0.00842 |
| Sonnet 5 | $0.00000 | $0.00337 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
cross-vm-serialization-conformance 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 7d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CROSS_VM_SERIALIZATION_CONFORMANCE
Trigger:
NON_EVM_TARGETflag (recon detects a non-EVM destination — Solana/Bitcoin/Move/Cosmos — via 32-byte pubkey constants, base58/bech32 handling, custom account/byte encoders (account-meta packers, Borsh-style packing), or a foreign chain-id/program-id). Inject Into: breadth agent owning the cross-chain/encoding focus, and depth-external. Protocol Types: any contract that SERIALIZES data on the EVM side for consumption by a DIFFERENT VM (cross-chain bridges, general cross-chain messaging protocols, Solana/Bitcoin gateways). Added in: recall-recovery (post a ground-truth audit comparison — closes the outbound-encoding gap CROSS_CHAIN_MESSAGE_INTEGRITY does not cover; that skill covers INBOUND decode/auth only).
Why this exists
CROSS_CHAIN_MESSAGE_INTEGRITY audits messages the contract RECEIVES (decode,
auth, replay). It does NOT audit whether the bytes the contract PRODUCES on the
EVM side match the layout the destination VM expects. An EVM contract that packs
a Solana account list, a Borsh struct, or a Bitcoin script with the wrong field
width, wrong byte order, wrong flag encoding, or wrong cursor advance will ship
structurally-valid-on-EVM but corrupt-on-arrival payloads — silently breaking
cross-chain execution or corrupting permissions/amounts. This is a recurring,
general bridge bug class and is INVISIBLE to pure EVM-side reasoning.
Methodology
Step 0 — Verify the serialization SCHEME matches the destination VM (GATES Steps 1-3)
Before ANY per-field check, confirm the encoder emits the destination VM's
NATIVE wire format — not EVM ABI. Native formats: Solana/Anchor = Borsh;
Cosmos = Protobuf/Amino; Move/Sui = BCS; Bitcoin = script + varint/
CompactSize; NEAR = Borsh. EVM abi.encode/abi.encodePacked emit EVM ABI
(32-byte-word-aligned head/tail offsets, dynamic-length prefixes) — a layout
that NONE of those VMs deserialize. So if the EVM side builds a payload with
abi.encode/abi.encodePacked (or returns such a blob) that a non-EVM program
will deserialize with its native decoder, the payload is structurally
undecodable on arrival — a CONFIRMED scheme-mismatch finding regardless of
field-level correctness. Field-level conformance (Steps 1-3) is meaningless if
the whole envelope is the wrong format; only proceed once the scheme is correct.
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.
- 7d ago First seen · 101 lines · 0 tokens per session scan A 40b3421b9911
cross-vm-serialization-conformance is a skill published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,683 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 skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
prowler-tour
Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
evm-bytecode-analysis
Analyze supplied deployed EVM runtime bytecode with EVMole or guide a separate application in integrating a published EVMole Rust, Go, Python, or JavaScript binding. Use for unverified-contract inspection, ABI reconstruction from runtime code, selector discovery, storage-access analysis, EVM control-flow inspection…
talos-action-development
Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.