sails-ethexe-architecture

sails-ethexe-architecture is a skill for Claude Code from gear-foundation/vara-skills. It costs 59 tokens per session (1,128 once invoked), scanned A, original, MIT.

An architecture-planning guide for Sails applications that use ethexe, a feature for connecting Gear programs with Ethereum-compatible systems. It covers how services communicate, accept payments, emit events, and expose Solidity interfaces.

In plain words
What is it for?
Use it to turn an approved specification into an ethexe architecture document before coding, including transport choices, payable methods, events, generated interfaces, and ethexe constraints.
Why use it?
It helps prevent designs that work for ordinary Gear or Vara applications but fail when Ethereum-style access or payments are required.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vara-skills plugin — 26 skills shipped together

Good fit Use it to turn an approved specification into an ethexe architecture document before coding, including transport choices, payable methods, events, generated interfaces, and ethexe constraints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gear-foundation/vara-skills/sails-ethexe-architecture
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.

Any agent
npx skills add gear-foundation/vara-skills --skill sails-ethexe-architecture
Clone the repo
git clone --depth 1 https://github.com/gear-foundation/vara-skills

Made for: Claude Code.

Or install vara-skills, the plugin that ships this one along with the rest of its 26 skills.

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 sails-ethexe-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-ethexe-architecture/github.svg)](https://agentmods.dev/skills/gear-foundation/vara-skills/sails-ethexe-architecture)
Your own site
<a href="https://agentmods.dev/skills/gear-foundation/vara-skills/sails-ethexe-architecture"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-ethexe-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sails-ethexe-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/gear-foundation/vara-skills/sails-ethexe-architecture"><img src="https://agentmods.dev/badge/skills/gear-foundation/vara-skills/sails-ethexe-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.01128
Opus 5 $0.00030 $0.00564
Sonnet 5 $0.00012 $0.00226
Haiku 4.5 $0.00006 $0.00113

Measured 12d ago against content hash c4763412e82b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sails-ethexe-architecture 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 12d 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.

skills/sails-ethexe-architecture/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sails Ethexe Architecture

Goal

Turn an approved spec into an ethexe-specific architecture artifact before implementation, covering transport strategy, payable design, event model, Solidity interface generation, and the constraints the ethexe feature imposes.

If the app does NOT need ethexe, use ../sails-architecture/SKILL.md instead.

Inputs

  • ../../references/sails-ethexe-patterns.md — ethexe diff table, transport rules, type requirements, gated syscalls
  • ../../references/sails-header-wire-format.md — interface ID stability, entry ID derivation
  • ../../references/sails-idl-v2-syntax.md — IDL v2 annotations
  • ../../assets/architecture-template.md
  • ../../references/vara-domain-overview.md
  • ../../references/sails-program-and-service-architecture.md
  • ../../references/gear-messaging-and-replies.md

Write the result to docs/plans/YYYY-MM-DD-<topic>-architecture.md.

Architecture Decisions Specific to Ethexe

Transport Strategy

The architecture must name the transport per service and per method:

Pattern When to use
Dual transport (default #[export]) Methods callable from both Gear programs and EVM
Scale-only (#[export(scale)]) Internal program-to-program calls, no EVM exposure needed
Ethabi-only (#[export(ethabi)]) Methods only meaningful from EVM side
Payable (#[export(ethabi, payable)]) Methods that accept value — requires ethabi

Document the transport choice per method in the architecture artifact. Dual transport is the default but not always desirable — scale-only methods reduce the ABI surface.

Payable Design

  • Which methods accept value? Name each one.
  • What happens to received value? (stored in program, forwarded, refunded on error?)
  • Non-payable methods panic if value > 0 — is this acceptable for all non-payable paths?
  • Constructors can also be payable — document if the program requires initial funding.

Event Model

Decide between:

  • emit_event() — standard Gear event (visible to Gear tooling, explorers)
  • emit_eth_event() — Ethereum-style event (visible to EVM tooling, indexed topics)
  • Both — if the same event must be visible to both ecosystems (requires two separate emissions)

Read the full file on GitHub · 104 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 104 lines · 59 tokens per session scan A c4763412e82b

Subscribe to this mod's changes

sails-ethexe-architecture is a skill published in the GitHub repository gear-foundation/vara-skills (17 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,128 once invoked, about $0.0003 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.