harness-web3

Enforce governance rules for blockchain-integrated AI systems in the harness web3 module.

3|1|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/unclenate/auto-harness --skill harness-web3
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: harness-web3
Source: https://github.com/unclenate/auto-harness/tree/main/platform/skills/harness-web3
Command: npx skills add https://github.com/unclenate/auto-harness --skill harness-web3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents Web3 AI systems from making risky or incorrect decisions when data is missing, evidence is unclear, rate limits are exceeded, or transaction-writing actions could be irreversible.

Core Features & Use Cases

  • UNKNOWN correctness discipline: Forces on-chain and external-data signals to return UNKNOWN (never coerced to 0/null/neutral) and to remain visible, preserving scoring integrity in production.
  • Rate limit budget enforcement: Ties every external call to the declared budget in docs/web3/chain-config.md, requiring updates before adding new API usage.
  • Evidence-required risk scoring: Requires each risk/score to cite specific on-chain evidence sources (RPC/BaseScan endpoints) and document availability assumptions in ADRs.
  • Irreversibility gates for Tier 5 actions: Blocks automatic execution of deployment, signing/submission to mainnet, wallet/key changes, and ABI changes, requiring explicit human authorization and second-human sign-off patterns.

Quick Start

Install harness-governance and harness-web3 in your project, then use the skill’s rules to ensure any Web3 scoring pipeline returns UNKNOWN when data cannot be computed and never auto-executes Tier 5 transaction-signing workflows.

Frequently Asked Questions about harness-web3

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent my Web3 AI agent from auto-executing irreversible smart contract transactions?

To prevent irreversible Web3 AI actions, enforce governance rules that block automatic execution of deployment, mainnet signing, and ABI changes by requiring explicit human authorization and second-human sign-off for Tier 5 transaction actions.

How should Web3 risk scoring handle missing or unavailable on-chain data?

Web3 risk scoring should handle missing on-chain data by enforcing UNKNOWN propagation, ensuring signals return UNKNOWN rather than being coerced to 0 or null to preserve scoring integrity in production pipelines.

What is the best way to manage API rate limits for blockchain analytics workflows?

The best way to manage blockchain API rate limits is to tie every external call to a declared rate limit budget in a chain configuration file, requiring updates before adding new API usage to maintain budget accounting.

How do I document evidence requirements for smart contract safety risk flags?

To document smart contract safety risk flags, require each risk score to cite specific on-chain evidence sources like RPC or BaseScan endpoints and document availability assumptions in Architecture Decision Records.

Can I use Web3 governance rules for wallet signing and key change workflows?

Yes, you can use Web3 governance rules for wallet signing and key change workflows by applying irreversibility gates that require human-gated controls to block automatic execution of these Tier 5 transaction actions.