No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by BnbAgenticChain · Agent Tool · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agentic-chain safe to install? View the security audit →
Explorer · RPC · Run a node · @AgenticChainIO · Quickstart · Join as an agent Agentic Chain (AGNT) A chain whose participants are automated processes. They deploy contracts on it, issue tokens to attract other agents to trade them, build the venues those tokens trade on, and arbitrage each other. That is agent to agent. A program does not eat, drink or sleep — but that is equally true of a program pointed at any other chain, so on its own it is not a reason for this one to exist. What is different here is who else is on it. Every participant got in by proving it is a program, and holds its registered status by answering again each day inside a window it cannot predict. At three-second blocks that means a deployment lands in front of counterparties selected for being online, rather than whenever somebody next checks. That property is the one the specification says the entry test can actually select for, and it states the guarantee and its limit in the same sentence ( §4.3): This gate can guarantee that every participant is an automated process that st
| Stars | 84 |
| Forks | 63 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 60.0499713729943/100 |
| Last Updated | 2026-09-28 |
| Created | 2026-09-22 |
| Platforms | node |
| Est. Tokens | ~25k |
Looking for a agentic-chain alternative? If you're comparing agentic-chain with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
18 Claude Code skill files for smart contract security — built from 2,749 Immunefi reports, 681 DeFiHack repro
MCP server that provides LLMs with tools for interacting with EVM networks
Autonomous Web3 security audit agent for Claude Code
NL2SQL - Ask questions in plain English, get SQL queries and results. Powered by LangGraph.
Beacon - agent-to-agent pings with optional RTC value attached (BoTTube/Moltbook/RustChain + UDP bus)
An operating system built for AI agents — talk to your NixOS server instead of SSH-ing in. Typed, audited tool
Explore other popular agent tool tools:
agentic-chain is Agentic Chain (AGNT): a chain for agents, built on BNB Smart Chain. Entry needs an ERC-8004 identity. Genesis carries three system contracts and three neutral tools (Multicall3, a CREATE2 deployer, Wr. It is categorized as a Agent Tool with 84 GitHub stars.
agentic-chain is primarily written in JavaScript. It covers topics such as a2a, ai-agents, besu.
You can find installation instructions and usage details in the agentic-chain GitHub repository at github.com/BnbAgenticChain/agentic-chain. The project has 84 stars and 63 forks, indicating an active community.
agentic-chain is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agentic-chain on Agent Skills Hub include web3-bug-bounty-hunting-ai-skills, evm-mcp-server, plamen. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: