pentagonal

A tool for generating, checking, and deploying smart contracts, which are programs that run on blockchains. It works with Solidity and Solana Anchor/Rust contracts and supports EVM networks and Solana.

In plain words
What is it for?
Use it to create ERC20, ERC721, or SPL tokens, generate other contract programs, audit existing code for vulnerabilities, and deploy contracts to EVM or Solana chains.
Why use it?
It brings contract creation, security review, and deployment tasks into one workflow. This can help identify bugs before a contract is released on a blockchain.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pentagonal-ai/pentagonal/openclaw-skill
Any agent
npx skills add Pentagonal-ai/pentagonal --skill openclaw-skill
Clone the repo
git clone --depth 1 https://github.com/Pentagonal-ai/pentagonal

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00036 $0.00857
Opus 5 $0.00018 $0.00428
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00004 $0.00086

Measured yesterday against content hash 28fdc9111697, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pentagonal scanned grade A with 1 finding 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 yesterday.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/pentagonal-audit.sh, scripts/pentagonal-compile.sh, scripts/pentagonal-faucet.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

bins: ["curl", "jq"]
openclaw-skill/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pentagonal — Smart Contract Security & Deployment

Use this skill when the user asks about:

  • Auditing smart contracts for vulnerabilities
  • Generating Solidity or Anchor/Rust smart contracts
  • Deploying contracts to EVM or Solana chains
  • Checking contract security or finding bugs
  • Creating ERC20/ERC721/SPL tokens

Setup

Set PENTAGONAL_API_URL to your Pentagonal instance (default: https://www.pentagonal.ai).

export PENTAGONAL_API_URL="https://www.pentagonal.ai"

Capabilities

1. Generate Smart Contracts

Generate AI-powered smart contracts from natural language descriptions.

# EVM (Solidity)
bash scripts/pentagonal-generate.sh --chain ethereum --prompt "ERC20 token with burn and pause"

# Solana (Anchor/Rust)
bash scripts/pentagonal-generate.sh --chain solana --type program --prompt "Escrow program with time lock"

# Solana (SPL Token)
bash scripts/pentagonal-generate.sh --chain solana --type token --prompt "Governance token with 1B supply"

2. Audit Smart Contracts

Run AI-powered security audits on existing contract code.

# Audit from file
bash scripts/pentagonal-audit.sh --file ./contracts/MyToken.sol

# Audit from stdin
cat contract.sol | bash scripts/pentagonal-audit.sh --stdin

# Audit with specific focus
bash scripts/pentagonal-audit.sh --file ./contracts/MyToken.sol --focus "reentrancy,access-control"

The audit returns findings classified by severity:

  • 🔴 Critical — Must fix before deployment
  • 🟠 High — Likely exploitable
  • 🟡 Medium — Potential issue
  • 🔵 Low — Best practice suggestion
  • Info — Informational note

3. Deploy Contracts

Deploy compiled contracts to supported chains.

Supported EVM Chains:

  • Ethereum (Mainnet, Sepolia)
  • Polygon (Mainnet, Amoy)
  • BSC (Mainnet, Testnet)
  • Arbitrum (Mainnet, Sepolia)
  • Base (Mainnet, Sepolia)
  • Optimism (Mainnet, Sepolia)
  • Avalanche (Mainnet, Fuji)

Supported Solana:

  • SPL Token creation (Devnet, Mainnet)
  • Anchor program deployment (via Solana Playground guided walkthrough)

Read the full file on GitHub · 119 lines

Files

What ships with it

5 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. yesterday First seen · 119 lines · 36 tokens per session scan A 28fdc9111697

Subscribe to this mod's changes

pentagonal is a skill published in the GitHub repository Pentagonal-ai/pentagonal (1 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 857 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories