A custody-free workflow for deploying Solidity smart contracts to Ethereum-compatible networks. Solidity is a programming language for blockchain contracts, and deployment publishes a contract so it can run on a chosen blockchain.

Use it to generate or audit a contract, compile it, estimate deployment cost, prepare an unsigned deployment transaction, and verify the published source on Etherscan.

It organizes generation, security review, compilation, cost estimation, transaction preparation, signing, and source verification into one process. The user's wallet signs and broadcasts the transaction; the workflow does not handle private keys.

deploy — Skill for Claude Code by ChainGPT-org/chaingpt-claude-skill

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 ChainGPT-org/chaingpt-claude-skill --skill deploy

Clone the repo

git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/deploy/github.svg)](https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/deploy)

Your own site

<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/deploy"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/deploy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/deploy"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,371 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 10
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00127	$0.01371
Opus 5.5	$0.00051	$0.00548
Sonnet 5.5	$0.00025	$0.00274
Haiku 4.5	$0.00013	$0.00137

Measured 1mo ago against content hash 4534521e4915, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deploy 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 1mo 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/deploy/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainGPT Deploy Skill

You orchestrate Solidity-contract deployment to real mainnet chains through the ChainGPT plugin. This skill is mainnet-first by design — testnet is an opt-in via the network parameter, never the default behavior.

The plugin is custody-free: it builds an unsigned transaction object and returns it. The user signs and broadcasts via their own wallet (MetaMask, Rabby, hardware wallet, ERC-4337 smart account, WalletConnect). Never ask the user for a private key. Never accept one in a tool argument.

The mandatory pipeline

chaingpt_generate_contract       (optional — if generating from description)
       │
       ▼
chaingpt_audit_contract          ← MANDATORY for mainnet. Costs 1 credit. Never skip.
       │
       ▼
chaingpt_deploy_compile          ← solc 0.8.x, returns bytecode + ABI
       │
       ▼
chaingpt_deploy_estimate         ← gas + USD cost on the chosen mainnet
       │
       ▼
chaingpt_deploy_build_tx         ← MAINNET REFUSES unless acknowledgeMainnet: true
       │
       ▼
[user signs externally + broadcasts]
       │
       ▼
chaingpt_deploy_verify           ← submit source to Etherscan v2 multichain
       │
       ▼
chaingpt_deploy_verify_status    ← poll until ✓ Pass — Verified

Hard rules for mainnet

Never call chaingpt_deploy_build_tx with a mainnet network and acknowledgeMainnet=true until you have surfaced the audit report to the user. If the audit raised any high-severity finding, refuse to proceed until the user explicitly waives it.
Always surface the estimated cost in USD before the build-tx step. Pull from chaingpt_deploy_estimate and convert via the current native-coin price.
Echo the constructor args back to the user in plain English before the build-tx step. ("You're about to deploy MyToken with name='X', symbol='Y', initialSupply=1,000,000 * 10**18 to mainnet Ethereum. Confirm?")
Echo the deployer address back and remind the user it must be the wallet they control.
Default to testnet only when the user explicitly says "test", "testnet", "dry run", or names a testnet chain (sepolia, base-sepolia, etc.). Anything else is mainnet.

Read the full file on GitHub · 88 lines

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.

1mo ago First seen · 88 lines · 127 tokens per session scan A 4534521e4915

Subscribe to this mod's changes

deploy is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (7 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 1,371 once invoked, about $0.0005 per session on Opus 5.5. 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.

Claude Code Web3 and blockchain chaingpt defi ethereum mcp

deploy

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

ChainGPT Deploy Skill

The mandatory pipeline

Hard rules for mainnet

What this file has done since we first saw it

Other skills, from other repositories

analyzing-ethereum-smart-contract-vulnerabilities

pump-swarm

trading-solana

public

copy-trading

trading-evm